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 +1,23 @@
general_cfg:
algo_name: DQN
device: cuda
env_name: Acrobot-v1
load_checkpoint: false
load_path: Train_CartPole-v1_DQN_20221026-054757
max_steps: 100000
mode: train
save_fig: true
seed: 1
show_fig: false
test_eps: 10
train_eps: 100
algo_cfg:
batch_size: 128
buffer_size: 200000
epsilon_decay: 500
epsilon_end: 0.01
epsilon_start: 0.95
gamma: 0.95
hidden_dim: 256
lr: 0.002
target_update: 4

View File

@@ -0,0 +1,104 @@
2022-10-26 09:46:45 - r - INFO: - n_states: 6, n_actions: 3
2022-10-26 09:46:48 - r - INFO: - Start training!
2022-10-26 09:46:48 - r - INFO: - Env: Acrobot-v1, Algorithm: DQN, Device: cuda
2022-10-26 09:46:50 - r - INFO: - Episode: 1/100, Reward: -861.00: Epislon: 0.178
2022-10-26 09:46:50 - r - INFO: - Episode: 2/100, Reward: -252.00: Epislon: 0.111
2022-10-26 09:46:50 - r - INFO: - Episode: 3/100, Reward: -196.00: Epislon: 0.078
2022-10-26 09:46:51 - r - INFO: - Episode: 4/100, Reward: -390.00: Epislon: 0.041
2022-10-26 09:46:52 - r - INFO: - Episode: 5/100, Reward: -371.00: Epislon: 0.025
2022-10-26 09:46:52 - r - INFO: - Episode: 6/100, Reward: -237.00: Epislon: 0.019
2022-10-26 09:46:52 - r - INFO: - Episode: 7/100, Reward: -227.00: Epislon: 0.016
2022-10-26 09:46:53 - r - INFO: - Episode: 8/100, Reward: -228.00: Epislon: 0.014
2022-10-26 09:46:53 - r - INFO: - Episode: 9/100, Reward: -305.00: Epislon: 0.012
2022-10-26 09:46:54 - r - INFO: - Episode: 10/100, Reward: -234.00: Epislon: 0.011
2022-10-26 09:46:54 - r - INFO: - Episode: 11/100, Reward: -204.00: Epislon: 0.011
2022-10-26 09:46:55 - r - INFO: - Episode: 12/100, Reward: -277.00: Epislon: 0.010
2022-10-26 09:46:55 - r - INFO: - Episode: 13/100, Reward: -148.00: Epislon: 0.010
2022-10-26 09:46:56 - r - INFO: - Episode: 14/100, Reward: -372.00: Epislon: 0.010
2022-10-26 09:46:56 - r - INFO: - Episode: 15/100, Reward: -273.00: Epislon: 0.010
2022-10-26 09:46:56 - r - INFO: - Episode: 16/100, Reward: -105.00: Epislon: 0.010
2022-10-26 09:46:56 - r - INFO: - Episode: 17/100, Reward: -79.00: Epislon: 0.010
2022-10-26 09:46:57 - r - INFO: - Episode: 18/100, Reward: -112.00: Epislon: 0.010
2022-10-26 09:46:57 - r - INFO: - Episode: 19/100, Reward: -276.00: Epislon: 0.010
2022-10-26 09:46:57 - r - INFO: - Episode: 20/100, Reward: -148.00: Epislon: 0.010
2022-10-26 09:46:58 - r - INFO: - Episode: 21/100, Reward: -201.00: Epislon: 0.010
2022-10-26 09:46:58 - r - INFO: - Episode: 22/100, Reward: -173.00: Epislon: 0.010
2022-10-26 09:46:58 - r - INFO: - Episode: 23/100, Reward: -226.00: Epislon: 0.010
2022-10-26 09:46:59 - r - INFO: - Episode: 24/100, Reward: -154.00: Epislon: 0.010
2022-10-26 09:46:59 - r - INFO: - Episode: 25/100, Reward: -269.00: Epislon: 0.010
2022-10-26 09:46:59 - r - INFO: - Episode: 26/100, Reward: -191.00: Epislon: 0.010
2022-10-26 09:47:00 - r - INFO: - Episode: 27/100, Reward: -177.00: Epislon: 0.010
2022-10-26 09:47:00 - r - INFO: - Episode: 28/100, Reward: -209.00: Epislon: 0.010
