更新算法模版

This commit is contained in:
johnjim0816
2022-11-06 12:15:36 +08:00
parent 466a17707f
commit dc78698262
256 changed files with 17282 additions and 10229 deletions

View File

@@ -0,0 +1,19 @@
general_cfg:
algo_name: Sarsa
device: cpu
env_name: CliffWalking-v0
load_checkpoint: true
load_path: Train_CliffWalking-v0_Sarsa_20221030-021146
max_steps: 200
mode: test
save_fig: true
seed: 1
show_fig: false
test_eps: 20
train_eps: 400
algo_cfg:
epsilon_decay: 300
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.95
lr: 0.1

View File

@@ -0,0 +1,24 @@
2022-10-30 02:12:06 - r - INFO: - n_states: 48, n_actions: 4
2022-10-30 02:12:06 - r - INFO: - Start testing!
2022-10-30 02:12:06 - r - INFO: - Env: CliffWalking-v0, Algorithm: Sarsa, Device: cpu
2022-10-30 02:12:06 - r - INFO: - Episode: 1/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 2/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 3/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 4/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 5/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 6/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 7/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 8/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 9/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 10/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 11/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 12/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 13/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 14/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 15/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 16/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 17/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 18/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 19/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Episode: 20/20, Reward: -15.00, Steps:15
2022-10-30 02:12:06 - r - INFO: - Finish testing!

View File

@@ -0,0 +1,19 @@
general_cfg:
algo_name: Sarsa
device: cpu
env_name: Racetrack-v0
load_checkpoint: true
load_path: Train_Racetrack-v0_Sarsa_20221030-021315
max_steps: 200
mode: test
save_fig: true
seed: 10
show_fig: false
test_eps: 20
train_eps: 400
algo_cfg:
epsilon_decay: 200
epsilon_end: 0.01
epsilon_start: 0.9
gamma: 0.99
lr: 0.1

View File

@@ -0,0 +1,24 @@
2022-10-30 02:13:47 - r - INFO: - n_states: 4, n_actions: 9
2022-10-30 02:13:47 - r - INFO: - Start testing!
2022-10-30 02:13:47 - r - INFO: - Env: Racetrack-v0, Algorithm: Sarsa, Device: cpu
2022-10-30 02:13:47 - r - INFO: - Episode: 1/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Episode: 2/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Episode: 3/20, Reward: 2.00, Steps:8
2022-10-30 02:13:47 - r - INFO: - Episode: 4/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Episode: 5/20, Reward: -12.00, Steps:12
2022-10-30 02:13:47 - r - INFO: - Episode: 6/20, Reward: -49.00, Steps:29
2022-10-30 02:13:47 - r - INFO: - Episode: 7/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Episode: 8/20, Reward: -17.00, Steps:17
2022-10-30 02:13:47 - r - INFO: - Episode: 9/20, Reward: 4.00, Steps:6
2022-10-30 02:13:47 - r - INFO: - Episode: 10/20, Reward: -17.00, Steps:17
2022-10-30 02:13:47 - r - INFO: - Episode: 11/20, Reward: 2.00, Steps:8
2022-10-30 02:13:47 - r - INFO: - Episode: 12/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Episode: 13/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Episode: 14/20, Reward: 2.00, Steps:8
2022-10-30 02:13:47 - r - INFO: - Episode: 15/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Episode: 16/20, Reward: -34.00, Steps:24
2022-10-30 02:13:47 - r - INFO: - Episode: 17/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Episode: 18/20, Reward: 5.00, Steps:5
2022-10-30 02:13:47 - r - INFO: - Episode: 19/20, Reward: 5.00, Steps:5
2022-10-30 02:13:47 - r - INFO: - Episode: 20/20, Reward: 3.00, Steps:7
2022-10-30 02:13:47 - r - INFO: - Finish testing!

Binary file not shown.

After

Width:  |  Height:  |  Size: 40 KiB

View File

@@ -0,0 +1,21 @@
episodes,rewards,steps
0,3,7
1,3,7
2,2,8
3,3,7
4,-12,12
5,-49,29
6,3,7
7,-17,17
8,4,6
9,-17,17
10,2,8
11,3,7
12,3,7
13,2,8
14,3,7
15,-34,24
16,3,7
17,5,5
18,5,5
19,3,7
1 episodes rewards steps
2 0 3 7
3 1 3 7
4 2 2 8
5 3 3 7
6 4 -12 12
7 5 -49 29
8 6 3 7
9 7 -17 17
10 8 4 6
11 9 -17 17
12 10 2 8
13 11 3 7
14 12 3 7
15 13 2 8
16 14 3 7
17 15 -34 24
18 16 3 7
19 17 5 5
20 18 5 5
21 19 3 7

View File

@@ -0,0 +1,19 @@
general_cfg:
algo_name: Sarsa
device: cpu
env_name: CliffWalking-v0
load_checkpoint: false
load_path: Train_CartPole-v1_DQN_20221026-054757
max_steps: 200
mode: train
save_fig: true
seed: 1
show_fig: false
test_eps: 20
train_eps: 800
algo_cfg:
epsilon_decay: 300
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.95
lr: 0.1

View File

@@ -0,0 +1,804 @@
2022-10-30 02:11:46 - r - INFO: - n_states: 48, n_actions: 4
2022-10-30 02:11:46 - r - INFO: - Start training!
2022-10-30 02:11:46 - r - INFO: - Env: CliffWalking-v0, Algorithm: Sarsa, Device: cpu
2022-10-30 02:11:46 - r - INFO: - Episode: 1/800, Reward: -1091.00, Steps:200, Epislon: 0.491
2022-10-30 02:11:46 - r - INFO: - Episode: 2/800, Reward: -320.00, Steps:122, Epislon: 0.329
2022-10-30 02:11:46 - r - INFO: - Episode: 3/800, Reward: -794.00, Steps:200, Epislon: 0.173
2022-10-30 02:11:46 - r - INFO: - Episode: 4/800, Reward: -596.00, Steps:200, Epislon: 0.094
2022-10-30 02:11:46 - r - INFO: - Episode: 5/800, Reward: -398.00, Steps:200, Epislon: 0.053
2022-10-30 02:11:46 - r - INFO: - Episode: 6/800, Reward: -59.00, Steps:59, Epislon: 0.045
2022-10-30 02:11:46 - r - INFO: - Episode: 7/800, Reward: -299.00, Steps:200, Epislon: 0.028
2022-10-30 02:11:46 - r - INFO: - Episode: 8/800, Reward: -82.00, Steps:82, Epislon: 0.024
2022-10-30 02:11:46 - r - INFO: - Episode: 9/800, Reward: -125.00, Steps:125, Epislon: 0.019
2022-10-30 02:11:46 - r - INFO: - Episode: 10/800, Reward: -75.00, Steps:75, Epislon: 0.017
2022-10-30 02:11:46 - r - INFO: - Episode: 11/800, Reward: -285.00, Steps:186, Epislon: 0.014
2022-10-30 02:11:46 - r - INFO: - Episode: 12/800, Reward: -103.00, Steps:103, Epislon: 0.013
2022-10-30 02:11:46 - r - INFO: - Episode: 13/800, Reward: -103.00, Steps:103, Epislon: 0.012
2022-10-30 02:11:46 - r - INFO: - Episode: 14/800, Reward: -131.00, Steps:131, Epislon: 0.011
2022-10-30 02:11:46 - r - INFO: - Episode: 15/800, Reward: -53.00, Steps:53, Epislon: 0.011
2022-10-30 02:11:46 - r - INFO: - Episode: 16/800, Reward: -113.00, Steps:113, Epislon: 0.011
2022-10-30 02:11:46 - r - INFO: - Episode: 17/800, Reward: -125.00, Steps:125, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 18/800, Reward: -95.00, Steps:95, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 19/800, Reward: -97.00, Steps:97, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 20/800, Reward: -145.00, Steps:145, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 21/800, Reward: -89.00, Steps:89, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 22/800, Reward: -97.00, Steps:97, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 23/800, Reward: -115.00, Steps:115, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 24/800, Reward: -121.00, Steps:121, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 25/800, Reward: -53.00, Steps:53, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 26/800, Reward: -111.00, Steps:111, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 27/800, Reward: -97.00, Steps:97, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 28/800, Reward: -206.00, Steps:107, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 29/800, Reward: -147.00, Steps:147, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 30/800, Reward: -36.00, Steps:36, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 31/800, Reward: -216.00, Steps:117, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 32/800, Reward: -103.00, Steps:103, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 33/800, Reward: -87.00, Steps:87, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 34/800, Reward: -80.00, Steps:80, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 35/800, Reward: -73.00, Steps:73, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 36/800, Reward: -83.00, Steps:83, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 37/800, Reward: -143.00, Steps:44, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 38/800, Reward: -241.00, Steps:142, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 39/800, Reward: -77.00, Steps:77, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 40/800, Reward: -49.00, Steps:49, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 41/800, Reward: -87.00, Steps:87, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 42/800, Reward: -47.00, Steps:47, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 43/800, Reward: -89.00, Steps:89, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 44/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 45/800, Reward: -192.00, Steps:93, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 46/800, Reward: -85.00, Steps:85, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 47/800, Reward: -55.00, Steps:55, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 48/800, Reward: -59.00, Steps:59, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 49/800, Reward: -60.00, Steps:60, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 50/800, Reward: -50.00, Steps:50, Epislon: 0.010
2022-10-30 02:11:46 - r - INFO: - Episode: 51/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 52/800, Reward: -101.00, Steps:101, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 53/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 54/800, Reward: -70.00, Steps:70, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 55/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 56/800, Reward: -47.00, Steps:47, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 57/800, Reward: -80.00, Steps:80, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 58/800, Reward: -61.00, Steps:61, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 59/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 60/800, Reward: -73.00, Steps:73, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 61/800, Reward: -54.00, Steps:54, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 62/800, Reward: -37.00, Steps:37, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 63/800, Reward: -65.00, Steps:65, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 64/800, Reward: -41.00, Steps:41, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 65/800, Reward: -81.00, Steps:81, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 66/800, Reward: -39.00, Steps:39, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 67/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 68/800, Reward: -61.00, Steps:61, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 69/800, Reward: -57.00, Steps:57, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 70/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 71/800, Reward: -59.00, Steps:59, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 72/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 73/800, Reward: -51.00, Steps:51, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 74/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 75/800, Reward: -69.00, Steps:69, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 76/800, Reward: -41.00, Steps:41, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 77/800, Reward: -194.00, Steps:95, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 78/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 79/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 80/800, Reward: -81.00, Steps:81, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 81/800, Reward: -65.00, Steps:65, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 82/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 83/800, Reward: -47.00, Steps:47, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 84/800, Reward: -53.00, Steps:53, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 85/800, Reward: -165.00, Steps:66, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 86/800, Reward: -69.00, Steps:69, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 87/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 88/800, Reward: -56.00, Steps:56, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 89/800, Reward: -164.00, Steps:65, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 90/800, Reward: -45.00, Steps:45, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 91/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 92/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 93/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 94/800, Reward: -69.00, Steps:69, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 95/800, Reward: -33.00, Steps:33, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 96/800, Reward: -57.00, Steps:57, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 97/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 98/800, Reward: -55.00, Steps:55, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 99/800, Reward: -61.00, Steps:61, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 100/800, Reward: -162.00, Steps:63, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 101/800, Reward: -55.00, Steps:55, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 102/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 103/800, Reward: -53.00, Steps:53, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 104/800, Reward: -39.00, Steps:39, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 105/800, Reward: -55.00, Steps:55, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 106/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 107/800, Reward: -33.00, Steps:33, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 108/800, Reward: -49.00, Steps:49, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 109/800, Reward: -65.00, Steps:65, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 110/800, Reward: -45.00, Steps:45, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 111/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 112/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 113/800, Reward: -51.00, Steps:51, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 114/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 115/800, Reward: -47.00, Steps:47, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 116/800, Reward: -41.00, Steps:41, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 117/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 118/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 119/800, Reward: -180.00, Steps:81, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 120/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 121/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 122/800, Reward: -47.00, Steps:47, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 123/800, Reward: -65.00, Steps:65, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 124/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 125/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 126/800, Reward: -49.00, Steps:49, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 127/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 128/800, Reward: -45.00, Steps:45, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 129/800, Reward: -49.00, Steps:49, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 130/800, Reward: -37.00, Steps:37, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 131/800, Reward: -49.00, Steps:49, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 132/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 133/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 134/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 135/800, Reward: -37.00, Steps:37, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 136/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 137/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 138/800, Reward: -51.00, Steps:51, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 139/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 140/800, Reward: -51.00, Steps:51, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 141/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 142/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 143/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 144/800, Reward: -41.00, Steps:41, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 145/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 146/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 147/800, Reward: -47.00, Steps:47, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 148/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 149/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 150/800, Reward: -45.00, Steps:45, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 151/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 152/800, Reward: -33.00, Steps:33, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 153/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 154/800, Reward: -148.00, Steps:49, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 155/800, Reward: -41.00, Steps:41, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 156/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 157/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 158/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 159/800, Reward: -33.00, Steps:33, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 160/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 161/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 162/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 163/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 164/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 165/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 166/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 167/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 168/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 169/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 170/800, Reward: -41.00, Steps:41, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 171/800, Reward: -39.00, Steps:39, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 172/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 173/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 174/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 175/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 176/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 177/800, Reward: -155.00, Steps:56, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 178/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 179/800, Reward: -37.00, Steps:37, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 180/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 181/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 182/800, Reward: -39.00, Steps:39, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 183/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 184/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 185/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 186/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 187/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 188/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 189/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 190/800, Reward: -42.00, Steps:42, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 191/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 192/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 193/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 194/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 195/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 196/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 197/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 198/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 199/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 200/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 201/800, Reward: -33.00, Steps:33, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 202/800, Reward: -37.00, Steps:37, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 203/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 204/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 205/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 206/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 207/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 208/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 209/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 210/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 211/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 212/800, Reward: -37.00, Steps:37, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 213/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 214/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 215/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 216/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 217/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 218/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 219/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 220/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 221/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 222/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 223/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 224/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 225/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 226/800, Reward: -43.00, Steps:43, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 227/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 228/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 229/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 230/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 231/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 232/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 233/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 234/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 235/800, Reward: -31.00, Steps:31, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 236/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 237/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 238/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 239/800, Reward: -30.00, Steps:30, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 240/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 241/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 242/800, Reward: -24.00, Steps:24, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 243/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 244/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 245/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 246/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 247/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 248/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 249/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 250/800, Reward: -29.00, Steps:29, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 251/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 252/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 253/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 254/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 255/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 256/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 257/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 258/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 259/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 260/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 261/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 262/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 263/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 264/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 265/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 266/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 267/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 268/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 269/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 270/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 271/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 272/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 273/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 274/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 275/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 276/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 277/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 278/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 279/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 280/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 281/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 282/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 283/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 284/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 285/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 286/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 287/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 288/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 289/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 290/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 291/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 292/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 293/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 294/800, Reward: -120.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 295/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 296/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 297/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 298/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 299/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 300/800, Reward: -35.00, Steps:35, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 301/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 302/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 303/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 304/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 305/800, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 306/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 307/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 308/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 309/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 310/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 311/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 312/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 313/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 314/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 315/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 316/800, Reward: -32.00, Steps:32, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 317/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 318/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 319/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 320/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 321/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 322/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 323/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 324/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 325/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 326/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 327/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 328/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 329/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 330/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 331/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 332/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 333/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 334/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 335/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 336/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 337/800, Reward: -26.00, Steps:26, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 338/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 339/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 340/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 341/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 342/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 343/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 344/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 345/800, Reward: -27.00, Steps:27, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 346/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 347/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 348/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 349/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 350/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 351/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 352/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 353/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 354/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 355/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 356/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 357/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 358/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 359/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 360/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 361/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 362/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 363/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 364/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 365/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 366/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 367/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 368/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 369/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 370/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 371/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 372/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 373/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 374/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 375/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 376/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 377/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 378/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 379/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 380/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 381/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 382/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 383/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 384/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 385/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 386/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 387/800, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 388/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 389/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 390/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 391/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 392/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 393/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 394/800, Reward: -122.00, Steps:23, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 395/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 396/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 397/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 398/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 399/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 400/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 401/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 402/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 403/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 404/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 405/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 406/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 407/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 408/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 409/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 410/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 411/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 412/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 413/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 414/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 415/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 416/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 417/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 418/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 419/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 420/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 421/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 422/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 423/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 424/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 425/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 426/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 427/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 428/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 429/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 430/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 431/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 432/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 433/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 434/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 435/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 436/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 437/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 438/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 439/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 440/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 441/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 442/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 443/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 444/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 445/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 446/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 447/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 448/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 449/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 450/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 451/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 452/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 453/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 454/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 455/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 456/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 457/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 458/800, Reward: -22.00, Steps:22, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 459/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 460/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 461/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 462/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 463/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 464/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 465/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 466/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 467/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 468/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 469/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 470/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 471/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 472/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 473/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 474/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 475/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 476/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 477/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 478/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 479/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 480/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 481/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 482/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 483/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 484/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 485/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 486/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 487/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 488/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 489/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 490/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 491/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 492/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 493/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 494/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 495/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 496/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 497/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 498/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 499/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 500/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 501/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 502/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 503/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 504/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 505/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 506/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 507/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 508/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 509/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 510/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 511/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 512/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 513/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 514/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 515/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 516/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 517/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 518/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 519/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 520/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 521/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 522/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 523/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 524/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 525/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 526/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 527/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 528/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 529/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 530/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 531/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 532/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 533/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 534/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 535/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 536/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 537/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 538/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 539/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 540/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 541/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 542/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 543/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 544/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 545/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 546/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 547/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 548/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 549/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 550/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 551/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 552/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 553/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 554/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 555/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 556/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 557/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 558/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:47 - r - INFO: - Episode: 559/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 560/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 561/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 562/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 563/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 564/800, Reward: -20.00, Steps:20, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 565/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 566/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 567/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 568/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 569/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 570/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 571/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 572/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 573/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 574/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 575/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 576/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 577/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 578/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 579/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 580/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 581/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 582/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 583/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 584/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 585/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 586/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 587/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 588/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 589/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 590/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 591/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 592/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 593/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 594/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 595/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 596/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 597/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 598/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 599/800, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 600/800, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 601/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 602/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 603/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 604/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 605/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 606/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 607/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 608/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 609/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 610/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 611/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 612/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 613/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 614/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 615/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 616/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 617/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 618/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 619/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 620/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 621/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 622/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 623/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 624/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 625/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 626/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 627/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 628/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 629/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 630/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 631/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 632/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 633/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 634/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 635/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 636/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 637/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 638/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 639/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 640/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 641/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 642/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 643/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 644/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 645/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 646/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 647/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 648/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 649/800, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 650/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 651/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 652/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 653/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 654/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 655/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 656/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 657/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 658/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 659/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 660/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 661/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 662/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 663/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 664/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 665/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 666/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 667/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 668/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 669/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 670/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 671/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 672/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 673/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 674/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 675/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 676/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 677/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 678/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 679/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 680/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 681/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 682/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 683/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 684/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 685/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 686/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 687/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 688/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 689/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 690/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 691/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 692/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 693/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 694/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 695/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 696/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 697/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 698/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 699/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 700/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 701/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 702/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 703/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 704/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 705/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 706/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 707/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 708/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 709/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 710/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 711/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 712/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 713/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 714/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 715/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 716/800, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 717/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 718/800, Reward: -117.00, Steps:18, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 719/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 720/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 721/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 722/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 723/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 724/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 725/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 726/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 727/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 728/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 729/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 730/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 731/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 732/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 733/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 734/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 735/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 736/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 737/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 738/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 739/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 740/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 741/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 742/800, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 743/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 744/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 745/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 746/800, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 747/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 748/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 749/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 750/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 751/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 752/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 753/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 754/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 755/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 756/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 757/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 758/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 759/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 760/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 761/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 762/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 763/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 764/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 765/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 766/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 767/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 768/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 769/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 770/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 771/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 772/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 773/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 774/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 775/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 776/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 777/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 778/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 779/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 780/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 781/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 782/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 783/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 784/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 785/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 786/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 787/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 788/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 789/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 790/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 791/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 792/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 793/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 794/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 795/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 796/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 797/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 798/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 799/800, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Episode: 800/800, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:11:48 - r - INFO: - Finish training!

