更新PPO,增加PER DQN

This commit is contained in:
johnjim0816
2022-11-14 21:35:28 +08:00
parent dc78698262
commit b8aec4c188
34 changed files with 1993 additions and 476 deletions

View File

@@ -0,0 +1,25 @@
general_cfg:
algo_name: PER_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: 200
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: 4

View File

@@ -0,0 +1,224 @@
2022-11-13 16:28:04 - r - INFO: - n_states: 4, n_actions: 2
2022-11-13 16:28:19 - r - INFO: - Start training!
2022-11-13 16:28:19 - r - INFO: - Env: CartPole-v1, Algorithm: PER_DQN, Device: cuda
2022-11-13 16:28:23 - r - INFO: - Episode: 1/200, Reward: 18.000, Step: 18
2022-11-13 16:28:24 - r - INFO: - Episode: 2/200, Reward: 35.000, Step: 35
2022-11-13 16:28:24 - r - INFO: - Episode: 3/200, Reward: 13.000, Step: 13
2022-11-13 16:28:24 - r - INFO: - Episode: 4/200, Reward: 20.000, Step: 20
2022-11-13 16:28:24 - r - INFO: - Episode: 5/200, Reward: 24.000, Step: 24
2022-11-13 16:28:24 - r - INFO: - Current episode 5 has the best eval reward: 9.100
2022-11-13 16:28:24 - r - INFO: - Episode: 6/200, Reward: 10.000, Step: 10
2022-11-13 16:28:24 - r - INFO: - Episode: 7/200, Reward: 20.000, Step: 20
2022-11-13 16:28:24 - r - INFO: - Episode: 8/200, Reward: 19.000, Step: 19
2022-11-13 16:28:25 - r - INFO: - Episode: 9/200, Reward: 30.000, Step: 30
2022-11-13 16:28:25 - r - INFO: - Episode: 10/200, Reward: 10.000, Step: 10
2022-11-13 16:28:25 - r - INFO: - Current episode 10 has the best eval reward: 9.200
2022-11-13 16:28:25 - r - INFO: - Episode: 11/200, Reward: 16.000, Step: 16
2022-11-13 16:28:25 - r - INFO: - Episode: 12/200, Reward: 16.000, Step: 16
2022-11-13 16:28:25 - r - INFO: - Episode: 13/200, Reward: 12.000, Step: 12
2022-11-13 16:28:25 - r - INFO: - Episode: 14/200, Reward: 28.000, Step: 28
2022-11-13 16:28:25 - r - INFO: - Episode: 15/200, Reward: 22.000, Step: 22
2022-11-13 16:28:25 - r - INFO: - Current episode 15 has the best eval reward: 9.300
2022-11-13 16:28:25 - r - INFO: - Episode: 16/200, Reward: 14.000, Step: 14
2022-11-13 16:28:25 - r - INFO: - Episode: 17/200, Reward: 9.000, Step: 9
2022-11-13 16:28:26 - r - INFO: - Episode: 18/200, Reward: 13.000, Step: 13
2022-11-13 16:28:26 - r - INFO: - Episode: 19/200, Reward: 19.000, Step: 19
2022-11-13 16:28:26 - r - INFO: - Episode: 20/200, Reward: 10.000, Step: 10
2022-11-13 16:28:26 - r - INFO: - Episode: 21/200, Reward: 10.000, Step: 10
2022-11-13 16:28:26 - r - INFO: - Episode: 22/200, Reward: 12.000, Step: 12
2022-11-13 16:28:26 - r - INFO: - Episode: 23/200, Reward: 9.000, Step: 9
2022-11-13 16:28:26 - r - INFO: - Episode: 24/200, Reward: 12.000, Step: 12
2022-11-13 16:28:26 - r - INFO: - Episode: 25/200, Reward: 11.000, Step: 11