2022-10-26 09:47:00 - r - INFO: - Episode: 29/100, Reward: -116.00: Epislon: 0.010
2022-10-26 09:47:00 - r - INFO: - Episode: 30/100, Reward: -117.00: Epislon: 0.010
2022-10-26 09:47:01 - r - INFO: - Episode: 31/100, Reward: -121.00: Epislon: 0.010
2022-10-26 09:47:01 - r - INFO: - Episode: 32/100, Reward: -208.00: Epislon: 0.010
2022-10-26 09:47:01 - r - INFO: - Episode: 33/100, Reward: -147.00: Epislon: 0.010
2022-10-26 09:47:02 - r - INFO: - Episode: 34/100, Reward: -104.00: Epislon: 0.010
2022-10-26 09:47:02 - r - INFO: - Episode: 35/100, Reward: -161.00: Epislon: 0.010
2022-10-26 09:47:02 - r - INFO: - Episode: 36/100, Reward: -144.00: Epislon: 0.010
2022-10-26 09:47:02 - r - INFO: - Episode: 37/100, Reward: -131.00: Epislon: 0.010
2022-10-26 09:47:03 - r - INFO: - Episode: 38/100, Reward: -226.00: Epislon: 0.010
2022-10-26 09:47:03 - r - INFO: - Episode: 39/100, Reward: -117.00: Epislon: 0.010
2022-10-26 09:47:03 - r - INFO: - Episode: 40/100, Reward: -344.00: Epislon: 0.010
2022-10-26 09:47:04 - r - INFO: - Episode: 41/100, Reward: -123.00: Epislon: 0.010
2022-10-26 09:47:04 - r - INFO: - Episode: 42/100, Reward: -232.00: Epislon: 0.010
2022-10-26 09:47:04 - r - INFO: - Episode: 43/100, Reward: -190.00: Epislon: 0.010
2022-10-26 09:47:05 - r - INFO: - Episode: 44/100, Reward: -176.00: Epislon: 0.010
2022-10-26 09:47:05 - r - INFO: - Episode: 45/100, Reward: -139.00: Epislon: 0.010
2022-10-26 09:47:06 - r - INFO: - Episode: 46/100, Reward: -410.00: Epislon: 0.010
2022-10-26 09:47:06 - r - INFO: - Episode: 47/100, Reward: -115.00: Epislon: 0.010
2022-10-26 09:47:06 - r - INFO: - Episode: 48/100, Reward: -118.00: Epislon: 0.010
2022-10-26 09:47:06 - r - INFO: - Episode: 49/100, Reward: -113.00: Epislon: 0.010
2022-10-26 09:47:07 - r - INFO: - Episode: 50/100, Reward: -355.00: Epislon: 0.010
2022-10-26 09:47:07 - r - INFO: - Episode: 51/100, Reward: -110.00: Epislon: 0.010
2022-10-26 09:47:07 - r - INFO: - Episode: 52/100, Reward: -148.00: Epislon: 0.010
2022-10-26 09:47:08 - r - INFO: - Episode: 53/100, Reward: -135.00: Epislon: 0.010
2022-10-26 09:47:08 - r - INFO: - Episode: 54/100, Reward: -220.00: Epislon: 0.010
2022-10-26 09:47:08 - r - INFO: - Episode: 55/100, Reward: -157.00: Epislon: 0.010
2022-10-26 09:47:09 - r - INFO: - Episode: 56/100, Reward: -130.00: Epislon: 0.010
2022-10-26 09:47:09 - r - INFO: - Episode: 57/100, Reward: -150.00: Epislon: 0.010
2022-10-26 09:47:09 - r - INFO: - Episode: 58/100, Reward: -254.00: Epislon: 0.010
2022-10-26 09:47:10 - r - INFO: - Episode: 59/100, Reward: -148.00: Epislon: 0.010
2022-10-26 09:47:10 - r - INFO: - Episode: 60/100, Reward: -108.00: Epislon: 0.010
2022-10-26 09:47:10 - r - INFO: - Episode: 61/100, Reward: -152.00: Epislon: 0.010
2022-10-26 09:47:10 - r - INFO: - Episode: 62/100, Reward: -107.00: Epislon: 0.010
2022-10-26 09:47:10 - r - INFO: - Episode: 63/100, Reward: -110.00: Epislon: 0.010
2022-10-26 09:47:11 - r - INFO: - Episode: 64/100, Reward: -266.00: Epislon: 0.010