Binary file not shown.

After

Width:  |  Height:  |  Size: 34 KiB

View File

@@ -0,0 +1,801 @@
episodes,rewards,steps
0,-1091,200
1,-320,122
2,-794,200
3,-596,200
4,-398,200
5,-59,59
6,-299,200
7,-82,82
8,-125,125
9,-75,75
10,-285,186
11,-103,103
12,-103,103
13,-131,131
14,-53,53
15,-113,113
16,-125,125
17,-95,95
18,-97,97
19,-145,145
20,-89,89
21,-97,97
22,-115,115
23,-121,121
24,-53,53
25,-111,111
26,-97,97
27,-206,107
28,-147,147
29,-36,36
30,-216,117
31,-103,103
32,-87,87
33,-80,80
34,-73,73
35,-83,83
36,-143,44
37,-241,142
38,-77,77
39,-49,49
40,-87,87
41,-47,47
42,-89,89
43,-31,31
44,-192,93
45,-85,85
46,-55,55
47,-59,59
48,-60,60
49,-50,50
50,-23,23
51,-101,101
52,-43,43
53,-70,70
54,-35,35
55,-47,47
56,-80,80
57,-61,61
58,-35,35
59,-73,73
60,-54,54
61,-37,37
62,-65,65
63,-41,41
64,-81,81
65,-39,39
66,-35,35
67,-61,61
68,-57,57
69,-43,43
70,-59,59
71,-43,43
72,-51,51
73,-43,43
74,-69,69
75,-41,41
76,-194,95
77,-35,35
78,-35,35
79,-81,81
80,-65,65
81,-35,35
82,-47,47
83,-53,53
84,-165,66
85,-69,69
86,-35,35
87,-56,56
88,-164,65
89,-45,45
90,-43,43
91,-43,43
92,-29,29
93,-69,69
94,-33,33
95,-57,57
96,-29,29
97,-55,55
98,-61,61
99,-162,63
100,-55,55
101,-31,31
102,-53,53
103,-39,39
104,-55,55
105,-25,25
106,-33,33
107,-49,49
108,-65,65
109,-45,45
110,-29,29
111,-25,25
112,-51,51
113,-43,43
114,-47,47
115,-41,41
116,-27,27
117,-31,31
118,-180,81
119,-43,43
120,-25,25
121,-47,47
122,-65,65
123,-29,29
124,-31,31
125,-49,49
126,-25,25
127,-45,45
128,-49,49
129,-37,37
130,-49,49
131,-25,25
132,-29,29
133,-35,35
134,-37,37
135,-43,43
136,-31,31
137,-51,51
138,-25,25
139,-51,51
140,-21,21
141,-35,35
142,-31,31
143,-41,41
144,-29,29
145,-27,27
146,-47,47
147,-27,27
148,-23,23
149,-45,45
150,-31,31
151,-33,33
152,-31,31
153,-148,49
154,-41,41
155,-25,25
156,-29,29
157,-31,31
158,-33,33
159,-27,27
160,-27,27
161,-29,29
162,-27,27
163,-27,27
164,-23,23
165,-35,35
166,-21,21
167,-23,23
168,-23,23
169,-41,41
170,-39,39
171,-21,21
172,-25,25
173,-23,23
174,-31,31
175,-21,21
176,-155,56
177,-21,21
178,-37,37
179,-17,17
180,-19,19
181,-39,39
182,-25,25
183,-25,25
184,-19,19
185,-29,29
186,-29,29
187,-25,25
188,-25,25
189,-42,42
190,-21,21
191,-21,21
192,-25,25
193,-29,29
194,-15,15
195,-21,21
196,-17,17
197,-29,29
198,-25,25
199,-15,15
200,-33,33
201,-37,37
202,-17,17
203,-29,29
204,-17,17
205,-25,25
206,-23,23
207,-25,25
208,-25,25
209,-25,25
210,-21,21
211,-37,37
212,-17,17
213,-17,17
214,-23,23
215,-31,31
216,-21,21
217,-21,21
218,-21,21
219,-19,19
220,-17,17
221,-27,27
222,-23,23
223,-15,15
224,-19,19
225,-43,43
226,-15,15
227,-25,25
228,-19,19
229,-19,19
230,-19,19
231,-19,19
232,-21,21
233,-23,23
234,-31,31
235,-23,23
236,-19,19
237,-29,29
238,-30,30
239,-19,19
240,-17,17
241,-24,24
242,-15,15
243,-23,23
244,-21,21
245,-15,15
246,-29,29
247,-19,19
248,-17,17
249,-29,29
250,-21,21
251,-25,25
252,-25,25
253,-19,19
254,-25,25
255,-21,21
256,-19,19
257,-19,19
258,-15,15
259,-21,21
260,-19,19
261,-23,23
262,-27,27
263,-19,19
264,-21,21
265,-21,21
266,-23,23
267,-17,17
268,-25,25
269,-27,27
270,-19,19
271,-19,19
272,-21,21
273,-15,15
274,-21,21
275,-17,17
276,-15,15
277,-23,23
278,-17,17
279,-19,19
280,-23,23
281,-27,27
282,-17,17
283,-23,23
284,-19,19
285,-17,17
286,-17,17
287,-15,15
288,-21,21
289,-15,15
290,-21,21
291,-19,19
292,-17,17
293,-120,21
294,-21,21
295,-15,15
296,-19,19
297,-15,15
298,-15,15
299,-35,35
300,-21,21
301,-21,21
302,-15,15
303,-15,15
304,-23,23
305,-17,17
306,-21,21
307,-17,17
308,-15,15
309,-15,15
310,-15,15
311,-17,17
312,-19,19
313,-25,25
314,-19,19
315,-32,32
316,-15,15
317,-17,17
318,-21,21
319,-15,15
320,-17,17
321,-19,19
322,-17,17
323,-17,17
324,-17,17
325,-17,17
326,-19,19
327,-15,15
328,-15,15
329,-21,21
330,-19,19
331,-15,15
332,-17,17
333,-17,17
334,-15,15
335,-19,19
336,-26,26
337,-17,17
338,-15,15
339,-21,21
340,-17,17
341,-15,15
342,-19,19
343,-17,17
344,-27,27
345,-15,15
346,-17,17
347,-15,15
348,-17,17
349,-17,17
350,-19,19
351,-15,15
352,-15,15
353,-15,15
354,-15,15
355,-17,17
356,-17,17
357,-15,15
358,-19,19
359,-15,15
360,-17,17
361,-17,17
362,-19,19
363,-17,17
364,-17,17
365,-21,21
366,-17,17
367,-15,15
368,-17,17
369,-21,21
370,-19,19
371,-17,17
372,-15,15
373,-15,15
374,-25,25
375,-15,15
376,-15,15
377,-17,17
378,-17,17
379,-17,17
380,-15,15
381,-15,15
382,-15,15
383,-15,15
384,-17,17
385,-17,17
386,-25,25
387,-17,17
388,-15,15
389,-15,15
390,-17,17
391,-15,15
392,-15,15
393,-122,23
394,-15,15
395,-15,15
396,-15,15
397,-15,15
398,-21,21
399,-15,15
400,-17,17
401,-17,17
402,-17,17
403,-15,15
404,-15,15
405,-15,15
406,-17,17
407,-15,15
408,-15,15
409,-17,17
410,-15,15
411,-15,15
412,-17,17
413,-19,19
414,-17,17
415,-17,17
416,-17,17
417,-15,15
418,-15,15
419,-17,17
420,-15,15
421,-15,15
422,-15,15
423,-21,21
424,-15,15
425,-15,15
426,-17,17
427,-15,15
428,-17,17
429,-15,15
430,-15,15
431,-15,15
432,-15,15
433,-15,15
434,-21,21
435,-15,15
436,-15,15
437,-17,17
438,-15,15
439,-15,15
440,-15,15
441,-17,17
442,-15,15
443,-15,15
444,-17,17
445,-15,15
446,-17,17
447,-17,17
448,-15,15
449,-17,17
450,-15,15
451,-17,17
452,-15,15
453,-15,15
454,-15,15
455,-15,15
456,-15,15
457,-22,22
458,-15,15
459,-15,15
460,-15,15
461,-15,15
462,-15,15
463,-15,15
464,-15,15
465,-15,15
466,-15,15
467,-15,15
468,-15,15
469,-15,15
470,-15,15
471,-17,17
472,-21,21
473,-15,15
474,-15,15
475,-15,15
476,-15,15
477,-17,17
478,-15,15
479,-17,17
480,-17,17
481,-15,15
482,-15,15
483,-15,15
484,-17,17
485,-21,21
486,-15,15
487,-15,15
488,-15,15
489,-15,15
490,-15,15
491,-17,17
492,-15,15
493,-17,17
494,-19,19
495,-15,15
496,-15,15
497,-15,15
498,-15,15
499,-15,15
500,-15,15
501,-15,15
502,-15,15
503,-15,15
504,-15,15
505,-15,15
506,-15,15
507,-15,15
508,-17,17
509,-15,15
510,-15,15
511,-15,15
512,-15,15
513,-15,15
514,-15,15
515,-15,15
516,-17,17
517,-15,15
518,-15,15
519,-15,15
520,-15,15
521,-15,15
522,-15,15
523,-15,15
524,-15,15
525,-15,15
526,-15,15
527,-15,15
528,-15,15
529,-15,15
530,-15,15
531,-17,17
532,-17,17
533,-15,15
534,-17,17
535,-15,15
536,-15,15
537,-15,15
538,-15,15
539,-15,15
540,-15,15
541,-15,15
542,-19,19
543,-15,15
544,-15,15
545,-15,15
546,-17,17
547,-15,15
548,-15,15
549,-15,15
550,-15,15
551,-15,15
552,-15,15
553,-15,15
554,-15,15
555,-15,15
556,-15,15
557,-15,15
558,-15,15
559,-15,15
560,-15,15
561,-15,15
562,-15,15
563,-20,20
564,-17,17
565,-15,15
566,-15,15
567,-15,15
568,-15,15
569,-15,15
570,-17,17
571,-17,17
572,-15,15
573,-15,15
574,-15,15
575,-15,15
576,-17,17
577,-15,15
578,-15,15
579,-15,15
580,-15,15
581,-15,15
582,-15,15
583,-17,17
584,-15,15
585,-15,15
586,-15,15
587,-15,15
588,-15,15
589,-15,15
590,-15,15
591,-15,15
592,-15,15
593,-15,15
594,-17,17
595,-15,15
596,-15,15
597,-15,15
598,-16,16
599,-16,16
600,-15,15
601,-15,15
602,-15,15
603,-15,15
604,-15,15
605,-17,17
606,-15,15
607,-15,15
608,-15,15
609,-15,15
610,-15,15
611,-15,15
612,-15,15
613,-15,15
614,-15,15
615,-15,15
616,-15,15
617,-15,15
618,-15,15
619,-15,15
620,-15,15
621,-15,15
622,-15,15
623,-15,15
624,-15,15
625,-15,15
626,-15,15
627,-15,15
628,-15,15
629,-15,15
630,-15,15
631,-15,15
632,-15,15
633,-21,21
634,-15,15
635,-15,15
636,-15,15
637,-15,15
638,-15,15
639,-15,15
640,-15,15
641,-15,15
642,-15,15
643,-15,15
644,-15,15
645,-15,15
646,-17,17
647,-15,15
648,-21,21
649,-15,15
650,-15,15
651,-15,15
652,-15,15
653,-17,17
654,-15,15
655,-15,15
656,-15,15
657,-15,15
658,-15,15
659,-15,15
660,-15,15
661,-15,15
662,-15,15
663,-15,15
664,-17,17
665,-15,15
666,-15,15
667,-15,15
668,-15,15
669,-15,15
670,-17,17
671,-15,15
672,-15,15
673,-15,15
674,-15,15
675,-15,15
676,-15,15
677,-17,17
678,-15,15
679,-15,15
680,-15,15
681,-15,15
682,-15,15
683,-15,15
684,-15,15
685,-15,15
686,-15,15
687,-15,15
688,-15,15
689,-15,15
690,-15,15
691,-15,15
692,-15,15
693,-15,15
694,-15,15
695,-15,15
696,-15,15
697,-15,15
698,-15,15
699,-15,15
700,-15,15
701,-15,15
702,-15,15
703,-17,17
704,-15,15
705,-15,15
706,-15,15
707,-15,15
708,-15,15
709,-15,15
710,-17,17
711,-15,15
712,-15,15
713,-15,15
714,-15,15
715,-16,16
716,-15,15
717,-117,18
718,-15,15
719,-17,17
720,-15,15
721,-15,15
722,-15,15
723,-15,15
724,-15,15
725,-15,15
726,-15,15
727,-15,15
728,-15,15
729,-15,15
730,-15,15
731,-15,15
732,-15,15
733,-15,15
734,-15,15
735,-15,15
736,-15,15
737,-15,15
738,-15,15
739,-15,15
740,-15,15
741,-16,16
742,-15,15
743,-17,17
744,-15,15
745,-19,19
746,-15,15
747,-15,15
748,-15,15
749,-17,17
750,-15,15
751,-15,15
752,-17,17
753,-15,15
754,-15,15
755,-15,15
756,-15,15
757,-17,17
758,-15,15
759,-15,15
760,-15,15
761,-17,17
762,-15,15
763,-15,15
764,-15,15
765,-15,15
766,-15,15
767,-17,17
768,-15,15
769,-15,15
770,-15,15
771,-15,15
772,-15,15
773,-15,15
774,-17,17
775,-15,15
776,-15,15
777,-15,15
778,-15,15
779,-15,15
780,-15,15
781,-15,15
782,-15,15
783,-15,15
784,-15,15
785,-15,15
786,-15,15
787,-15,15
788,-15,15
789,-15,15
790,-15,15
791,-15,15
792,-17,17
793,-15,15
794,-15,15
795,-15,15
796,-15,15
797,-15,15
798,-17,17
799,-15,15
1 episodes rewards steps
2 0 -1091 200
3 1 -320 122
4 2 -794 200
5 3 -596 200
6 4 -398 200
7 5 -59 59
8 6 -299 200
9 7 -82 82
10 8 -125 125
11 9 -75 75
12 10 -285 186
13 11 -103 103
14 12 -103 103
15 13 -131 131
16 14 -53 53
17 15 -113 113
18 16 -125 125
19 17 -95 95
20 18 -97 97
21 19 -145 145
22 20 -89 89
23 21 -97 97
24 22 -115 115
25 23 -121 121
26 24 -53 53
27 25 -111 111
28 26 -97 97
29 27 -206 107
30 28 -147 147
31 29 -36 36
32 30 -216 117
33 31 -103 103
34 32 -87 87
35 33 -80 80
36 34 -73 73
37 35 -83 83
38 36 -143 44
39 37 -241 142
40 38 -77 77
41 39 -49 49
42 40 -87 87
43 41 -47 47
44 42 -89 89
45 43 -31 31
46 44 -192 93
47 45 -85 85
48 46 -55 55
49 47 -59 59
50 48 -60 60
51 49 -50 50
52 50 -23 23
53 51 -101 101
54 52 -43 43
55 53 -70 70
56 54 -35 35
57 55 -47 47
58 56 -80 80
59 57 -61 61
60 58 -35 35
61 59 -73 73
62 60 -54 54
63 61 -37 37
64 62 -65 65
65 63 -41 41
66 64 -81 81
67 65 -39 39
68 66 -35 35
69 67 -61 61
70 68 -57 57
71 69 -43 43
72 70 -59 59
73 71 -43 43
74 72 -51 51
75 73 -43 43
76 74 -69 69
77 75 -41 41
78 76 -194 95
79 77 -35 35
80 78 -35 35
81 79 -81 81
82 80 -65 65
83 81 -35 35
84 82 -47 47
85 83 -53 53
86 84 -165 66
87 85 -69 69
88 86 -35 35
89 87 -56 56
90 88 -164 65
91 89 -45 45
92 90 -43 43
93 91 -43 43
94 92 -29 29
95 93 -69 69
96 94 -33 33
97 95 -57 57
98 96 -29 29
99 97 -55 55
100 98 -61 61
101 99 -162 63
102 100 -55 55
103 101 -31 31
104 102 -53 53
105 103 -39 39
106 104 -55 55
107 105 -25 25
108 106 -33 33
109 107 -49 49
110 108 -65 65
