bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

更新算法模版

Browse Source
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
Download Patch File Download Diff File Expand all files Collapse all files

21
projects/codes/QLearning/Test_CliffWalking-v0_QLearning_20221030-014151/config.yaml Normal file
View File

@@ -0,0 +1,21 @@
general_cfg:
algo_name: QLearning
device: cpu
env_name: CliffWalking-v0
load_checkpoint: true
load_path: Train_CliffWalking-v0_QLearning_20221030-013856
max_steps: 200
mode: test
save_fig: true
seed: 1
show_fig: false
test_eps: 20
train_eps: 400
algo_cfg:
batch_size: 64
buffer_size: 100000
epsilon_decay: 300
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.95
lr: 0.1

24
projects/codes/QLearning/Test_CliffWalking-v0_QLearning_20221030-014151/logs/log.txt Normal file
View File

@@ -0,0 +1,24 @@
2022-10-30 01:41:51 - r - INFO: - n_states: 48, n_actions: 4
2022-10-30 01:41:51 - r - INFO: - Start testing!
2022-10-30 01:41:51 - r - INFO: - Env: CliffWalking-v0, Algorithm: QLearning, Device: cpu
2022-10-30 01:41:51 - r - INFO: - Episode: 1/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 2/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 3/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 4/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 5/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 6/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 7/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 8/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 9/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 10/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 11/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 12/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 13/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 14/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 15/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 16/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 17/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 18/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 19/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Episode: 20/20, Steps:13 Reward: -13.00
2022-10-30 01:41:51 - r - INFO: - Finish testing!

BIN
projects/codes/QLearning/Test_CliffWalking-v0_QLearning_20221030-014151/models/Qleaning_model.pkl Normal file
View File

Binary file not shown.

BIN
projects/codes/QLearning/Test_CliffWalking-v0_QLearning_20221030-014151/results/learning_curve.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 24 KiB

21
projects/codes/QLearning/Test_CliffWalking-v0_QLearning_20221030-014151/results/res.csv Normal file
View File

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