2022-10-26 09:47:11 - r - INFO: - Episode: 65/100, Reward: -344.00: Epislon: 0.010
2022-10-26 09:47:12 - r - INFO: - Episode: 66/100, Reward: -93.00: Epislon: 0.010
2022-10-26 09:47:12 - r - INFO: - Episode: 67/100, Reward: -113.00: Epislon: 0.010
2022-10-26 09:47:12 - r - INFO: - Episode: 68/100, Reward: -191.00: Epislon: 0.010
2022-10-26 09:47:12 - r - INFO: - Episode: 69/100, Reward: -102.00: Epislon: 0.010
2022-10-26 09:47:13 - r - INFO: - Episode: 70/100, Reward: -187.00: Epislon: 0.010
2022-10-26 09:47:13 - r - INFO: - Episode: 71/100, Reward: -158.00: Epislon: 0.010
2022-10-26 09:47:13 - r - INFO: - Episode: 72/100, Reward: -166.00: Epislon: 0.010
2022-10-26 09:47:14 - r - INFO: - Episode: 73/100, Reward: -202.00: Epislon: 0.010
2022-10-26 09:47:14 - r - INFO: - Episode: 74/100, Reward: -179.00: Epislon: 0.010
2022-10-26 09:47:14 - r - INFO: - Episode: 75/100, Reward: -150.00: Epislon: 0.010
2022-10-26 09:47:14 - r - INFO: - Episode: 76/100, Reward: -170.00: Epislon: 0.010
2022-10-26 09:47:15 - r - INFO: - Episode: 77/100, Reward: -149.00: Epislon: 0.010
2022-10-26 09:47:15 - r - INFO: - Episode: 78/100, Reward: -119.00: Epislon: 0.010
2022-10-26 09:47:15 - r - INFO: - Episode: 79/100, Reward: -115.00: Epislon: 0.010
2022-10-26 09:47:15 - r - INFO: - Episode: 80/100, Reward: -97.00: Epislon: 0.010
2022-10-26 09:47:16 - r - INFO: - Episode: 81/100, Reward: -153.00: Epislon: 0.010
2022-10-26 09:47:16 - r - INFO: - Episode: 82/100, Reward: -97.00: Epislon: 0.010
2022-10-26 09:47:16 - r - INFO: - Episode: 83/100, Reward: -211.00: Epislon: 0.010
2022-10-26 09:47:16 - r - INFO: - Episode: 84/100, Reward: -195.00: Epislon: 0.010
2022-10-26 09:47:17 - r - INFO: - Episode: 85/100, Reward: -125.00: Epislon: 0.010
2022-10-26 09:47:17 - r - INFO: - Episode: 86/100, Reward: -155.00: Epislon: 0.010
2022-10-26 09:47:17 - r - INFO: - Episode: 87/100, Reward: -151.00: Epislon: 0.010
2022-10-26 09:47:18 - r - INFO: - Episode: 88/100, Reward: -194.00: Epislon: 0.010
2022-10-26 09:47:18 - r - INFO: - Episode: 89/100, Reward: -188.00: Epislon: 0.010
2022-10-26 09:47:18 - r - INFO: - Episode: 90/100, Reward: -195.00: Epislon: 0.010
2022-10-26 09:47:19 - r - INFO: - Episode: 91/100, Reward: -141.00: Epislon: 0.010
2022-10-26 09:47:19 - r - INFO: - Episode: 92/100, Reward: -132.00: Epislon: 0.010
2022-10-26 09:47:19 - r - INFO: - Episode: 93/100, Reward: -127.00: Epislon: 0.010
2022-10-26 09:47:19 - r - INFO: - Episode: 94/100, Reward: -195.00: Epislon: 0.010
2022-10-26 09:47:20 - r - INFO: - Episode: 95/100, Reward: -152.00: Epislon: 0.010
2022-10-26 09:47:20 - r - INFO: - Episode: 96/100, Reward: -145.00: Epislon: 0.010
2022-10-26 09:47:20 - r - INFO: - Episode: 97/100, Reward: -123.00: Epislon: 0.010
2022-10-26 09:47:20 - r - INFO: - Episode: 98/100, Reward: -176.00: Epislon: 0.010
2022-10-26 09:47:21 - r - INFO: - Episode: 99/100, Reward: -180.00: Epislon: 0.010
2022-10-26 09:47:21 - r - INFO: - Episode: 100/100, Reward: -124.00: Epislon: 0.010
2022-10-26 09:47:21 - r - INFO: - Finish training!

Binary file not shown.

After

Width:  |  Height:  |  Size: 55 KiB

View File

@@ -0,0 +1,101 @@
episodes,rewards,steps
0,-861.0,862
1,-252.0,253
2,-196.0,197
3,-390.0,391
4,-371.0,372
5,-237.0,238
6,-227.0,228
7,-228.0,229
8,-305.0,306
9,-234.0,235
10,-204.0,205
11,-277.0,278
12,-148.0,149
13,-372.0,373
14,-273.0,274
15,-105.0,106
16,-79.0,80
17,-112.0,113
18,-276.0,277
19,-148.0,149
20,-201.0,202
21,-173.0,174
22,-226.0,227
23,-154.0,155
24,-269.0,270
25,-191.0,192
26,-177.0,178
27,-209.0,210
28,-116.0,117
29,-117.0,118
30,-121.0,122
31,-208.0,209
32,-147.0,148
33,-104.0,105
34,-161.0,162
35,-144.0,145
36,-131.0,132
37,-226.0,227
38,-117.0,118
39,-344.0,345
40,-123.0,124
41,-232.0,233
42,-190.0,191
43,-176.0,177
44,-139.0,140
45,-410.0,411
46,-115.0,116
47,-118.0,119
48,-113.0,114
49,-355.0,356
50,-110.0,111
51,-148.0,149
52,-135.0,136
53,-220.0,221
54,-157.0,158
55,-130.0,131
56,-150.0,151
57,-254.0,255
58,-148.0,149
59,-108.0,109
60,-152.0,153
61,-107.0,108
62,-110.0,111
63,-266.0,267
64,-344.0,345
65,-93.0,94
66,-113.0,114
67,-191.0,192
68,-102.0,103
69,-187.0,188
70,-158.0,159
71,-166.0,167
72,-202.0,203
73,-179.0,180
74,-150.0,151
75,-170.0,171
76,-149.0,150
77,-119.0,120
78,-115.0,116
79,-97.0,98
80,-153.0,154
81,-97.0,98
82,-211.0,212
83,-195.0,196
84,-125.0,126
85,-155.0,156
86,-151.0,152
87,-194.0,195
88,-188.0,189
89,-195.0,196
90,-141.0,142
91,-132.0,133
92,-127.0,128
93,-195.0,196
94,-152.0,153
95,-145.0,146
96,-123.0,124
97,-176.0,177
98,-180.0,181
99,-124.0,125
1 episodes rewards steps
2 0 -861.0 862
3 1 -252.0 253
4 2 -196.0 197
5 3 -390.0 391
6 4 -371.0 372
7 5 -237.0 238
8 6 -227.0 228
9 7 -228.0 229
10 8 -305.0 306
11 9 -234.0 235
12 10 -204.0 205
13 11 -277.0 278
14 12 -148.0 149
15 13 -372.0 373
16 14 -273.0 274
17 15 -105.0 106
18 16 -79.0 80
19 17 -112.0 113
20 18 -276.0 277
21 19 -148.0 149
22 20 -201.0 202
23 21 -173.0 174
24 22 -226.0 227
25 23 -154.0 155
26 24 -269.0 270
27 25 -191.0 192
28 26 -177.0 178
29 27 -209.0 210
30 28 -116.0 117
31 29 -117.0 118
32 30 -121.0 122
33 31 -208.0 209
34 32 -147.0 148
35 33 -104.0 105
36 34 -161.0 162
37 35 -144.0 145
38 36 -131.0 132
39 37 -226.0 227
40 38 -117.0 118
41 39 -344.0 345
42 40 -123.0 124
43 41 -232.0 233
44 42 -190.0 191
45 43 -176.0 177
46 44 -139.0 140
47 45 -410.0 411
48 46 -115.0 116
49 47 -118.0 119
50 48 -113.0 114
51 49 -355.0 356
52 50 -110.0 111
53 51 -148.0 149
54 52 -135.0 136
55 53 -220.0 221
56 54 -157.0 158
57 55 -130.0 131
58 56 -150.0 151
59 57 -254.0 255
60 58 -148.0 149
61 59 -108.0 109
62 60 -152.0 153
63 61 -107.0 108
64 62 -110.0 111
65 63 -266.0 267
66 64 -344.0 345
67 65 -93.0 94
68 66 -113.0 114
69 67 -191.0 192
70 68 -102.0 103
71 69 -187.0 188
72 70 -158.0 159
73 71 -166.0 167
74 72 -202.0 203
75 73 -179.0 180
76 74 -150.0 151
77 75 -170.0 171
78 76 -149.0 150
79 77 -119.0 120
80 78 -115.0 116
81 79 -97.0 98
82 80 -153.0 154
83 81 -97.0 98
84 82 -211.0 212
85 83 -195.0 196
86 84 -125.0 126
87 85 -155.0 156
88 86 -151.0 152
89 87 -194.0 195
90 88 -188.0 189
91 89 -195.0 196
92 90 -141.0 142
93 91 -132.0 133
94 92 -127.0 128
95 93 -195.0 196
96 94 -152.0 153
97 95 -145.0 146
98 96 -123.0 124
99 97 -176.0 177
100 98 -180.0 181
101 99 -124.0 125