111 109 -45 45
112 110 -29 29
113 111 -25 25
114 112 -51 51
115 113 -43 43
116 114 -47 47
117 115 -41 41
118 116 -27 27
119 117 -31 31
120 118 -180 81
121 119 -43 43
122 120 -25 25
123 121 -47 47
124 122 -65 65
125 123 -29 29
126 124 -31 31
127 125 -49 49
128 126 -25 25
129 127 -45 45
130 128 -49 49
131 129 -37 37
132 130 -49 49
133 131 -25 25
134 132 -29 29
135 133 -35 35
136 134 -37 37
137 135 -43 43
138 136 -31 31
139 137 -51 51
140 138 -25 25
141 139 -51 51
142 140 -21 21
143 141 -35 35
144 142 -31 31
145 143 -41 41
146 144 -29 29
147 145 -27 27
148 146 -47 47
149 147 -27 27
150 148 -23 23
151 149 -45 45
152 150 -31 31
153 151 -33 33
154 152 -31 31
155 153 -148 49
156 154 -41 41
157 155 -25 25
158 156 -29 29
159 157 -31 31
160 158 -33 33
161 159 -27 27
162 160 -27 27
163 161 -29 29
164 162 -27 27
165 163 -27 27
166 164 -23 23
167 165 -35 35
168 166 -21 21
169 167 -23 23
170 168 -23 23
171 169 -41 41
172 170 -39 39
173 171 -21 21
174 172 -25 25
175 173 -23 23
176 174 -31 31
177 175 -21 21
178 176 -155 56
179 177 -21 21
180 178 -37 37
181 179 -17 17
182 180 -19 19
183 181 -39 39
184 182 -25 25
185 183 -25 25
186 184 -19 19
187 185 -29 29
188 186 -29 29
189 187 -25 25
190 188 -25 25
191 189 -42 42
192 190 -21 21
193 191 -21 21
194 192 -25 25
195 193 -29 29
196 194 -15 15
197 195 -21 21
198 196 -17 17
199 197 -29 29
200 198 -25 25
201 199 -15 15
202 200 -33 33
203 201 -37 37
204 202 -17 17
205 203 -29 29
206 204 -17 17
207 205 -25 25
208 206 -23 23
209 207 -25 25
210 208 -25 25
211 209 -25 25
212 210 -21 21
213 211 -37 37
214 212 -17 17
215 213 -17 17
216 214 -23 23
217 215 -31 31
218 216 -21 21
219 217 -21 21
220 218 -21 21
221 219 -19 19
222 220 -17 17
223 221 -27 27
224 222 -23 23
225 223 -15 15
226 224 -19 19
227 225 -43 43
228 226 -15 15
229 227 -25 25
230 228 -19 19
231 229 -19 19
232 230 -19 19
233 231 -19 19
234 232 -21 21
235 233 -23 23
236 234 -31 31
237 235 -23 23
238 236 -19 19
239 237 -29 29
240 238 -30 30
241 239 -19 19
242 240 -17 17
243 241 -24 24
244 242 -15 15
245 243 -23 23
246 244 -21 21
247 245 -15 15
248 246 -29 29
249 247 -19 19
250 248 -17 17
251 249 -29 29
252 250 -21 21
253 251 -25 25
254 252 -25 25
255 253 -19 19
256 254 -25 25
257 255 -21 21
258 256 -19 19
259 257 -19 19
260 258 -15 15
261 259 -21 21
262 260 -19 19
263 261 -23 23
264 262 -27 27
265 263 -19 19
266 264 -21 21
267 265 -21 21
268 266 -23 23
269 267 -17 17
270 268 -25 25
271 269 -27 27
272 270 -19 19
273 271 -19 19
274 272 -21 21
275 273 -15 15
276 274 -21 21
277 275 -17 17
278 276 -15 15
279 277 -23 23
280 278 -17 17
281 279 -19 19
282 280 -23 23
283 281 -27 27
284 282 -17 17
285 283 -23 23
286 284 -19 19
287 285 -17 17
288 286 -17 17
289 287 -15 15
290 288 -21 21
291 289 -15 15
292 290 -21 21
293 291 -19 19
294 292 -17 17
295 293 -120 21
296 294 -21 21
297 295 -15 15
298 296 -19 19
299 297 -15 15
300 298 -15 15
301 299 -35 35
302 300 -21 21
303 301 -21 21
304 302 -15 15
305 303 -15 15
306 304 -23 23
307 305 -17 17
308 306 -21 21
309 307 -17 17
310 308 -15 15
311 309 -15 15
312 310 -15 15
313 311 -17 17
314 312 -19 19
315 313 -25 25
316 314 -19 19
317 315 -32 32
318 316 -15 15
319 317 -17 17
320 318 -21 21
321 319 -15 15
322 320 -17 17
323 321 -19 19
324 322 -17 17
325 323 -17 17
326 324 -17 17
327 325 -17 17
328 326 -19 19
329 327 -15 15
330 328 -15 15
331 329 -21 21
332 330 -19 19
333 331 -15 15
334 332 -17 17
335 333 -17 17
336 334 -15 15
337 335 -19 19
338 336 -26 26
339 337 -17 17
340 338 -15 15
341 339 -21 21
342 340 -17 17
343 341 -15 15
344 342 -19 19
345 343 -17 17
346 344 -27 27
347 345 -15 15
348 346 -17 17
349 347 -15 15
350 348 -17 17
351 349 -17 17
352 350 -19 19
353 351 -15 15
354 352 -15 15
355 353 -15 15
356 354 -15 15
357 355 -17 17
358 356 -17 17
359 357 -15 15
360 358 -19 19
361 359 -15 15
362 360 -17 17
363 361 -17 17
364 362 -19 19
365 363 -17 17
366 364 -17 17
367 365 -21 21
368 366 -17 17
369 367 -15 15
370 368 -17 17
371 369 -21 21
372 370 -19 19
373 371 -17 17
374 372 -15 15
375 373 -15 15
376 374 -25 25
377 375 -15 15
378 376 -15 15
379 377 -17 17
380 378 -17 17
381 379 -17 17
382 380 -15 15
383 381 -15 15
384 382 -15 15
385 383 -15 15
386 384 -17 17
387 385 -17 17
388 386 -25 25
389 387 -17 17
390 388 -15 15
391 389 -15 15
392 390 -17 17
393 391 -15 15
394 392 -15 15
395 393 -122 23
396 394 -15 15
397 395 -15 15
398 396 -15 15
399 397 -15 15
400 398 -21 21
401 399 -15 15
402 400 -17 17
403 401 -17 17
404 402 -17 17
405 403 -15 15
406 404 -15 15
407 405 -15 15
408 406 -17 17
409 407 -15 15
410 408 -15 15
411 409 -17 17
412 410 -15 15
413 411 -15 15
414 412 -17 17
415 413 -19 19
416 414 -17 17
417 415 -17 17
418 416 -17 17
419 417 -15 15
420 418 -15 15
421 419 -17 17
422 420 -15 15
423 421 -15 15
424 422 -15 15
425 423 -21 21
426 424 -15 15
427 425 -15 15
428 426 -17 17
429 427 -15 15
430 428 -17 17
431 429 -15 15
432 430 -15 15
433 431 -15 15
434 432 -15 15
435 433 -15 15
436 434 -21 21
437 435 -15 15
438 436 -15 15
439 437 -17 17
440 438 -15 15
441 439 -15 15
442 440 -15 15
443 441 -17 17
444 442 -15 15
445 443 -15 15
446 444 -17 17
447 445 -15 15
448 446 -17 17
449 447 -17 17
450 448 -15 15
451 449 -17 17
452 450 -15 15
453 451 -17 17
454 452 -15 15
455 453 -15 15
456 454 -15 15
457 455 -15 15
458 456 -15 15
459 457 -22 22
460 458 -15 15
461 459 -15 15
462 460 -15 15
463 461 -15 15
464 462 -15 15
465 463 -15 15
466 464 -15 15
467 465 -15 15
468 466 -15 15
469 467 -15 15
470 468 -15 15
471 469 -15 15
472 470 -15 15
473 471 -17 17
474 472 -21 21
475 473 -15 15
476 474 -15 15
477 475 -15 15
478 476 -15 15
479 477 -17 17
480 478 -15 15
481 479 -17 17
482 480 -17 17
483 481 -15 15
484 482 -15 15
485 483 -15 15
486 484 -17 17
487 485 -21 21
488 486 -15 15
489 487 -15 15
490 488 -15 15
491 489 -15 15
492 490 -15 15
493 491 -17 17
494 492 -15 15
495 493 -17 17
496 494 -19 19
497 495 -15 15
498 496 -15 15
499 497 -15 15
500 498 -15 15
501 499 -15 15
502 500 -15 15
503 501 -15 15
504 502 -15 15
505 503 -15 15
506 504 -15 15
507 505 -15 15
508 506 -15 15
509 507 -15 15
510 508 -17 17
511 509 -15 15
512 510 -15 15
513 511 -15 15
514 512 -15 15
515 513 -15 15
516 514 -15 15
517 515 -15 15
518 516 -17 17
519 517 -15 15
520 518 -15 15
521 519 -15 15
522 520 -15 15
523 521 -15 15
524 522 -15 15
525 523 -15 15
526 524 -15 15
527 525 -15 15
528 526 -15 15
529 527 -15 15
530 528 -15 15
531 529 -15 15
532 530 -15 15
533 531 -17 17
534 532 -17 17
535 533 -15 15
536 534 -17 17
537 535 -15 15
538 536 -15 15
539 537 -15 15
540 538 -15 15
541 539 -15 15
542 540 -15 15
543 541 -15 15
544 542 -19 19
545 543 -15 15
546 544 -15 15
547 545 -15 15
548 546 -17 17
549 547 -15 15
550 548 -15 15
551 549 -15 15
552 550 -15 15
553 551 -15 15
554 552 -15 15
555 553 -15 15
556 554 -15 15
557 555 -15 15
558 556 -15 15
559 557 -15 15
560 558 -15 15
561 559 -15 15
562 560 -15 15
563 561 -15 15
564 562 -15 15
565 563 -20 20
566 564 -17 17
567 565 -15 15
568 566 -15 15
569 567 -15 15
570 568 -15 15
571 569 -15 15
572 570 -17 17
573 571 -17 17
574 572 -15 15
575 573 -15 15
576 574 -15 15
577 575 -15 15
578 576 -17 17
579 577 -15 15
580 578 -15 15
581 579 -15 15
582 580 -15 15
583 581 -15 15
584 582 -15 15
585 583 -17 17
586 584 -15 15
587 585 -15 15
588 586 -15 15
589 587 -15 15
590 588 -15 15
591 589 -15 15
592 590 -15 15
593 591 -15 15
594 592 -15 15
595 593 -15 15
596 594 -17 17
597 595 -15 15
598 596 -15 15
599 597 -15 15
600 598 -16 16
601 599 -16 16
602 600 -15 15
603 601 -15 15
604 602 -15 15
605 603 -15 15
606 604 -15 15
607 605 -17 17
608 606 -15 15
609 607 -15 15
610 608 -15 15
611 609 -15 15
612 610 -15 15
613 611 -15 15
614 612 -15 15
615 613 -15 15
616 614 -15 15
617 615 -15 15
618 616 -15 15
619 617 -15 15
620 618 -15 15
621 619 -15 15
622 620 -15 15
623 621 -15 15
624 622 -15 15
625 623 -15 15
626 624 -15 15
627 625 -15 15
628 626 -15 15
629 627 -15 15
630 628 -15 15
631 629 -15 15
632 630 -15 15
633 631 -15 15
634 632 -15 15
635 633 -21 21
636 634 -15 15
637 635 -15 15
638 636 -15 15
639 637 -15 15
640 638 -15 15
641 639 -15 15
642 640 -15 15
643 641 -15 15
644 642 -15 15
645 643 -15 15
646 644 -15 15
647 645 -15 15
648 646 -17 17
649 647 -15 15
650 648 -21 21
651 649 -15 15
652 650 -15 15
653 651 -15 15
654 652 -15 15
655 653 -17 17
656 654 -15 15
657 655 -15 15
658 656 -15 15
659 657 -15 15
660 658 -15 15
661 659 -15 15
662 660 -15 15
663 661 -15 15
664 662 -15 15
665 663 -15 15
666 664 -17 17
667 665 -15 15
668 666 -15 15
669 667 -15 15
670 668 -15 15
671 669 -15 15
672 670 -17 17
673 671 -15 15
674 672 -15 15
675 673 -15 15
676 674 -15 15
677 675 -15 15
678 676 -15 15
679 677 -17 17
680 678 -15 15
681 679 -15 15
682 680 -15 15
683 681 -15 15
684 682 -15 15
685 683 -15 15
686 684 -15 15
687 685 -15 15
688 686 -15 15
689 687 -15 15
690 688 -15 15
691 689 -15 15
692 690 -15 15
693 691 -15 15
694 692 -15 15
695 693 -15 15
696 694 -15 15
697 695 -15 15
698 696 -15 15
699 697 -15 15
700 698 -15 15
701 699 -15 15
702 700 -15 15
703 701 -15 15
704 702 -15 15
705 703 -17 17
706 704 -15 15
707 705 -15 15
708 706 -15 15
709 707 -15 15
710 708 -15 15
711 709 -15 15
712 710 -17 17
713 711 -15 15
714 712 -15 15
715 713 -15 15
716 714 -15 15
717 715 -16 16
718 716 -15 15
719 717 -117 18
720 718 -15 15
721 719 -17 17
722 720 -15 15
723 721 -15 15
724 722 -15 15
725 723 -15 15
726 724 -15 15
727 725 -15 15
728 726 -15 15
729 727 -15 15
730 728 -15 15
731 729 -15 15
732 730 -15 15
733 731 -15 15
734 732 -15 15
735 733 -15 15
736 734 -15 15
737 735 -15 15
738 736 -15 15
739 737 -15 15
740 738 -15 15
741 739 -15 15
742 740 -15 15
743 741 -16 16
744 742 -15 15
745 743 -17 17
746 744 -15 15
747 745 -19 19
748 746 -15 15
749 747 -15 15
750 748 -15 15
751 749 -17 17
752 750 -15 15
753 751 -15 15
754 752 -17 17
755 753 -15 15
756 754 -15 15
757 755 -15 15
758 756 -15 15
759 757 -17 17
760 758 -15 15
761 759 -15 15
762 760 -15 15
763 761 -17 17
764 762 -15 15
765 763 -15 15
766 764 -15 15
767 765 -15 15
768 766 -15 15
769 767 -17 17
770 768 -15 15
771 769 -15 15
772 770 -15 15
773 771 -15 15
774 772 -15 15
775 773 -15 15
776 774 -17 17
777 775 -15 15
778 776 -15 15
779 777 -15 15
780 778 -15 15
781 779 -15 15
782 780 -15 15
783 781 -15 15
784 782 -15 15
785 783 -15 15
786 784 -15 15
787 785 -15 15
788 786 -15 15
789 787 -15 15
790 788 -15 15
791 789 -15 15
792 790 -15 15
793 791 -15 15
794 792 -17 17
795 793 -15 15
796 794 -15 15
797 795 -15 15
798 796 -15 15
799 797 -15 15
800 798 -17 17
801 799 -15 15