2022-11-13 16:28:26 - r - INFO: - Current episode 25 has the best eval reward: 9.800
2022-11-13 16:28:26 - r - INFO: - Episode: 26/200, Reward: 11.000, Step: 11
2022-11-13 16:28:26 - r - INFO: - Episode: 27/200, Reward: 13.000, Step: 13
2022-11-13 16:28:26 - r - INFO: - Episode: 28/200, Reward: 11.000, Step: 11
2022-11-13 16:28:27 - r - INFO: - Episode: 29/200, Reward: 13.000, Step: 13
2022-11-13 16:28:27 - r - INFO: - Episode: 30/200, Reward: 20.000, Step: 20
2022-11-13 16:28:27 - r - INFO: - Current episode 30 has the best eval reward: 12.200
2022-11-13 16:28:27 - r - INFO: - Episode: 31/200, Reward: 16.000, Step: 16
2022-11-13 16:28:27 - r - INFO: - Episode: 32/200, Reward: 9.000, Step: 9
2022-11-13 16:28:27 - r - INFO: - Episode: 33/200, Reward: 16.000, Step: 16
2022-11-13 16:28:27 - r - INFO: - Episode: 34/200, Reward: 15.000, Step: 15
2022-11-13 16:28:27 - r - INFO: - Episode: 35/200, Reward: 12.000, Step: 12
2022-11-13 16:28:27 - r - INFO: - Current episode 35 has the best eval reward: 12.500
2022-11-13 16:28:27 - r - INFO: - Episode: 36/200, Reward: 12.000, Step: 12
2022-11-13 16:28:27 - r - INFO: - Episode: 37/200, Reward: 16.000, Step: 16
2022-11-13 16:28:28 - r - INFO: - Episode: 38/200, Reward: 13.000, Step: 13
2022-11-13 16:28:28 - r - INFO: - Episode: 39/200, Reward: 18.000, Step: 18
2022-11-13 16:28:28 - r - INFO: - Episode: 40/200, Reward: 18.000, Step: 18
2022-11-13 16:28:28 - r - INFO: - Current episode 40 has the best eval reward: 20.400
2022-11-13 16:28:28 - r - INFO: - Episode: 41/200, Reward: 48.000, Step: 48
2022-11-13 16:28:29 - r - INFO: - Episode: 42/200, Reward: 52.000, Step: 52
2022-11-13 16:28:29 - r - INFO: - Episode: 43/200, Reward: 33.000, Step: 33
2022-11-13 16:28:29 - r - INFO: - Episode: 44/200, Reward: 15.000, Step: 15
2022-11-13 16:28:29 - r - INFO: - Episode: 45/200, Reward: 18.000, Step: 18
2022-11-13 16:28:29 - r - INFO: - Episode: 46/200, Reward: 22.000, Step: 22
2022-11-13 16:28:29 - r - INFO: - Episode: 47/200, Reward: 19.000, Step: 19
2022-11-13 16:28:30 - r - INFO: - Episode: 48/200, Reward: 19.000, Step: 19
2022-11-13 16:28:30 - r - INFO: - Episode: 49/200, Reward: 11.000, Step: 11
2022-11-13 16:28:30 - r - INFO: - Episode: 50/200, Reward: 9.000, Step: 9
2022-11-13 16:28:30 - r - INFO: - Episode: 51/200, Reward: 10.000, Step: 10
2022-11-13 16:28:30 - r - INFO: - Episode: 52/200, Reward: 10.000, Step: 10
2022-11-13 16:28:30 - r - INFO: - Episode: 53/200, Reward: 10.000, Step: 10
2022-11-13 16:28:30 - r - INFO: - Episode: 54/200, Reward: 10.000, Step: 10
2022-11-13 16:28:30 - r - INFO: - Episode: 55/200, Reward: 9.000, Step: 9
2022-11-13 16:28:30 - r - INFO: - Episode: 56/200, Reward: 17.000, Step: 17
2022-11-13 16:28:31 - r - INFO: - Episode: 57/200, Reward: 75.000, Step: 75
2022-11-13 16:28:31 - r - INFO: - Episode: 58/200, Reward: 28.000, Step: 28
2022-11-13 16:28:31 - r - INFO: - Episode: 59/200, Reward: 30.000, Step: 30
2022-11-13 16:28:32 - r - INFO: - Episode: 60/200, Reward: 54.000, Step: 54
2022-11-13 16:28:32 - r - INFO: - Current episode 60 has the best eval reward: 34.600
2022-11-13 16:28:32 - r - INFO: - Episode: 61/200, Reward: 22.000, Step: 22
2022-11-13 16:28:32 - r - INFO: - Episode: 62/200, Reward: 28.000, Step: 28
2022-11-13 16:28:32 - r - INFO: - Episode: 63/200, Reward: 26.000, Step: 26
2022-11-13 16:28:33 - r - INFO: - Episode: 64/200, Reward: 32.000, Step: 32
2022-11-13 16:28:33 - r - INFO: - Episode: 65/200, Reward: 30.000, Step: 30
2022-11-13 16:28:33 - r - INFO: - Episode: 66/200, Reward: 29.000, Step: 29
2022-11-13 16:28:34 - r - INFO: - Episode: 67/200, Reward: 28.000, Step: 28
2022-11-13 16:28:34 - r - INFO: - Episode: 68/200, Reward: 38.000, Step: 38
2022-11-13 16:28:34 - r - INFO: - Episode: 69/200, Reward: 28.000, Step: 28
2022-11-13 16:28:34 - r - INFO: - Episode: 70/200, Reward: 22.000, Step: 22
2022-11-13 16:28:34 - r - INFO: - Current episode 70 has the best eval reward: 36.700
2022-11-13 16:28:35 - r - INFO: - Episode: 71/200, Reward: 40.000, Step: 40
2022-11-13 16:28:35 - r - INFO: - Episode: 72/200, Reward: 27.000, Step: 27
2022-11-13 16:28:35 - r - INFO: - Episode: 73/200, Reward: 24.000, Step: 24
2022-11-13 16:28:35 - r - INFO: - Episode: 74/200, Reward: 47.000, Step: 47
2022-11-13 16:28:36 - r - INFO: - Episode: 75/200, Reward: 127.000, Step: 127
2022-11-13 16:28:37 - r - INFO: - Episode: 76/200, Reward: 48.000, Step: 48
2022-11-13 16:28:37 - r - INFO: - Episode: 77/200, Reward: 27.000, Step: 27
2022-11-13 16:28:37 - r - INFO: - Episode: 78/200, Reward: 65.000, Step: 65
2022-11-13 16:28:38 - r - INFO: - Episode: 79/200, Reward: 75.000, Step: 75
2022-11-13 16:28:38 - r - INFO: - Episode: 80/200, Reward: 47.000, Step: 47
2022-11-13 16:28:38 - r - INFO: - Current episode 80 has the best eval reward: 37.200
2022-11-13 16:28:39 - r - INFO: - Episode: 81/200, Reward: 34.000, Step: 34
2022-11-13 16:28:39 - r - INFO: - Episode: 82/200, Reward: 38.000, Step: 38
2022-11-13 16:28:39 - r - INFO: - Episode: 83/200, Reward: 24.000, Step: 24
2022-11-13 16:28:39 - r - INFO: - Episode: 84/200, Reward: 47.000, Step: 47
2022-11-13 16:28:40 - r - INFO: - Episode: 85/200, Reward: 35.000, Step: 35
2022-11-13 16:28:40 - r - INFO: - Current episode 85 has the best eval reward: 66.900
2022-11-13 16:28:41 - r - INFO: - Episode: 86/200, Reward: 103.000, Step: 103
2022-11-13 16:28:41 - r - INFO: - Episode: 87/200, