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 +1,25 @@
general_cfg:
algo_name: DQN
device: cuda
env_name: CartPole-v1
eval_eps: 10
eval_per_episode: 5
load_checkpoint: false
load_path: tasks
max_steps: 200
mode: train
save_fig: true
seed: 1
show_fig: false
test_eps: 10
train_eps: 100
algo_cfg:
batch_size: 64
buffer_size: 100000
epsilon_decay: 500
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.95
hidden_dim: 256
lr: 0.0001
target_update: 800

View File

@@ -0,0 +1,116 @@
2022-10-31 00:12:01 - r - INFO: - n_states: 4, n_actions: 2
2022-10-31 00:12:01 - r - INFO: - Start training!
2022-10-31 00:12:01 - r - INFO: - Env: CartPole-v1, Algorithm: DQN, Device: cuda
2022-10-31 00:12:04 - r - INFO: - Episode: 1/100, Reward: 18.0, Step: 18
2022-10-31 00:12:04 - r - INFO: - Episode: 2/100, Reward: 35.0, Step: 35
2022-10-31 00:12:04 - r - INFO: - Episode: 3/100, Reward: 13.0, Step: 13
2022-10-31 00:12:04 - r - INFO: - Episode: 4/100, Reward: 32.0, Step: 32
2022-10-31 00:12:04 - r - INFO: - Episode: 5/100, Reward: 16.0, Step: 16
2022-10-31 00:12:04 - r - INFO: - Current episode 5 has the best eval reward: 15.30
2022-10-31 00:12:04 - r - INFO: - Episode: 6/100, Reward: 12.0, Step: 12
2022-10-31 00:12:04 - r - INFO: - Episode: 7/100, Reward: 13.0, Step: 13
2022-10-31 00:12:04 - r - INFO: - Episode: 8/100, Reward: 15.0, Step: 15
2022-10-31 00:12:04 - r - INFO: - Episode: 9/100, Reward: 11.0, Step: 11
2022-10-31 00:12:04 - r - INFO: - Episode: 10/100, Reward: 15.0, Step: 15
2022-10-31 00:12:04 - r - INFO: - Episode: 11/100, Reward: 9.0, Step: 9
2022-10-31 00:12:04 - r - INFO: - Episode: 12/100, Reward: 13.0, Step: 13
2022-10-31 00:12:04 - r - INFO: - Episode: 13/100, Reward: 13.0, Step: 13
2022-10-31 00:12:04 - r - INFO: - Episode: 14/100, Reward: 10.0, Step: 10
2022-10-31 00:12:04 - r - INFO: - Episode: 15/100, Reward: 9.0, Step: 9
2022-10-31 00:12:04 - r - INFO: - Episode: 16/100, Reward: 24.0, Step: 24
2022-10-31 00:12:04 - r - INFO: - Episode: 17/100, Reward: 8.0, Step: 8
2022-10-31 00:12:04 - r - INFO: - Episode: 18/100, Reward: 10.0, Step: 10
2022-10-31 00:12:04 - r - INFO: - Episode: 19/100, Reward: 11.0, Step: 11
2022-10-31 00:12:04 - r - INFO: - Episode: 20/100, Reward: 13.0, Step: 13
2022-10-31 00:12:04 - r - INFO: - Episode: 21/100, Reward: 12.0, Step: 12
2022-10-31 00:12:04 - r - INFO: - Episode: 22/100, Reward: 11.0, Step: 11
2022-10-31 00:12:04 - r - INFO: - Episode: 23/100, Reward: 9.0, Step: 9
2022-10-31 00:12:04 - r - INFO: - Episode: 24/100, Reward: 21.0, Step: 21
2022-10-31 00:12:05 - r - INFO: - Episode: 25/100, Reward: 14.0, Step: 14
2022-10-31 00:12:05 - r - INFO: - Episode: 26/100, Reward: 12.0, Step: 12
2022-10-31 00:12:05 - r - INFO: - Episode: 27/100, Reward: 9.0, Step: 9
2022-10-31 00:12:05 - r - INFO: - Episode: 28/100, Reward: 11.0, Step: 11
2022-10-31 00:12:05 - r - INFO: - Episode: 29/100, Reward: 12.0, Step: 12
2022-10-31 00:12:05 - r - INFO: - Episode: 30/100, Reward: 13.0, Step: 13
2022-10-31 00:12:05 - r - INFO: - Episode: 31/100, Reward: 10.0, Step: 10
2022-10-31 00:12:05 - r - INFO: - Episode: 32/100, Reward: 13.0, Step: 13
2022-10-31 00:12:05 - r - INFO: - Episode: 33/100, Reward: 18.0, Step: 18
2022-10-31 00:12:05 - r - INFO: - Episode: 34/100, Reward: 9.0, Step: 9
2022-10-31 00:12:05 - r - INFO: - Episode: 35/100, Reward: 10.0, Step: 10
2022-10-31 00:12:05 - r - INFO: - Episode: 36/100, Reward: 9.0, Step: 9
2022-10-31 00:12:05 - r - INFO: - Episode: 37/100, Reward: 10.0, Step: 10
2022-10-31 00:12:05 - r - INFO: - Episode: 38/100, Reward: 10.0, Step: 10
2022-10-31 00:12:05 - r - INFO: - Episode: 39/100, Reward: 10.0, Step: 10
2022-10-31 00:12:05 - r - INFO: - Episode: 40/100, Reward: 8.0, Step: 8
2022-10-31 00:12:06 - r - INFO: - Episode: 41/100, Reward: 9.0, Step: 9
2022-10-31 00:12:06 - r - INFO: - Episode: 42/100, Reward: 9.0, Step: 9
2022-10-31 00:12:06 - r - INFO: - Episode: 43/100, Reward: 20.0, Step: 20
2022-10-31 00:12:06 - r - INFO: - Episode: 44/100, Reward: 16.0, Step: 16
2022-10-31 00:12:06 - r - INFO: - Episode: 45/100, Reward: 17.0, Step: 17
2022-10-31 00:12:06 - r - INFO: - Current episode 45 has the best eval reward: 17.50
2022-10-31 00:12:06 - r - INFO: - Episode: 46/100, Reward: 17.0, Step: 17
2022-10-31 00:12:06 - r - INFO: - Episode: 47/100, Reward: 17.0, Step: 17
2022-10-31 00:12:06 - r - INFO: - Episode: 48/100, Reward: 18.0, Step: 18
2022-10-31 00:12:06 - r - INFO: - Episode: 49/100, Reward: 25.0, Step: 25
2022-10-31 00:12:06 - r - INFO: - Episode: 50/100, Reward: 31.0, Step: 31
2022-10-31 00:12:06 - r - INFO: - Current episode 50 has the best eval reward: 24.80
2022-10-31 00:12:06 - r - INFO: - Episode: 51/100, Reward: 22.0, Step: 22
2022-10-31 00:12:06 - r - INFO: - Episode: 52/100, Reward: 39.0, Step: 39
2022-10-31 00:12:06 - r - INFO: - Episode: 53/100, Reward: 36.0, Step: 36
2022-10-31 00:12:06 - r - INFO: - Episode: 54/100, Reward: 26.0, Step: 26
2022-10-31 00:12:07 - r - INFO: - Episode: 55/100, Reward: 33.0, Step: 33
2022-10-31 00:12:07 - r - INFO: - Current episode 55 has the best eval reward: 38.70
2022-10-31 00:12:07 - r - INFO: - Episode: 56/100, Reward: 56.0, Step: 56
2022-10-31 00:12:07 - r - INFO: - Episode: 57/100, Reward: 112.0, Step: 112
2022-10-31 00:12:07 - r - INFO: - Episode: 58/100, Reward: 101.0, Step: 101
2022-10-31 00:12:08 - r - INFO: - Episode: 59/100, Reward: 69.0, Step: 69
2022-10-31 00:12:08 - r - INFO: - Episode: 60/100, Reward: 75.0, Step: 75
2022-10-31 00:12:08 - r - INFO: - Episode: 61/100, Reward: 182.0, Step: 182
2022-10-31 00:12:09 - r - INFO: - Episode: 62/100, Reward: 52.0, Step: 52
2022-10-31 00:12:09 - r - INFO: - Episode: 63/100, Reward: 67.0, Step: 67
2022-10-31 00:12:09 - r - INFO: - Episode: 64/100, Reward: 53.0, Step: 53
2022-10-31 00:12:09 - r - INFO: - Episode: 65/100, Reward: 119.0, Step: 119
2022-10-31 00:12:10 - r - INFO: - Current episode 65 has the best eval reward: 171.90
2022-10-31 00:12:10 - r - INFO: - Episode: 66/100, Reward: 200.0, Step: 200
2022-10-31 00:12:10 - r - INFO: - Episode: 67/100, Reward: 74.0, Step: 74
2022-10-31 00:12:11 - r - INFO: - Episode: 68/100, Reward: 138.0, Step: 138
2022-10-31 00:12:11 - r - INFO: - Episode: 69/100, Reward: 149.0, Step: 149
2022-10-31 00:12:12 - r - INFO: - Episode: 70/100, Reward: 144.0, Step: 144
2022-10-31 00:12:12 - r - INFO: - Current episode 70 has the best eval reward: 173.70
2022-10-31 00:12:13 - r - INFO: - Episode: 71/100, Reward: 200.0, Step: 200
2022-10-31 00:12:13 - r - INFO: - Episode: 72/100, Reward: 198.0, Step: 198
2022-10-31 00:12:14 - r - INFO: - Episode: 73/100, Reward: 200.0, Step: 200
2022-10-31 00:12:14 - r - INFO: - Episode: 74/100, Reward: 200.0, Step: 200
2022-10-31 00:12:15 - r - INFO: - Episode: 75/100, Reward: 200.0, Step: 200
2022-10-31 00:12:16 - r - INFO: - Current episode 75 has the best eval reward: 200.00
2022-10-31 00:12:16 - r - INFO: - Episode: 76/100, Reward: 200.0, Step: 200
2022-10-31 00:12:17 - r - INFO: - Episode: 77/100, Reward: 200.0, Step: 200
2022-10-31 00:12:17 - r - INFO: - Episode: 78/100, Reward: 200.0, Step: 200
2022-10-31 00:12:18 - r - INFO: - Episode: 79/100, Reward: 200.0, Step: 200
2022-10-31 00:12:19 - r - INFO: - Episode: 80/100, Reward: 200.0, Step: 200
2022-10-31 00:12:19 - r - INFO: - Current episode 80 has the best eval reward: 200.00
2022-10-31 00:12:20 - r - INFO: - Episode: 81/100, Reward: 200.0, Step: 200
2022-10-31 00:12:20 - r - INFO: - Episode: 82/100, Reward: 200.0, Step: 200
2022-10-31 00:12:21 - r - INFO: - Episode: 83/100, Reward: 200.0, Step: 200
2022-10-31 00:12:21 - r - INFO: - Episode: 84/100, Reward: 200.0, Step: 200
2022-10-31 00:12:22 - r - INFO: - Episode: 85/100, Reward: 200.0, Step: 200
2022-10-31 00:12:23 - r - INFO: - Current episode 85 has the best eval reward: 200.00
2022-10-31 00:12:23 - r - INFO: - Episode: 86/100, Reward: 200.0, Step: 200
2022-10-31 00:12:24 - r - INFO: - Episode: 87/100, Reward: 200.0, Step: 200
2022-10-31 00:12:25 - r - INFO: - Episode: 88/100, Reward: 200.0, Step: 200
2022-10-31 00:12:25 - r - INFO: - Episode: 89/100, Reward: 200.0, Step: 200
2022-10-31 00:12:26 - r - INFO: - Episode: 90/100, Reward: 200.0, Step: 200
2022-10-31 00:12:27 - r - INFO: - Current episode 90 has the best eval reward: 200.00
2022-10-31 00:12:27 - r - INFO: - Episode: 91/100, Reward: 200.0, Step: 200
2022-10-31 00:12:28 - r - INFO: - Episode: 92/100, Reward: 200.0, Step: 200
2022-10-31 00:12:28 - r - INFO: - Episode: 93/100, Reward: 200.0, Step: 200
2022-10-31 00:12:29 - r - INFO: - Episode: 94/100, Reward: 200.0, Step: 200
2022-10-31 00:12:29 - r - INFO: - Episode: 95/100, Reward: 200.0, Step: 200
2022-10-31 00:12:30 - r - INFO: - Current episode 95 has the best eval reward: 200.00
2022-10-31 00:12:31 - r - INFO: - Episode: 96/100, Reward: 200.0, Step: 200
2022-10-31 00:12:31 - r - INFO: - Episode: 97/100, Reward: 200.0, Step: 200
2022-10-31 00:12:32 - r - INFO: - Episode: 98/100, Reward: 200.0, Step: 200
2022-10-31 00:12:32 - r - INFO: - Episode: 99/100, Reward: 200.0, Step: 200
2022-10-31 00:12:33 - r - INFO: - Episode: 100/100, Reward: 200.0, Step: 200
2022-10-31 00:12:33 - r - INFO: - Current episode 100 has the best eval reward: 200.00
2022-10-31 00:12:33 - r - INFO: - Finish training!