View File

@@ -0,0 +1,19 @@
general_cfg:
algo_name: Sarsa
device: cpu
env_name: Racetrack-v0
load_checkpoint: false
load_path: Train_CartPole-v1_DQN_20221026-054757
max_steps: 200
mode: train
save_fig: true
seed: 10
show_fig: false
test_eps: 20
train_eps: 400
algo_cfg:
epsilon_decay: 200
epsilon_end: 0.01
epsilon_start: 0.9
gamma: 0.99
lr: 0.1

View File

@@ -0,0 +1,404 @@
2022-10-30 02:13:15 - r - INFO: - n_states: 4, n_actions: 9
2022-10-30 02:13:15 - r - INFO: - Start training!
2022-10-30 02:13:15 - r - INFO: - Env: Racetrack-v0, Algorithm: Sarsa, Device: cpu
2022-10-30 02:13:15 - r - INFO: - Episode: 1/400, Reward: -870.00, Steps:200, Epislon: 0.336
2022-10-30 02:13:15 - r - INFO: - Episode: 2/400, Reward: -740.00, Steps:200, Epislon: 0.129
2022-10-30 02:13:15 - r - INFO: - Episode: 3/400, Reward: -710.00, Steps:200, Epislon: 0.054
2022-10-30 02:13:15 - r - INFO: - Episode: 4/400, Reward: -600.00, Steps:200, Epislon: 0.026
2022-10-30 02:13:15 - r - INFO: - Episode: 5/400, Reward: -580.00, Steps:200, Epislon: 0.016
2022-10-30 02:13:15 - r - INFO: - Episode: 6/400, Reward: -620.00, Steps:200, Epislon: 0.012
2022-10-30 02:13:16 - r - INFO: - Episode: 7/400, Reward: -590.00, Steps:200, Epislon: 0.011
2022-10-30 02:13:16 - r - INFO: - Episode: 8/400, Reward: -590.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 9/400, Reward: -520.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 10/400, Reward: -570.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 11/400, Reward: -580.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 12/400, Reward: -580.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 13/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 14/400, Reward: -540.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 15/400, Reward: -510.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 16/400, Reward: -570.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 17/400, Reward: -560.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 18/400, Reward: -540.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 19/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 20/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 21/400, Reward: -530.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 22/400, Reward: -520.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 23/400, Reward: -530.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 24/400, Reward: -520.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 25/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 26/400, Reward: -510.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 27/400, Reward: -520.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:16 - r - INFO: - Episode: 28/400, Reward: -530.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 29/400, Reward: -560.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 30/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 31/400, Reward: -530.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 32/400, Reward: -359.00, Steps:149, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 33/400, Reward: -470.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 34/400, Reward: -510.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 35/400, Reward: -520.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 36/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 37/400, Reward: -540.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 38/400, Reward: -560.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 39/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 40/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 41/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 42/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 43/400, Reward: -540.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 44/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 45/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 46/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 47/400, Reward: -550.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 48/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 49/400, Reward: -540.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 50/400, Reward: -420.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 51/400, Reward: -530.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:17 - r - INFO: - Episode: 52/400, Reward: -510.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 53/400, Reward: -530.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 54/400, Reward: -460.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 55/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 56/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 57/400, Reward: -470.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 58/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 59/400, Reward: -470.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 60/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 61/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 62/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 63/400, Reward: -450.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 64/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 65/400, Reward: -420.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 66/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 67/400, Reward: -440.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 68/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 69/400, Reward: -188.00, Steps:88, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 70/400, Reward: -327.00, Steps:167, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 71/400, Reward: -530.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 72/400, Reward: -48.00, Steps:28, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 73/400, Reward: -460.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 74/400, Reward: -460.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 75/400, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 76/400, Reward: -428.00, Steps:178, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 77/400, Reward: -460.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 78/400, Reward: -341.00, Steps:151, Epislon: 0.010
2022-10-30 02:13:18 - r - INFO: - Episode: 79/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 80/400, Reward: -346.00, Steps:156, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 81/400, Reward: -34.00, Steps:24, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 82/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 83/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 84/400, Reward: -222.00, Steps:112, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 85/400, Reward: -470.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 86/400, Reward: -409.00, Steps:169, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 87/400, Reward: -139.00, Steps:59, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 88/400, Reward: -520.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 89/400, Reward: -108.00, Steps:58, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 90/400, Reward: -3.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 91/400, Reward: -131.00, Steps:71, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 92/400, Reward: -355.00, Steps:145, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 93/400, Reward: -470.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 94/400, Reward: -450.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 95/400, Reward: -490.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 96/400, Reward: -425.00, Steps:185, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 97/400, Reward: -130.00, Steps:70, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 98/400, Reward: -246.00, Steps:116, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 99/400, Reward: -480.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 100/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 101/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 102/400, Reward: -63.00, Steps:33, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 103/400, Reward: -311.00, Steps:131, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 104/400, Reward: -450.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 105/400, Reward: -520.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 106/400, Reward: -430.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 107/400, Reward: -79.00, Steps:39, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 108/400, Reward: -94.00, Steps:44, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 109/400, Reward: -37.00, Steps:27, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 110/400, Reward: -235.00, Steps:115, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 111/400, Reward: -440.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 112/400, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 113/400, Reward: -424.00, Steps:194, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 114/400, Reward: -470.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:19 - r - INFO: - Episode: 115/400, Reward: -344.00, Steps:164, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 116/400, Reward: -307.00, Steps:147, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 117/400, Reward: -82.00, Steps:52, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 118/400, Reward: -387.00, Steps:177, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 119/400, Reward: -500.00, Steps:200, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 120/400, Reward: -315.00, Steps:145, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 121/400, Reward: -289.00, Steps:119, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 122/400, Reward: -139.00, Steps:79, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 123/400, Reward: -392.00, Steps:192, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 124/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 125/400, Reward: -35.00, Steps:25, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 126/400, Reward: -82.00, Steps:42, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 127/400, Reward: -134.00, Steps:64, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 128/400, Reward: -93.00, Steps:53, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 129/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 130/400, Reward: -212.00, Steps:102, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 131/400, Reward: -87.00, Steps:47, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 132/400, Reward: -70.00, Steps:40, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 133/400, Reward: -109.00, Steps:49, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 134/400, Reward: -77.00, Steps:47, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 135/400, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 136/400, Reward: -118.00, Steps:58, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 137/400, Reward: -132.00, Steps:62, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 138/400, Reward: -76.00, Steps:36, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 139/400, Reward: -93.00, Steps:63, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 140/400, Reward: -357.00, Steps:157, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 141/400, Reward: -129.00, Steps:69, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 142/400, Reward: -46.00, Steps:26, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 143/400, Reward: -60.00, Steps:30, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 144/400, Reward: -339.00, Steps:159, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 145/400, Reward: -10.00, Steps:10, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 146/400, Reward: -164.00, Steps:84, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 147/400, Reward: -145.00, Steps:75, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 148/400, Reward: -53.00, Steps:33, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 149/400, Reward: -3.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 150/400, Reward: -55.00, Steps:35, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 151/400, Reward: -398.00, Steps:178, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 152/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 153/400, Reward: -20.00, Steps:20, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 154/400, Reward: -354.00, Steps:154, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 155/400, Reward: -439.00, Steps:189, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 156/400, Reward: -122.00, Steps:62, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 157/400, Reward: -80.00, Steps:40, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 158/400, Reward: -29.00, Steps:19, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 159/400, Reward: -185.00, Steps:85, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 160/400, Reward: -354.00, Steps:154, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 161/400, Reward: -35.00, Steps:25, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 162/400, Reward: -132.00, Steps:62, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 163/400, Reward: -155.00, Steps:75, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 164/400, Reward: -261.00, Steps:111, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 165/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 166/400, Reward: -135.00, Steps:65, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 167/400, Reward: -57.00, Steps:37, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 168/400, Reward: -432.00, Steps:182, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 169/400, Reward: -63.00, Steps:33, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 170/400, Reward: -119.00, Steps:59, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 171/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 172/400, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 173/400, Reward: -112.00, Steps:62, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 174/400, Reward: 1.00, Steps:9, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 175/400, Reward: -354.00, Steps:164, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 176/400, Reward: -101.00, Steps:61, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 177/400, Reward: -86.00, Steps:46, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 178/400, Reward: -33.00, Steps:23, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 179/400, Reward: -339.00, Steps:139, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 180/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 181/400, Reward: -9.00, Steps:9, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 182/400, Reward: -224.00, Steps:104, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 183/400, Reward: -11.00, Steps:11, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 184/400, Reward: -52.00, Steps:32, Epislon: 0.010
2022-10-30 02:13:20 - r - INFO: - Episode: 185/400, Reward: -98.00, Steps:48, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 186/400, Reward: -26.00, Steps:16, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 187/400, Reward: -89.00, Steps:39, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 188/400, Reward: 1.00, Steps:9, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 189/400, Reward: -66.00, Steps:36, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 190/400, Reward: -77.00, Steps:37, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 191/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 192/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 193/400, Reward: -64.00, Steps:34, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 194/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 195/400, Reward: -10.00, Steps:10, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 196/400, Reward: -79.00, Steps:39, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 197/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 198/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 199/400, Reward: 0.00, Steps:10, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 200/400, Reward: -33.00, Steps:23, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 201/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 202/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 203/400, Reward: -110.00, Steps:50, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 204/400, Reward: -43.00, Steps:23, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 205/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 206/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 207/400, Reward: 1.00, Steps:9, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 208/400, Reward: -32.00, Steps:22, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 209/400, Reward: -77.00, Steps:37, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 210/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 211/400, Reward: -23.00, Steps:23, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 212/400, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 213/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 214/400, Reward: 1.00, Steps:9, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 215/400, Reward: -42.00, Steps:22, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 216/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 217/400, Reward: -64.00, Steps:34, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 218/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 219/400, Reward: -2.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 220/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 221/400, Reward: -129.00, Steps:69, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 222/400, Reward: -133.00, Steps:63, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 223/400, Reward: -47.00, Steps:37, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 224/400, Reward: -11.00, Steps:11, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 225/400, Reward: -25.00, Steps:25, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 226/400, Reward: -1.00, Steps:11, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 227/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 228/400, Reward: -103.00, Steps:53, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 229/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 230/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 231/400, Reward: -67.00, Steps:37, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 232/400, Reward: -65.00, Steps:35, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 233/400, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 234/400, Reward: -30.00, Steps:20, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 235/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 236/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 237/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 238/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 239/400, Reward: 1.00, Steps:9, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 240/400, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 241/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 242/400, Reward: -39.00, Steps:29, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 243/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 244/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 245/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 246/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 247/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 248/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 249/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 250/400, Reward: -12.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 251/400, Reward: -14.00, Steps:14, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 252/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 253/400, Reward: -57.00, Steps:37, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 254/400, Reward: -29.00, Steps:19, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 255/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 256/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 257/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 258/400, Reward: -40.00, Steps:30, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 259/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 260/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 261/400, Reward: -30.00, Steps:20, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 262/400, Reward: -34.00, Steps:24, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 263/400, Reward: -1.00, Steps:11, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 264/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 265/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 266/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 267/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 268/400, Reward: -42.00, Steps:32, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 269/400, Reward: -17.00, Steps:17, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 270/400, Reward: -12.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 271/400, Reward: -28.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 272/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 273/400, Reward: -2.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 274/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 275/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 276/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 277/400, Reward: -14.00, Steps:14, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 278/400, Reward: -14.00, Steps:14, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 279/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 280/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 281/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 282/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 283/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 284/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 285/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 286/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 287/400, Reward: -1.00, Steps:11, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 288/400, Reward: -39.00, Steps:29, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 289/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 290/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 291/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 292/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 293/400, Reward: -11.00, Steps:11, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 294/400, Reward: -30.00, Steps:20, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 295/400, Reward: -18.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 296/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 297/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 298/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 299/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 300/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 301/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 302/400, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 303/400, Reward: -14.00, Steps:14, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 304/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 305/400, Reward: -55.00, Steps:35, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 306/400, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 307/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 308/400, Reward: -12.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 309/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 310/400, Reward: -67.00, Steps:37, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 311/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 312/400, Reward: -20.00, Steps:20, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 313/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 314/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 315/400, Reward: -20.00, Steps:20, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 316/400, Reward: -36.00, Steps:26, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 317/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 318/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 319/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 320/400, Reward: -12.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 321/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 322/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 323/400, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 324/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 325/400, Reward: -18.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 326/400, Reward: -36.00, Steps:26, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 327/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 328/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 329/400, Reward: -28.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 330/400, Reward: -31.00, Steps:21, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 331/400, Reward: -1.00, Steps:11, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 332/400, Reward: -109.00, Steps:59, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 333/400, Reward: -29.00, Steps:19, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 334/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 335/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 336/400, Reward: 0.00, Steps:10, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 337/400, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 338/400, Reward: -12.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 339/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 340/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 341/400, Reward: -14.00, Steps:14, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 342/400, Reward: -35.00, Steps:25, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 343/400, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 344/400, Reward: -21.00, Steps:21, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 345/400, Reward: -28.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 346/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 347/400, Reward: -12.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 348/400, Reward: -28.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 349/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 350/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 351/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 352/400, Reward: -10.00, Steps:10, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 353/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 354/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 355/400, Reward: -62.00, Steps:32, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 356/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 357/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 358/400, Reward: -28.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 359/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 360/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 361/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 362/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 363/400, Reward: -16.00, Steps:16, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 364/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 365/400, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 366/400, Reward: -18.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 367/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 368/400, Reward: -18.00, Steps:18, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 369/400, Reward: -15.00, Steps:15, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 370/400, Reward: 5.00, Steps:5, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 371/400, Reward: -29.00, Steps:19, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 372/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 373/400, Reward: -14.00, Steps:14, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 374/400, Reward: 1.00, Steps:9, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 375/400, Reward: -19.00, Steps:19, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 376/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 377/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 378/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 379/400, Reward: -31.00, Steps:21, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 380/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 381/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 382/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 383/400, Reward: -14.00, Steps:14, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 384/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 385/400, Reward: 2.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 386/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 387/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 388/400, Reward: -8.00, Steps:8, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 389/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 390/400, Reward: 4.00, Steps:6, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 391/400, Reward: -13.00, Steps:13, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 392/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 393/400, Reward: -12.00, Steps:12, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 394/400, Reward: -32.00, Steps:22, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 395/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 396/400, Reward: -27.00, Steps:17, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 397/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 398/400, Reward: 3.00, Steps:7, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 399/400, Reward: -37.00, Steps:27, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Episode: 400/400, Reward: -57.00, Steps:37, Epislon: 0.010
2022-10-30 02:13:21 - r - INFO: - Finish training!

Binary file not shown.

After

Width:  |  Height:  |  Size: 56 KiB

View File

@@ -0,0 +1,401 @@
episodes,rewards,steps
0,-870,200
1,-740,200
2,-710,200
3,-600,200
4,-580,200
5,-620,200
6,-590,200
7,-590,200
8,-520,200
9,-570,200
10,-580,200
11,-580,200
12,-500,200
13,-540,200
14,-510,200
15,-570,200
16,-560,200
17,-540,200
18,-490,200
19,-490,200
20,-530,200
21,-520,200
22,-530,200
23,-520,200
24,-500,200
25,-510,200
26,-520,200
27,-530,200
28,-560,200
29,-490,200
30,-530,200
31,-359,149
32,-470,200
33,-510,200
34,-520,200
35,-500,200
36,-540,200
37,-560,200
38,-500,200
39,-480,200
40,-490,200
41,-480,200
42,-540,200
43,-500,200
44,-500,200
45,-480,200
46,-550,200
47,-490,200
48,-540,200
49,-420,200
50,-530,200
51,-510,200
52,-530,200
53,-460,200
54,-480,200
55,-480,200
56,-470,200
57,-490,200
58,-470,200
59,-500,200
60,-500,200
61,-480,200
62,-450,200
63,-490,200
64,-420,200
65,-480,200
66,-440,200
67,-490,200
68,-188,88
69,-327,167
70,-530,200
71,-48,28
72,-460,200
73,-460,200
74,-25,25
75,-428,178
76,-460,200
77,-341,151
78,-480,200
79,-346,156
80,-34,24
81,-480,200
82,-480,200
83,-222,112
84,-470,200
85,-409,169
86,-139,59
87,-520,200
88,-108,58
89,-3,13
90,-131,71
91,-355,145
92,-470,200
93,-450,200
94,-490,200
95,-425,185
96,-130,70
97,-246,116
98,-480,200
99,-500,200
100,-13,13
101,-63,33
102,-311,131
103,-450,200
104,-520,200
105,-430,200
106,-79,39
107,-94,44
108,-37,27
109,-235,115
110,-440,200
111,-19,19
112,-424,194
113,-470,200
114,-344,164
115,-307,147
116,-82,52
117,-387,177
118,-500,200
119,-315,145
120,-289,119
121,-139,79
122,-392,192
123,-13,13
124,-35,25
125,-82,42
126,-134,64
127,-93,53
128,2,8
129,-212,102
130,-87,47
131,-70,40
132,-109,49
133,-77,47
134,-17,17
135,-118,58
136,-132,62
137,-76,36
138,-93,63
139,-357,157
140,-129,69
141,-46,26
142,-60,30
143,-339,159
144,-10,10
145,-164,84
146,-145,75
147,-53,33
148,-3,13
149,-55,35
150,-398,178
151,3,7
152,-20,20
153,-354,154
154,-439,189
155,-122,62
156,-80,40
157,-29,19
158,-185,85
159,-354,154
160,-35,25
161,-132,62
162,-155,75
163,-261,111
164,3,7
165,-135,65
166,-57,37
167,-432,182
168,-63,33
169,-119,59
170,3,7
171,-16,16
172,-112,62
173,1,9
174,-354,164
175,-101,61
176,-86,46
177,-33,23
178,-339,139
179,3,7
180,-9,9
181,-224,104
182,-11,11
183,-52,32
184,-98,48
185,-26,16
186,-89,39
187,1,9
188,-66,36
189,-77,37
190,5,5
191,2,8
192,-64,34
193,5,5
194,-10,10
195,-79,39
196,3,7
197,3,7
198,0,10
199,-33,23
200,2,8
201,5,5
202,-110,50
203,-43,23
204,3,7
205,-13,13
206,1,9
207,-32,22
208,-77,37
209,5,5
210,-23,23
211,-15,15
212,4,6
213,1,9
214,-42,22
215,-13,13
216,-64,34
217,-13,13
218,-2,12
219,5,5
220,-129,69
221,-133,63
222,-47,37
223,-11,11
224,-25,25
225,-1,11
226,5,5
227,-103,53
228,3,7
229,2,8
230,-67,37
231,-65,35
232,-15,15
233,-30,20
234,3,7
235,4,6
236,3,7
237,-13,13
238,1,9
239,-16,16
240,3,7
241,-39,29
242,3,7
243,3,7
244,3,7
245,-13,13
246,5,5
247,3,7
248,2,8
249,-12,12
250,-14,14
251,2,8
252,-57,37
253,-29,19
254,4,6
255,2,8
256,-13,13
257,-40,30
258,3,7
259,3,7
260,-30,20
261,-34,24
262,-1,11
263,-13,13
264,2,8
265,5,5
266,3,7
267,-42,32
268,-17,17
269,-12,12
270,-28,18
271,-13,13
272,-2,12
273,3,7
274,3,7
275,3,7
276,-14,14
277,-14,14
278,3,7
279,4,6
280,3,7
281,5,5
282,-13,13
283,3,7
284,2,8
285,5,5
286,-1,11
287,-39,29
288,5,5
289,3,7
290,3,7
291,3,7
292,-11,11
293,-30,20
294,-18,18
295,-13,13
296,2,8
297,5,5
298,3,7
299,4,6
300,2,8
301,-15,15
302,-14,14
303,-13,13
304,-55,35
305,-19,19
306,3,7
307,-12,12
308,3,7
309,-67,37
310,3,7
311,-20,20
312,4,6
313,5,5
314,-20,20
315,-36,26
316,3,7
317,4,6
318,2,8
319,-12,12
320,5,5
321,4,6
322,-16,16
323,4,6
324,-18,18
325,-36,26
326,3,7
327,3,7
328,-28,18
329,-31,21
330,-1,11
331,-109,59
332,-29,19
333,3,7
334,3,7
335,0,10
336,-15,15
337,-12,12
338,3,7
339,3,7
340,-14,14
341,-35,25
342,-16,16
343,-21,21
344,-28,18
345,2,8
346,-12,12
347,-28,18
348,3,7
349,3,7
350,3,7
351,-10,10
352,3,7
353,3,7
354,-62,32
355,5,5
356,4,6
357,-28,18
358,3,7
359,3,7
360,2,8
361,2,8
362,-16,16
363,2,8
364,-15,15
365,-18,18
366,3,7
367,-18,18
368,-15,15
369,5,5
370,-29,19
371,3,7
372,-14,14
373,1,9
374,-19,19
375,3,7
376,3,7
377,3,7
378,-31,21
379,2,8
380,3,7
381,3,7
382,-14,14
383,3,7
384,2,8
385,3,7
386,4,6
387,-8,8
388,3,7
389,4,6
390,-13,13
391,3,7
392,-12,12
393,-32,22
394,3,7
395,-27,17
396,3,7
397,3,7
398,-37,27
399,-57,37
1 episodes rewards steps
2 0 -870 200
3 1 -740 200
4 2 -710 200
5 3 -600 200
6 4 -580 200
7 5 -620 200
8 6 -590 200
9 7 -590 200
10 8 -520 200
11 9 -570 200
12 10 -580 200
13 11 -580 200
14 12 -500 200
15 13 -540 200
16 14 -510 200
17 15 -570 200
18 16 -560 200
19 17 -540 200
20 18 -490 200
21 19 -490 200
22 20 -530 200
23 21 -520 200
24 22 -530 200
25 23 -520 200
26 24 -500 200
27 25 -510 200
28 26 -520 200
29 27 -530 200
30 28 -560 200
31 29 -490 200
32 30 -530 200
33 31 -359 149
34 32 -470 200
35 33 -510 200
36 34 -520 200
37 35 -500 200
38 36 -540 200
39 37 -560 200
40 38 -500 200
41 39 -480 200
42 40 -490 200
43 41 -480 200
44 42 -540 200
45 43 -500 200
46 44 -500 200
47 45 -480 200
48 46 -550 200
49 47 -490 200
50 48 -540 200
51 49 -420 200
52 50 -530 200
53 51 -510 200
54 52 -530 200
55 53 -460 200
56 54 -480 200
57 55 -480 200
58 56 -470 200
59 57 -490 200
60 58 -470 200
61 59 -500 200
62 60 -500 200
63 61 -480 200
64 62 -450 200
65 63 -490 200
66 64 -420 200
67 65 -480 200
68 66 -440 200
69 67 -490 200
70 68 -188 88
71 69 -327 167
72 70 -530 200
73 71 -48 28
74 72 -460 200
75 73 -460 200
76 74 -25 25
77 75 -428 178
78 76 -460 200
79 77 -341 151
80 78 -480 200
81 79 -346 156
82 80 -34 24
83 81 -480 200
84 82 -480 200
85 83 -222 112
86 84 -470 200
87 85 -409 169
88 86 -139 59
89 87 -520 200
90 88 -108 58
91 89 -3 13
92 90 -131 71
93 91 -355 145
94 92 -470 200
95 93 -450 200
96 94 -490 200
97 95 -425 185
98 96 -130 70
99 97 -246 116
100 98 -480 200
101 99 -500 200
102 100 -13 13
103 101 -63 33
104 102 -311 131
105 103 -450 200
106 104 -520 200
107 105 -430 200
108 106 -79 39
109 107 -94 44
110 108 -37 27
111 109 -235 115
112 110 -440 200
113 111 -19 19
114 112 -424 194
115 113 -470 200
116 114 -344 164
117 115 -307 147
118 116 -82 52
119 117 -387 177
120 118 -500 200
121 119 -315 145
122 120 -289 119
123 121 -139 79
124 122 -392 192
125 123 -13 13
126 124 -35 25
127 125 -82 42
128 126 -134 64
129 127 -93 53
130 128 2 8
131 129 -212 102
132 130 -87 47
133 131 -70 40
134 132 -109 49
135 133 -77 47
136 134 -17 17
137 135 -118 58
138 136 -132 62
139 137 -76 36
140 138 -93 63
141 139 -357 157
142 140 -129 69
143 141 -46 26
144 142 -60 30
145 143 -339 159
146 144 -10 10
147 145 -164 84
148 146 -145 75
149 147 -53 33
150 148 -3 13
151 149 -55 35
152 150 -398 178
153 151 3 7
154 152 -20 20
155 153 -354 154
156 154 -439 189
157 155 -122 62
158 156 -80 40
159 157 -29 19
160 158 -185 85
161 159 -354 154
162 160 -35 25
163 161 -132 62
164 162 -155 75
165 163 -261 111
166 164 3 7
167 165 -135 65
168 166 -57 37
169 167 -432 182
170 168 -63 33
171 169 -119 59
172 170 3 7
173 171 -16 16
174 172 -112 62
175 173 1 9
176 174 -354 164
177 175 -101 61
178 176 -86 46
179 177 -33 23
180 178 -339 139
181 179 3 7
182 180 -9 9
183 181 -224 104
184 182 -11 11
185 183 -52 32
186 184 -98 48
187 185 -26 16
188 186 -89 39
189 187 1 9
190 188 -66 36
191 189 -77 37
192 190 5 5
193 191 2 8
194 192 -64 34
195 193 5 5
196 194 -10 10
197 195 -79 39
198 196 3 7
199 197 3 7
200 198 0 10
201 199 -33 23
202 200 2 8
203 201 5 5
204 202 -110 50
205 203 -43 23
206 204 3 7
207 205 -13 13
208 206 1 9
209 207 -32 22
210 208 -77 37
211 209 5 5
212 210 -23 23
213 211 -15 15
214 212 4 6
215 213 1 9
216 214 -42 22
217 215 -13 13
218 216 -64 34
219 217 -13 13
220 218 -2 12
221 219 5 5
222 220 -129 69
223 221 -133 63
224 222 -47 37
225 223 -11 11
226 224 -25 25
227 225 -1 11
228 226 5 5
229 227 -103 53
230 228 3 7
231 229 2 8
232 230 -67 37
233 231 -65 35
234 232 -15 15
235 233 -30 20
236 234 3 7
237 235 4 6
238 236 3 7
239 237 -13 13
240 238 1 9
241 239 -16 16
242 240 3 7
243 241 -39 29
244 242 3 7
245 243 3 7
246 244 3 7
247 245 -13 13
248 246 5 5
249 247 3 7
250 248 2 8
251 249 -12 12
252 250 -14 14
253 251 2 8
254 252 -57 37
255 253 -29 19
256 254 4 6
257 255 2 8
258 256 -13 13
259 257 -40 30
260 258 3 7
261 259 3 7
262 260 -30 20
263 261 -34 24
264 262 -1 11
265 263 -13 13
266 264 2 8
267 265 5 5
268 266 3 7
269 267 -42 32
270 268 -17 17
271 269 -12 12
272 270 -28 18
273 271 -13 13
274 272 -2 12
275 273 3 7
276 274 3 7
277 275 3 7
278 276 -14 14
279 277 -14 14
280 278 3 7
281 279 4 6
282 280 3 7
283 281 5 5
284 282 -13 13
285 283 3 7
286 284 2 8
287 285 5 5
288 286 -1 11
289 287 -39 29
290 288 5 5
291 289 3 7
292 290 3 7
293 291 3 7
294 292 -11 11
295 293 -30 20
296 294 -18 18
297 295 -13 13
298 296 2 8
299 297 5 5
300 298 3 7
301 299 4 6
302 300 2 8
303 301 -15 15
304 302 -14 14
305 303 -13 13
306 304 -55 35
307 305 -19 19
308 306 3 7
309 307 -12 12
310 308 3 7
311 309 -67 37
312 310 3 7
313 311 -20 20
314 312 4 6
315 313 5 5
316 314 -20 20
317 315 -36 26
318 316 3 7
319 317 4 6
320 318 2 8
321 319 -12 12
322 320 5 5
323 321 4 6
324 322 -16 16
325 323 4 6
326 324 -18 18
327 325 -36 26
328 326 3 7
329 327 3 7
330 328 -28 18
331 329 -31 21
332 330 -1 11
333 331 -109 59
334 332 -29 19
335 333 3 7
336 334 3 7
337 335 0 10
338 336 -15 15
339 337 -12 12
340 338 3 7
341 339 3 7
342 340 -14 14
343 341 -35 25
344 342 -16 16
345 343 -21 21
346 344 -28 18
347 345 2 8
348 346 -12 12
349 347 -28 18
350 348 3 7
351 349 3 7
352 350 3 7
353 351 -10 10
354 352 3 7
355 353 3 7
356 354 -62 32
357 355 5 5
358 356 4 6
359 357 -28 18
360 358 3 7
361 359 3 7
362 360 2 8
363 361 2 8
364 362 -16 16
365 363 2 8
366 364 -15 15
367 365 -18 18
368 366 3 7
369 367 -18 18
370 368 -15 15
371 369 5 5
372 370 -29 19
373 371 3 7
374 372 -14 14
375 373 1 9
376 374 -19 19
377 375 3 7
378 376 3 7
379 377 3 7
380 378 -31 21
381 379 2 8
382 380 3 7
383 381 3 7
384 382 -14 14
385 383 3 7
386 384 2 8
387 385 3 7
388 386 4 6
389 387 -8 8
390 388 3 7
391 389 4 6
392 390 -13 13
393 391 3 7
394 392 -12 12
395 393 -32 22
396 394 3 7
397 395 -27 17
398 396 3 7
399 397 3 7
400 398 -37 27
401 399 -57 37

View File

@@ -0,0 +1,19 @@
general_cfg:
algo_name: Sarsa
device: cpu
env_name: CliffWalking-v0
mode: test
load_checkpoint: true
load_path: Train_CliffWalking-v0_Sarsa_20221030-021146
max_steps: 200
save_fig: true
seed: 1
show_fig: false
test_eps: 20
train_eps: 400
algo_cfg:
epsilon_decay: 300
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.95
lr: 0.1

View File

@@ -0,0 +1,19 @@
general_cfg:
algo_name: Sarsa
device: cpu
env_name: CliffWalking-v0
mode: train
load_checkpoint: false
load_path: Train_CartPole-v1_DQN_20221026-054757
max_steps: 200
save_fig: true
seed: 1
show_fig: false
test_eps: 20
train_eps: 800
algo_cfg:
epsilon_decay: 300
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.95
lr: 0.1

View File

@@ -0,0 +1,19 @@
general_cfg:
algo_name: Sarsa
device: cpu
env_name: Racetrack-v0
mode: test
load_checkpoint: true
load_path: Train_Racetrack-v0_Sarsa_20221030-021315
max_steps: 200
save_fig: true
seed: 10
show_fig: false
test_eps: 20
train_eps: 400
algo_cfg:
epsilon_decay: 200
epsilon_end: 0.01
epsilon_start: 0.9
gamma: 0.99
lr: 0.1

View File

@@ -0,0 +1,19 @@
general_cfg:
algo_name: Sarsa
device: cpu
env_name: Racetrack-v0
mode: train
load_checkpoint: false
load_path: Train_CartPole-v1_DQN_20221026-054757
max_steps: 200
save_fig: true
seed: 10
show_fig: false
test_eps: 20
train_eps: 400
algo_cfg:
epsilon_decay: 200
epsilon_end: 0.01
epsilon_start: 0.9
gamma: 0.99
lr: 0.1

View File

@@ -0,0 +1,35 @@
#!/usr/bin/env python
# coding=utf-8
'''
Author: JiangJi
Email: johnjim0816@gmail.com
Date: 2022-10-30 01:23:07
LastEditor: JiangJi
LastEditTime: 2022-10-30 02:01:54
Discription: default parameters of QLearning
'''
from common.config import GeneralConfig,AlgoConfig
class GeneralConfigSarsa(GeneralConfig):
def __init__(self) -> None:
self.env_name = "CliffWalking-v0" # name of environment
self.algo_name = "Sarsa" # name of algorithm
self.mode = "train" # train or test
self.seed = 1 # random seed
self.device = "cpu" # device to use
self.train_eps = 400 # number of episodes for training
self.test_eps = 20 # number of episodes for testing
self.max_steps = 200 # max steps for each episode
self.load_checkpoint = False
self.load_path = "tasks" # path to load model
self.show_fig = False # show figure or not
self.save_fig = True # save figure or not
class AlgoConfigSarsa(AlgoConfig):
def __init__(self) -> None:
# set epsilon_start=epsilon_end can obtain fixed epsilon=epsilon_end
self.epsilon_start = 0.95 # epsilon start value
self.epsilon_end = 0.01 # epsilon end value
self.epsilon_decay = 300 # epsilon decay rate
self.gamma = 0.90 # discount factor
self.lr = 0.1 # learning rate

View File

@@ -1,124 +0,0 @@
#!/usr/bin/env python
# coding=utf-8
'''
Author: John
Email: johnjim0816@gmail.com
Date: 2021-03-11 17:59:16
LastEditor: John
LastEditTime: 2022-08-26 23:03:39
Discription:
Environment:
'''
import sys,os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE" # avoid "OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized."
curr_path = os.path.dirname(os.path.abspath(__file__)) # current path
parent_path = os.path.dirname(curr_path) # parent path
sys.path.append(parent_path) # add path to system path
import gym
import datetime
import argparse
from envs.register import register_env
from envs.wrappers import CliffWalkingWapper
from Sarsa.sarsa import Sarsa
from common.utils import all_seed
from common.launcher import Launcher
class Main(Launcher):
def get_args(self):
curr_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S") # obtain current time
parser = argparse.ArgumentParser(description="hyperparameters")
parser.add_argument('--algo_name',default = 'Sarsa',type=str,help="name of algorithm")
parser.add_argument('--env_name',default = 'Racetrack-v0',type=str,help="name of environment")
parser.add_argument('--train_eps',default = 300,type=int,help="episodes of training")
parser.add_argument('--test_eps',default = 20,type=int,help="episodes of testing")
parser.add_argument('--ep_max_steps',default = 100000,type=int,help="steps per episode, much larger value can simulate infinite steps")
parser.add_argument('--gamma',default=0.99,type=float,help="discounted factor")
parser.add_argument('--epsilon_start',default=0.90,type=float,help="initial value of epsilon")
parser.add_argument('--epsilon_end',default=0.01,type=float,help="final value of epsilon")
parser.add_argument('--epsilon_decay',default=200,type=int,help="decay rate of epsilon")
parser.add_argument('--lr',default=0.2,type=float,help="learning rate")
parser.add_argument('--device',default='cpu',type=str,help="cpu or cuda")
parser.add_argument('--seed',default=10,type=int,help="seed")
parser.add_argument('--show_fig',default=False,type=bool,help="if show figure or not")
parser.add_argument('--save_fig',default=True,type=bool,help="if save figure or not")
args = parser.parse_args()
default_args = {'result_path':f"{curr_path}/outputs/{args.env_name}/{curr_time}/results/",
'model_path':f"{curr_path}/outputs/{args.env_name}/{curr_time}/models/",
}
args = {**vars(args),**default_args} # type(dict)
return args
def env_agent_config(self,cfg):
register_env(cfg['env_name'])
env = gym.make(cfg['env_name'])
if cfg['seed'] !=0: # set random seed
all_seed(env,seed= cfg['seed'])
if cfg['env_name'] == 'CliffWalking-v0':
env = CliffWalkingWapper(env)
try: # state dimension
n_states = env.observation_space.n # print(hasattr(env.observation_space, 'n'))
except AttributeError:
n_states = env.observation_space.shape[0] # print(hasattr(env.observation_space, 'shape'))
n_actions = env.action_space.n # action dimension
print(f"n_states: {n_states}, n_actions: {n_actions}")
cfg.update({"n_states":n_states,"n_actions":n_actions}) # update to cfg paramters
agent = Sarsa(cfg)
return env,agent
def train(self,cfg,env,agent):
print("Start training!")
print(f"Env: {cfg['env_name']}, Algorithm: {cfg['algo_name']}, Device: {cfg['device']}")
rewards = [] # record rewards for all episodes
steps = [] # record steps for all episodes
for i_ep in range(cfg['train_eps']):
ep_reward = 0 # reward per episode
ep_step = 0 # step per episode
state = env.reset() # reset and obtain initial state
action = agent.sample_action(state)
# while True:
for _ in range(cfg['ep_max_steps']):
next_state, reward, done, _ = env.step(action) # update env and return transitions
next_action = agent.sample_action(next_state)
agent.update(state, action, reward, next_state, next_action,done) # update agent
state = next_state # update state
action = next_action
ep_reward += reward
ep_step += 1
if done:
break
rewards.append(ep_reward)
steps.append(ep_step)
if (i_ep+1)%10==0:
print(f'Episode: {i_ep+1}/{cfg["train_eps"]}, Reward: {ep_reward:.2f}, Steps: {ep_step}, Epislon: {agent.epsilon:.3f}')
print("Finish training!")
return {'episodes':range(len(rewards)),'rewards':rewards,'steps':steps}
def test(self,cfg,env,agent):
print("Start testing!")
print(f"Env: {cfg['env_name']}, Algorithm: {cfg['algo_name']}, Device: {cfg['device']}")
rewards = [] # record rewards for all episodes
steps = [] # record steps for all episodes
for i_ep in range(cfg['test_eps']):
ep_reward = 0 # reward per episode
ep_step = 0
state = env.reset() # reset and obtain initial state
for _ in range(cfg['ep_max_steps']):
action = agent.predict_action(state)
next_state, reward, done, _ = env.step(action)
state = next_state
ep_reward+=reward
ep_step+=1
if done:
break
rewards.append(ep_reward)
steps.append(ep_step)
print(f"Episode: {i_ep+1}/{cfg['test_eps']}, Steps: {ep_step}, Reward: {ep_reward:.2f}")
print("Finish testing!")
return {'episodes':range(len(rewards)),'rewards':rewards,'steps':steps}
if __name__ == "__main__":
main = Main()
main.run()

View File

@@ -1,19 +0,0 @@
{
"algo_name": "Sarsa",
"env_name": "CliffWalking-v0",
"train_eps": 400,
"test_eps": 20,
"gamma": 0.9,
"epsilon_start": 0.95,
"epsilon_end": 0.01,
"epsilon_decay": 300,
"lr": 0.1,
"device": "cpu",
"seed": 10,
"show_fig": false,
"save_fig": true,
"result_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/CliffWalking-v0/20220825-213316/results/",
"model_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/CliffWalking-v0/20220825-213316/models/",
"n_states": 48,
"n_actions": 4
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 33 KiB

View File

@@ -1,401 +0,0 @@
episodes,rewards,steps
0,-649,154
1,-2822,842
2,-176,176
3,-139,139
4,-221,221
5,-51,51
6,-219,219
7,-247,148
8,-90,90
9,-145,145
10,-104,104
11,-162,162
12,-49,49
13,-129,129
14,-140,140
15,-19,19
16,-131,131
17,-115,115
18,-43,43
19,-133,133
20,-73,73
21,-89,89
22,-131,131
23,-61,61
24,-113,113
25,-119,119
26,-119,119
27,-71,71
28,-132,132
29,-47,47
30,-79,79
31,-57,57
32,-125,125
33,-77,77
34,-87,87
35,-49,49
36,-57,57
37,-81,81
38,-81,81
39,-97,97
40,-61,61
41,-85,85
42,-217,118
43,-39,39
44,-117,117
45,-41,41
46,-71,71
47,-105,105
48,-73,73
49,-68,68
50,-95,95
51,-41,41
52,-41,41
53,-67,67
54,-71,71
55,-65,65
56,-41,41
57,-61,61
58,-81,81
59,-21,21
60,-76,76
61,-80,80
62,-23,23
63,-53,53
64,-67,67
65,-33,33
66,-41,41
67,-59,59
68,-33,33
69,-64,64
70,-188,89
71,-47,47
72,-57,57
73,-45,45
74,-33,33
75,-79,79
76,-45,45
77,-23,23
78,-47,47
79,-57,57
80,-47,47
81,-45,45
82,-53,53
83,-29,29
84,-33,33
85,-69,69
86,-61,61
87,-35,35
88,-59,59
89,-43,43
90,-17,17
91,-39,39
92,-59,59
93,-29,29
94,-31,31
95,-55,55
96,-35,35
97,-45,45
98,-29,29
99,-59,59
100,-25,25
101,-29,29
102,-33,33
103,-39,39
104,-19,19
105,-47,47
106,-57,57
107,-19,19
108,-47,47
109,-25,25
110,-23,23
111,-53,53
112,-39,39
113,-34,34
114,-27,27
115,-27,27
116,-63,63
117,-33,33
118,-17,17
119,-21,21
120,-19,19
121,-49,49
122,-25,25
123,-39,39
124,-25,25
125,-167,68
126,-35,35
127,-29,29
128,-31,31
129,-44,44
130,-33,33
131,-23,23
132,-37,37
133,-134,35
134,-31,31
135,-19,19
136,-29,29
137,-37,37
138,-25,25
139,-39,39
140,-47,47
141,-29,29
142,-27,27
143,-21,21
144,-41,41
145,-29,29
146,-25,25
147,-25,25
148,-21,21
149,-29,29
150,-39,39
151,-35,35
152,-35,35
153,-32,32
154,-31,31
155,-19,19
156,-21,21
157,-35,35
158,-33,33
159,-37,37
160,-25,25
161,-41,41
162,-25,25
163,-23,23
164,-27,27
165,-25,25
166,-39,39
167,-28,28
168,-24,24
169,-23,23
170,-41,41
171,-17,17
172,-35,35
173,-23,23
174,-29,29
175,-17,17
176,-39,39
177,-33,33
178,-29,29
179,-24,24
180,-23,23
181,-19,19
182,-15,15
183,-23,23
184,-39,39
185,-25,25
186,-35,35
187,-33,33
188,-19,19
189,-35,35
190,-21,21
191,-131,32
192,-15,15
193,-23,23
194,-21,21
195,-17,17
196,-23,23
197,-31,31
198,-21,21
199,-31,31
200,-35,35
201,-27,27
202,-19,19
203,-21,21
204,-23,23
205,-23,23
206,-21,21
207,-31,31
208,-25,25
209,-23,23
210,-17,17
211,-19,19
212,-25,25
213,-23,23
214,-19,19
215,-19,19
216,-25,25
217,-25,25
218,-25,25
219,-25,25
220,-23,23
221,-19,19
222,-19,19
223,-149,50
224,-41,41
225,-19,19
226,-29,29
227,-37,37
228,-17,17
229,-17,17
230,-19,19
231,-27,27
232,-19,19
233,-33,33
234,-23,23
235,-23,23
236,-34,34
237,-15,15
238,-33,33
239,-29,29
240,-17,17
241,-23,23
242,-17,17
243,-19,19
244,-21,21
245,-23,23
246,-17,17
247,-15,15
248,-39,39
249,-21,21
250,-23,23
251,-29,29
252,-15,15
253,-17,17
254,-29,29
255,-15,15
256,-21,21
257,-19,19
258,-19,19
259,-21,21
260,-17,17
261,-21,21
262,-27,27
263,-27,27
264,-21,21
265,-19,19
266,-17,17
267,-23,23
268,-19,19
269,-17,17
270,-19,19
271,-19,19
272,-17,17
273,-23,23
274,-17,17
275,-22,22
276,-31,31
277,-19,19
278,-17,17
279,-33,33
280,-19,19
281,-17,17
282,-31,31
283,-15,15
284,-15,15
285,-15,15
286,-29,29
287,-19,19
288,-17,17
289,-26,26
290,-17,17
291,-19,19
292,-15,15
293,-21,21
294,-21,21
295,-15,15
296,-19,19
297,-15,15
298,-17,17
299,-19,19
300,-17,17
301,-21,21
302,-17,17
303,-27,27
304,-17,17
305,-19,19
306,-15,15
307,-19,19
308,-33,33
309,-17,17
310,-20,20
311,-19,19
312,-17,17
313,-15,15
314,-23,23
315,-15,15
316,-15,15
317,-17,17
318,-25,25
319,-15,15
320,-17,17
321,-19,19
322,-17,17
323,-15,15
324,-23,23
325,-19,19
326,-17,17
327,-23,23
328,-15,15
329,-19,19
330,-15,15
331,-17,17
332,-19,19
333,-15,15
334,-17,17
335,-17,17
336,-19,19
337,-15,15
338,-19,19
339,-19,19
340,-17,17
341,-15,15
342,-21,21
343,-19,19
344,-17,17
345,-17,17
346,-15,15
347,-21,21
348,-20,20
349,-15,15
350,-15,15
351,-15,15
352,-19,19
353,-17,17
354,-15,15
355,-27,27
356,-15,15
357,-15,15
358,-23,23
359,-125,26
360,-132,33
361,-17,17
362,-15,15
363,-17,17
364,-23,23
365,-17,17
366,-15,15
367,-15,15
368,-17,17
369,-15,15
370,-17,17
371,-15,15
372,-15,15
373,-15,15
374,-15,15
375,-15,15
376,-15,15
377,-15,15
378,-15,15
379,-15,15
380,-17,17
381,-15,15
382,-15,15
383,-19,19
384,-15,15
385,-17,17
386,-27,27
387,-15,15
388,-21,21
389,-125,26
390,-15,15
391,-15,15
392,-15,15
393,-27,27
394,-15,15
395,-15,15
396,-17,17
397,-15,15
398,-15,15
399,-15,15
1 episodes rewards steps
2 0 -649 154
3 1 -2822 842
4 2 -176 176
5 3 -139 139
6 4 -221 221
7 5 -51 51
8 6 -219 219
9 7 -247 148
10 8 -90 90
11 9 -145 145
12 10 -104 104
13 11 -162 162
14 12 -49 49
15 13 -129 129
16 14 -140 140
17 15 -19 19
18 16 -131 131
19 17 -115 115
20 18 -43 43
21 19 -133 133
22 20 -73 73
23 21 -89 89
24 22 -131 131
25 23 -61 61
26 24 -113 113
27 25 -119 119
28 26 -119 119
29 27 -71 71
30 28 -132 132
31 29 -47 47
32 30 -79 79
33 31 -57 57
34 32 -125 125
35 33 -77 77
36 34 -87 87
37 35 -49 49
38 36 -57 57
39 37 -81 81
40 38 -81 81
41 39 -97 97
42 40 -61 61
43 41 -85 85
44 42 -217 118
45 43 -39 39
46 44 -117 117
47 45 -41 41
48 46 -71 71
49 47 -105 105
50 48 -73 73
51 49 -68 68
52 50 -95 95
53 51 -41 41
54 52 -41 41
55 53 -67 67
56 54 -71 71
57 55 -65 65
58 56 -41 41
59 57 -61 61
60 58 -81 81
61 59 -21 21
62 60 -76 76
63 61 -80 80
64 62 -23 23
65 63 -53 53
66 64 -67 67
67 65 -33 33
68 66 -41 41
69 67 -59 59
70 68 -33 33
71 69 -64 64
72 70 -188 89
73 71 -47 47
74 72 -57 57
75 73 -45 45
76 74 -33 33
77 75 -79 79
78 76 -45 45
79 77 -23 23
80 78 -47 47
81 79 -57 57
82 80 -47 47
83 81 -45 45
84 82 -53 53
85 83 -29 29
86 84 -33 33
87 85 -69 69
88 86 -61 61
89 87 -35 35
90 88 -59 59
91 89 -43 43
92 90 -17 17
93 91 -39 39
94 92 -59 59
95 93 -29 29
96 94 -31 31
97 95 -55 55
98 96 -35 35
99 97 -45 45
100 98 -29 29
101 99 -59 59
102 100 -25 25
103 101 -29 29
104 102 -33 33
105 103 -39 39
106 104 -19 19
107 105 -47 47
108 106 -57 57
109 107 -19 19
110 108 -47 47
111 109 -25 25
112 110 -23 23
113 111 -53 53
114 112 -39 39
115 113 -34 34
116 114 -27 27
117 115 -27 27
118 116 -63 63
119 117 -33 33
120 118 -17 17
121 119 -21 21
122 120 -19 19
123 121 -49 49
124 122 -25 25
125 123 -39 39
126 124 -25 25
127 125 -167 68
128 126 -35 35
129 127 -29 29
130 128 -31 31
131 129 -44 44
132 130 -33 33
133 131 -23 23
134 132 -37 37
135 133 -134 35
136 134 -31 31
137 135 -19 19
138 136 -29 29
139 137 -37 37
140 138 -25 25
141 139 -39 39
142 140 -47 47
143 141 -29 29
144 142 -27 27
145 143 -21 21
146 144 -41 41
147 145 -29 29
148 146 -25 25
149 147 -25 25
150 148 -21 21
151 149 -29 29
152 150 -39 39
153 151 -35 35
154 152 -35 35
155 153 -32 32
156 154 -31 31
157 155 -19 19
158 156 -21 21
159 157 -35 35
160 158 -33 33
161 159 -37 37
162 160 -25 25
163 161 -41 41
164 162 -25 25
165 163 -23 23
166 164 -27 27
167 165 -25 25
168 166 -39 39
169 167 -28 28
170 168 -24 24
171 169 -23 23
172 170 -41 41
173 171 -17 17
174 172 -35 35
175 173 -23 23
176 174 -29 29
177 175 -17 17
178 176 -39 39
179 177 -33 33
180 178 -29 29
181 179 -24 24
182 180 -23 23
183 181 -19 19
184 182 -15 15
185 183 -23 23
186 184 -39 39
187 185 -25 25
188 186 -35 35
189 187 -33 33
190 188 -19 19
191 189 -35 35
192 190 -21 21
193 191 -131 32
194 192 -15 15
195 193 -23 23
196 194 -21 21
197 195 -17 17
198 196 -23 23
199 197 -31 31
200 198 -21 21
201 199 -31 31
202 200 -35 35
203 201 -27 27
204 202 -19 19
205 203 -21 21
206 204 -23 23
207 205 -23 23
208 206 -21 21
209 207 -31 31
210 208 -25 25
211 209 -23 23
212 210 -17 17
213 211 -19 19
214 212 -25 25
215 213 -23 23
216 214 -19 19
217 215 -19 19
218 216 -25 25
219 217 -25 25
220 218 -25 25
221 219 -25 25
222 220 -23 23
223 221 -19 19
224 222 -19 19
225 223 -149 50
226 224 -41 41
227 225 -19 19
228 226 -29 29
229 227 -37 37
230 228 -17 17
231 229 -17 17
232 230 -19 19
233 231 -27 27
234 232 -19 19
235 233 -33 33
236 234 -23 23
237 235 -23 23
238 236 -34 34
239 237 -15 15
240 238 -33 33
241 239 -29 29
242 240 -17 17
243 241 -23 23
244 242 -17 17
245 243 -19 19
246 244 -21 21
247 245 -23 23
248 246 -17 17
249 247 -15 15
250 248 -39 39
251 249 -21 21
252 250 -23 23
253 251 -29 29
254 252 -15 15
255 253 -17 17
256 254 -29 29
257 255 -15 15
258 256 -21 21
259 257 -19 19
260 258 -19 19
261 259 -21 21
262 260 -17 17
263 261 -21 21
264 262 -27 27
265 263 -27 27
266 264 -21 21
267 265 -19 19
268 266 -17 17
269 267 -23 23
270 268 -19 19
271 269 -17 17
272 270 -19 19
273 271 -19 19
274 272 -17 17
275 273 -23 23
276 274 -17 17
277 275 -22 22
278 276 -31 31
279 277 -19 19
280 278 -17 17
281 279 -33 33
282 280 -19 19
283 281 -17 17
284 282 -31 31
285 283 -15 15
286 284 -15 15
287 285 -15 15
288 286 -29 29
289 287 -19 19
290 288 -17 17
291 289 -26 26
292 290 -17 17
293 291 -19 19
294 292 -15 15
295 293 -21 21
296 294 -21 21
297 295 -15 15
298 296 -19 19
299 297 -15 15
300 298 -17 17
301 299 -19 19
302 300 -17 17
303 301 -21 21
304 302 -17 17
305 303 -27 27
306 304 -17 17
307 305 -19 19
308 306 -15 15
309 307 -19 19
310 308 -33 33
311 309 -17 17
312 310 -20 20
313 311 -19 19
314 312 -17 17
315 313 -15 15
316 314 -23 23
317 315 -15 15
318 316 -15 15
319 317 -17 17
320 318 -25 25
321 319 -15 15
322 320 -17 17
323 321 -19 19
324 322 -17 17
325 323 -15 15
326 324 -23 23
327 325 -19 19
328 326 -17 17
329 327 -23 23
330 328 -15 15
331 329 -19 19
332 330 -15 15
333 331 -17 17
334 332 -19 19
335 333 -15 15
336 334 -17 17
337 335 -17 17
338 336 -19 19
339 337 -15 15
340 338 -19 19
341 339 -19 19
342 340 -17 17
343 341 -15 15
344 342 -21 21
345 343 -19 19
346 344 -17 17
347 345 -17 17
348 346 -15 15
349 347 -21 21
350 348 -20 20
351 349 -15 15
352 350 -15 15
353 351 -15 15
354 352 -19 19
355 353 -17 17
356 354 -15 15
357 355 -27 27
358 356 -15 15
359 357 -15 15
360 358 -23 23
361 359 -125 26
362 360 -132 33
363 361 -17 17
364 362 -15 15
365 363 -17 17
366 364 -23 23
367 365 -17 17
368 366 -15 15
369 367 -15 15
370 368 -17 17
371 369 -15 15
372 370 -17 17
373 371 -15 15
374 372 -15 15
375 373 -15 15
376 374 -15 15
377 375 -15 15
378 376 -15 15
379 377 -15 15
380 378 -15 15
381 379 -15 15
382 380 -17 17
383 381 -15 15
384 382 -15 15
385 383 -19 19
386 384 -15 15
387 385 -17 17
388 386 -27 27
389 387 -15 15
390 388 -21 21
391 389 -125 26
392 390 -15 15
393 391 -15 15
394 392 -15 15
395 393 -27 27
396 394 -15 15
397 395 -15 15
398 396 -17 17
399 397 -15 15
400 398 -15 15
401 399 -15 15

View File

@@ -1 +0,0 @@
{"algo_name": "Sarsa", "env_name": "Racetrack-v0", "train_eps": 300, "test_eps": 20, "gamma": 0.99, "epsilon_start": 0.9, "epsilon_end": 0.01, "epsilon_decay": 200, "lr": 0.2, "device": "cpu", "seed": 10, "show_fig": false, "save_fig": true, "result_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/Racetrack-v0/20220825-212738/results/", "model_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/Racetrack-v0/20220825-212738/models/", "n_states": 4, "n_actions": 9}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 39 KiB

View File

@@ -1,21 +0,0 @@
episodes,rewards,steps
0,4,6
1,4,6
2,-1010,1000
3,-14,14
4,4,6
5,4,6
6,4,6
7,-1060,1000
8,2,8
9,-12,12
10,3,7
11,-15,15
12,3,7
13,4,6
14,-14,14
15,3,7
16,-18,18
17,4,6
18,4,6
19,-1020,1000
1 episodes rewards steps
2 0 4 6
3 1 4 6
4 2 -1010 1000
5 3 -14 14
6 4 4 6
7 5 4 6
8 6 4 6
9 7 -1060 1000
10 8 2 8
11 9 -12 12
12 10 3 7
13 11 -15 15
14 12 3 7
15 13 4 6
16 14 -14 14
17 15 3 7
18 16 -18 18
19 17 4 6
20 18 4 6
21 19 -1020 1000

Binary file not shown.

Before

Width:  |  Height:  |  Size: 41 KiB

View File

@@ -1,301 +0,0 @@
episodes,rewards,steps
0,-3460,1000
1,-2800,1000
2,-2910,1000
3,-2620,1000
4,-2620,1000
5,-2590,1000
6,-2390,1000
7,-2510,1000
8,-2470,1000
9,-611,251
10,-891,371
11,-265,125
12,-2281,911
13,-1203,523
14,-616,266
15,-213,113
16,-633,273
17,-1112,482
18,-350,160
19,-852,342
20,-87,47
21,-11,11
22,-27,17
23,-117,57
24,-15,15
25,4,6
26,-27,17
27,-94,44
28,-184,84
29,-44,24
30,-150,80
31,-14,14
32,-219,89
33,-50,30
34,-111,61
35,-10,10
36,-28,18
37,-34,24
38,-12,12
39,-19,19
40,-136,66
41,-171,71
42,-51,31
43,4,6
44,-117,57
45,4,6
46,4,6
47,-127,67
48,-78,48
49,-311,131
50,-25,15
51,4,6
52,-49,29
53,-25,15
54,-78,48
55,-238,108
56,4,6
57,-17,17
58,-29,19
59,-218,98
60,4,6
61,-129,59
62,-344,144
63,-25,15
64,-15,15
65,-77,37
66,2,8
67,0,10
68,4,6
69,4,6
70,-242,102
71,3,7
72,4,6
73,-53,33
74,-14,14
75,4,6
76,4,6
77,-30,20
78,-12,12
79,2,8
80,-12,12
81,-150,70
82,-48,28
83,-102,52
84,4,6
85,-97,47
86,-10,10
87,-125,55
88,-28,18
89,-26,16
90,-107,57
91,4,6
92,-16,16
93,-84,44
94,-13,13
95,-43,23
96,-14,14
97,-12,12
98,-13,13
99,-2,12
100,-14,14
101,-47,27
102,4,6
103,4,6
104,-91,51
105,-65,35
106,4,6
107,-12,12
108,-14,14
109,-13,13
110,4,6
111,-41,31
112,-13,13
113,4,6
114,-4,14
115,-74,34
116,4,6
117,-60,30
118,4,6
119,-15,15
120,3,7
121,4,6
122,4,6
123,-19,19
124,4,6
125,-49,29
126,-13,13
127,-30,20
128,2,8
129,-21,21
130,-45,25
131,-32,22
132,-67,37
133,-46,26
134,0,10
135,-12,12
136,-9,9
137,-10,10
138,-14,14
139,4,6
140,-11,11
141,-12,12
142,2,8
143,-35,25
144,4,6
145,-73,43
146,4,6
147,-20,20
148,4,6
149,2,8
150,-29,19
151,-20,20
152,4,6
153,-28,18
154,4,6
155,4,6
156,4,6
157,4,6
158,-34,24
159,4,6
160,4,6
161,4,6
162,-25,15
163,4,6
164,3,7
165,-48,28
166,4,6
167,-58,38
168,-20,20
169,-9,9
170,3,7
171,4,6
172,3,7
173,-33,23
174,-50,30
175,-16,16
176,-32,22
177,-65,35
178,4,6
179,-13,13
180,-11,11
181,3,7
182,4,6
183,-16,16
184,-12,12
185,4,6
186,-48,28
187,-13,13
188,2,8
189,3,7
190,-27,17
191,3,7
192,4,6
193,4,6
194,4,6
195,4,6
196,4,6
197,-13,13
198,-14,14
199,4,6
200,4,6
201,-13,13
202,-33,23
203,4,6
204,-32,22
205,4,6
206,-48,28
207,4,6
208,4,6
209,3,7
210,4,6
211,-34,24
212,3,7
213,4,6
214,4,6
215,4,6
216,3,7
217,-12,12
218,3,7
219,-8,8
220,3,7
221,4,6
222,-46,26
223,-33,23
224,4,6
225,1,9
226,3,7
227,2,8
228,-34,24
229,4,6
230,4,6
231,4,6
232,4,6
233,-55,35
234,-37,27
235,4,6
236,-14,14
237,-65,35
238,4,6
239,-13,13
240,4,6
241,4,6
242,-13,13
243,-30,20
244,3,7
245,-13,13
246,4,6
247,4,6
248,-13,13
249,-32,22
250,4,6
251,-55,35
252,-12,12
253,3,7
254,3,7
255,3,7
256,4,6
257,2,8
258,-12,12
259,3,7
260,-10,10
261,-12,12
262,4,6
263,3,7
264,3,7
265,-16,16
266,3,7
267,-47,27
268,-13,13
269,4,6
270,3,7
271,-13,13
272,4,6
273,4,6
274,-17,17
275,4,6
276,3,7
277,3,7
278,4,6
279,-41,31
280,3,7
281,-47,27
282,-32,22
283,4,6
284,3,7
285,-17,17
286,3,7
287,3,7
288,3,7
289,-12,12
290,4,6
291,3,7
292,3,7
293,-24,14
294,3,7
295,4,6
296,3,7
297,3,7
298,3,7
299,-13,13
1 episodes rewards steps
2 0 -3460 1000
3 1 -2800 1000
4 2 -2910 1000
5 3 -2620 1000
6 4 -2620 1000
7 5 -2590 1000
8 6 -2390 1000
9 7 -2510 1000
10 8 -2470 1000
11 9 -611 251
12 10 -891 371
13 11 -265 125
14 12 -2281 911
15 13 -1203 523
16 14 -616 266
17 15 -213 113
18 16 -633 273
19 17 -1112 482
20 18 -350 160
21 19 -852 342
22 20 -87 47
23 21 -11 11
24 22 -27 17
25 23 -117 57
26 24 -15 15
27 25 4 6
28 26 -27 17
29 27 -94 44
30 28 -184 84
31 29 -44 24
32 30 -150 80
33 31 -14 14
34 32 -219 89
35 33 -50 30
36 34 -111 61
37 35 -10 10
38 36 -28 18
39 37 -34 24
40 38 -12 12
41 39 -19 19
42 40 -136 66
43 41 -171 71
44 42 -51 31
45 43 4 6
46 44 -117 57
47 45 4 6
48 46 4 6
49 47 -127 67
50 48 -78 48
51 49 -311 131
52 50 -25 15
53 51 4 6
54 52 -49 29
55 53 -25 15
56 54 -78 48
57 55 -238 108
58 56 4 6
59 57 -17 17
60 58 -29 19
61 59 -218 98
62 60 4 6
63 61 -129 59
64 62 -344 144
65 63 -25 15
66 64 -15 15
67 65 -77 37
68 66 2 8
69 67 0 10
70 68 4 6
71 69 4 6
72 70 -242 102
73 71 3 7
74 72 4 6
75 73 -53 33
76 74 -14 14
77 75 4 6
78 76 4 6
79 77 -30 20
80 78 -12 12
81 79 2 8
82 80 -12 12
83 81 -150 70
84 82 -48 28
85 83 -102 52
86 84 4 6
87 85 -97 47
88 86 -10 10
89 87 -125 55
90 88 -28 18
91 89 -26 16
92 90 -107 57
93 91 4 6
94 92 -16 16
95 93 -84 44
96 94 -13 13
97 95 -43 23
98 96 -14 14
99 97 -12 12
100 98 -13 13
101 99 -2 12
102 100 -14 14
103 101 -47 27
104 102 4 6
105 103 4 6
106 104 -91 51
107 105 -65 35
108 106 4 6
109 107 -12 12
110 108 -14 14
111 109 -13 13
112 110 4 6
113 111 -41 31
114 112 -13 13
115 113 4 6
116 114 -4 14
117 115 -74 34
118 116 4 6
119 117 -60 30
120 118 4 6
121 119 -15 15
122 120 3 7
123 121 4 6
124 122 4 6
125 123 -19 19
126 124 4 6
127 125 -49 29
128 126 -13 13
129 127 -30 20
130 128 2 8
131 129 -21 21
132 130 -45 25
133 131 -32 22
134 132 -67 37
135 133 -46 26
136 134 0 10
137 135 -12 12
138 136 -9 9
139 137 -10 10
140 138 -14 14
141 139 4 6
142 140 -11 11
143 141 -12 12
144 142 2 8
145 143 -35 25
146 144 4 6
147 145 -73 43
148 146 4 6
149 147 -20 20
150 148 4 6
151 149 2 8
152 150 -29 19
153 151 -20 20
154 152 4 6
155 153 -28 18
156 154 4 6
157 155 4 6
158 156 4 6
159 157 4 6
160 158 -34 24
161 159 4 6
162 160 4 6
163 161 4 6
164 162 -25 15
165 163 4 6
166 164 3 7
167 165 -48 28
168 166 4 6
169 167 -58 38
170 168 -20 20
171 169 -9 9
172 170 3 7
173 171 4 6
174 172 3 7
175 173 -33 23
176 174 -50 30
177 175 -16 16
178 176 -32 22
179 177 -65 35
180 178 4 6
181 179 -13 13
182 180 -11 11
183 181 3 7
184 182 4 6
185 183 -16 16
186 184 -12 12
187 185 4 6
188 186 -48 28
189 187 -13 13
190 188 2 8
191 189 3 7
192 190 -27 17
193 191 3 7
194 192 4 6
195 193 4 6
196 194 4 6
197 195 4 6
198 196 4 6
199 197 -13 13
200 198 -14 14
201 199 4 6
202 200 4 6
203 201 -13 13
204 202 -33 23
205 203 4 6
206 204 -32 22
207 205 4 6
208 206 -48 28
209 207 4 6
210 208 4 6
211 209 3 7
212 210 4 6
213 211 -34 24
214 212 3 7
215 213 4 6
216 214 4 6
217 215 4 6
218 216 3 7
219 217 -12 12
220 218 3 7
221 219 -8 8
222 220 3 7
223 221 4 6
224 222 -46 26
225 223 -33 23
226 224 4 6
227 225 1 9
228 226 3 7
229 227 2 8
230 228 -34 24
231 229 4 6
232 230 4 6
233 231 4 6
234 232 4 6
235 233 -55 35
236 234 -37 27
237 235 4 6
238 236 -14 14
239 237 -65 35
240 238 4 6
241 239 -13 13
242 240 4 6
243 241 4 6
244 242 -13 13
245 243 -30 20
246 244 3 7
247 245 -13 13
248 246 4 6
249 247 4 6
250 248 -13 13
251 249 -32 22
252 250 4 6
253 251 -55 35
254 252 -12 12
255 253 3 7
256 254 3 7
257 255 3 7
258 256 4 6
259 257 2 8
260 258 -12 12
261 259 3 7
262 260 -10 10
263 261 -12 12
264 262 4 6
265 263 3 7
266 264 3 7
267 265 -16 16
268 266 3 7
269 267 -47 27
270 268 -13 13
271 269 4 6
272 270 3 7
273 271 -13 13
274 272 4 6
275 273 4 6
276 274 -17 17
277 275 4 6
278 276 3 7
279 277 3 7
280 278 4 6
281 279 -41 31
282 280 3 7
283 281 -47 27
284 282 -32 22
285 283 4 6
286 284 3 7
287 285 -17 17
288 286 3 7
289 287 3 7
290 288 3 7
291 289 -12 12
292 290 4 6
293 291 3 7
294 292 3 7
295 293 -24 14
296 294 3 7
297 295 4 6
298 296 3 7
299 297 3 7
300 298 3 7
301 299 -13 13

View File

@@ -5,7 +5,7 @@ Author: John
Email: johnjim0816@gmail.com
Date: 2021-03-12 16:58:16
LastEditor: John
LastEditTime: 2022-08-25 21:26:08
LastEditTime: 2022-10-30 02:00:51
Discription:
Environment:
'''
@@ -15,14 +15,14 @@ import torch
import math
class Sarsa(object):
def __init__(self,cfg):
self.n_actions = cfg['n_actions']
self.lr = cfg['lr']
self.gamma = cfg['gamma']
self.epsilon = cfg['epsilon_start']
self.n_actions = cfg.n_actions
self.lr = cfg.lr
self.gamma = cfg.gamma
self.epsilon = cfg.epsilon_start
self.sample_count = 0
self.epsilon_start = cfg['epsilon_start']
self.epsilon_end = cfg['epsilon_end']
self.epsilon_decay = cfg['epsilon_decay']
self.epsilon_start = cfg.epsilon_start
self.epsilon_end = cfg.epsilon_end
self.epsilon_decay = cfg.epsilon_decay
self.Q_table = defaultdict(lambda: np.zeros(self.n_actions)) # Q table
def sample_action(self, state):
''' another way to represent e-greedy policy

View File

@@ -0,0 +1,106 @@
#!/usr/bin/env python
# coding=utf-8
'''
Author: JiangJi
Email: johnjim0816@gmail.com
Date: 2022-09-19 14:48:16
LastEditor: JiangJi
LastEditTime: 2022-10-30 02:11:31
Discription:
'''
import sys,os
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE" # avoid "OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized."
curr_path = os.path.dirname(os.path.abspath(__file__)) # current path
parent_path = os.path.dirname(curr_path) # parent path
sys.path.append(parent_path) # add path to system path
import gym
import datetime
import argparse
from envs.register import register_env
from envs.wrappers import CliffWalkingWapper
from Sarsa.sarsa import Sarsa
from common.utils import all_seed,merge_class_attrs
from common.launcher import Launcher
from config.config import GeneralConfigSarsa,AlgoConfigSarsa
class Main(Launcher):
def __init__(self) -> None:
super().__init__()
self.cfgs['general_cfg'] = merge_class_attrs(self.cfgs['general_cfg'],GeneralConfigSarsa())
self.cfgs['algo_cfg'] = merge_class_attrs(self.cfgs['algo_cfg'],AlgoConfigSarsa())
def env_agent_config(self,cfg,logger):
register_env(cfg.env_name)
env = gym.make(cfg.env_name,new_step_api=False) # create env
if cfg.env_name == 'CliffWalking-v0':
env = CliffWalkingWapper(env)
if cfg.seed !=0: # set random seed
all_seed(env,seed=cfg.seed)
try: # state dimension
n_states = env.observation_space.n # print(hasattr(env.observation_space, 'n'))
except AttributeError:
n_states = env.observation_space.shape[0] # print(hasattr(env.observation_space, 'shape'))
n_actions = env.action_space.n # action dimension
logger.info(f"n_states: {n_states}, n_actions: {n_actions}") # print info
# update to cfg paramters
setattr(cfg, 'n_states', n_states)
setattr(cfg, 'n_actions', n_actions)
agent = Sarsa(cfg)
return env,agent
def train(self,cfg,env,agent,logger):
logger.info("Start training!")
logger.info(f"Env: {cfg.env_name}, Algorithm: {cfg.algo_name}, Device: {cfg.device}")
rewards = [] # record rewards for all episodes
steps = [] # record steps for all episodes
for i_ep in range(cfg.train_eps):
ep_reward = 0 # reward per episode
ep_step = 0 # step per episode
state = env.reset() # reset and obtain initial state
action = agent.sample_action(state)
# while True:
for _ in range(cfg.max_steps):
next_state, reward, done, _ = env.step(action) # update env and return transitions
next_action = agent.sample_action(next_state)
agent.update(state, action, reward, next_state, next_action,done) # update agent
state = next_state # update state
action = next_action
ep_reward += reward
ep_step += 1
if done:
break
rewards.append(ep_reward)
steps.append(ep_step)
logger.info(f'Episode: {i_ep+1}/{cfg.train_eps}, Reward: {ep_reward:.2f}, Steps:{ep_step:d}, Epislon: {agent.epsilon:.3f}')
logger.info("Finish training!")
return {'episodes':range(len(rewards)),'rewards':rewards,'steps':steps}
def test(self,cfg,env,agent,logger):
logger.info("Start testing!")
logger.info(f"Env: {cfg.env_name}, Algorithm: {cfg.algo_name}, Device: {cfg.device}")
rewards = [] # record rewards for all episodes
steps = [] # record steps for all episodes
for i_ep in range(cfg.test_eps):
ep_reward = 0 # reward per episode
ep_step = 0
state = env.reset() # reset and obtain initial state
for _ in range(cfg.max_steps):
action = agent.predict_action(state)
next_state, reward, done, _ = env.step(action)
state = next_state
ep_reward+=reward
ep_step+=1
if done:
break
rewards.append(ep_reward)
steps.append(ep_step)
logger.info(f"Episode: {i_ep+1}/{cfg.test_eps}, Reward: {ep_reward:.2f}, Steps:{ep_step:d}")
logger.info("Finish testing!")
return {'episodes':range(len(rewards)),'rewards':rewards,'steps':steps}
if __name__ == "__main__":
main = Main()
main.run()