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

View File

@@ -0,0 +1,101 @@
episodes,rewards,steps
0,18.0,18
1,35.0,35
2,13.0,13
3,32.0,32
4,16.0,16
5,12.0,12
6,13.0,13
7,15.0,15
8,11.0,11
9,15.0,15
10,9.0,9
11,13.0,13
12,13.0,13
13,10.0,10
14,9.0,9
15,24.0,24
16,8.0,8
17,10.0,10
18,11.0,11
19,13.0,13
20,12.0,12
21,11.0,11
22,9.0,9
23,21.0,21
24,14.0,14
25,12.0,12
26,9.0,9
27,11.0,11
28,12.0,12
29,13.0,13
30,10.0,10
31,13.0,13
32,18.0,18
33,9.0,9
34,10.0,10
35,9.0,9
36,10.0,10
37,10.0,10
38,10.0,10
39,8.0,8
40,9.0,9
41,9.0,9
42,20.0,20
43,16.0,16
44,17.0,17
45,17.0,17
46,17.0,17
47,18.0,18
48,25.0,25
49,31.0,31
50,22.0,22
51,39.0,39
52,36.0,36
53,26.0,26
54,33.0,33
55,56.0,56
56,112.0,112
57,101.0,101
58,69.0,69
59,75.0,75
60,182.0,182
61,52.0,52
62,67.0,67
63,53.0,53
64,119.0,119
65,200.0,200
66,74.0,74
67,138.0,138
68,149.0,149
69,144.0,144
70,200.0,200
71,198.0,198
72,200.0,200
73,200.0,200
74,200.0,200
75,200.0,200
76,200.0,200
77,200.0,200
78,200.0,200
79,200.0,200
80,200.0,200
81,200.0,200
82,200.0,200
83,200.0,200
84,200.0,200
85,200.0,200
86,200.0,200
87,200.0,200
88,200.0,200
89,200.0,200
90,200.0,200
91,200.0,200
92,200.0,200
93,200.0,200
94,200.0,200
95,200.0,200
96,200.0,200
97,200.0,200
98,200.0,200
99,200.0,200
1 episodes rewards steps
2 0 18.0 18
3 1 35.0 35
4 2 13.0 13
5 3 32.0 32
6 4 16.0 16
7 5 12.0 12
8 6 13.0 13
9 7 15.0 15
10 8 11.0 11
11 9 15.0 15
12 10 9.0 9
13 11 13.0 13
14 12 13.0 13
15 13 10.0 10
16 14 9.0 9
17 15 24.0 24
18 16 8.0 8
19 17 10.0 10
20 18 11.0 11
21 19 13.0 13
22 20 12.0 12
23 21 11.0 11
24 22 9.0 9
25 23 21.0 21
26 24 14.0 14
27 25 12.0 12
28 26 9.0 9
29 27 11.0 11
30 28 12.0 12
31 29 13.0 13
32 30 10.0 10
33 31 13.0 13
34 32 18.0 18
35 33 9.0 9
36 34 10.0 10
37 35 9.0 9
38 36 10.0 10
39 37 10.0 10
40 38 10.0 10
41 39 8.0 8
42 40 9.0 9
43 41 9.0 9
44 42 20.0 20
45 43 16.0 16
46 44 17.0 17
47 45 17.0 17
48 46 17.0 17
49 47 18.0 18
50 48 25.0 25
51 49 31.0 31
52 50 22.0 22
53 51 39.0 39
54 52 36.0 36
55 53 26.0 26
56 54 33.0 33
57 55 56.0 56
58 56 112.0 112
59 57 101.0 101
60 58 69.0 69
61 59 75.0 75
62 60 182.0 182
63 61 52.0 52
64 62 67.0 67
65 63 53.0 53
66 64 119.0 119
67 65 200.0 200
68 66 74.0 74
69 67 138.0 138
70 68 149.0 149
71 69 144.0 144
72 70 200.0 200
73 71 198.0 198
74 72 200.0 200
75 73 200.0 200
76 74 200.0 200
77 75 200.0 200
78 76 200.0 200
79 77 200.0 200
80 78 200.0 200
81 79 200.0 200
82 80 200.0 200
83 81 200.0 200
84 82 200.0 200
85 83 200.0 200
86 84 200.0 200
87 85 200.0 200
88 86 200.0 200
89 87 200.0 200
90 88 200.0 200
91 89 200.0 200
92 90 200.0 200
93 91 200.0 200
94 92 200.0 200
95 93 200.0 200
96 94 200.0 200
97 95 200.0 200
98 96 200.0 200
99 97 200.0 200
100 98 200.0 200
101 99 200.0 200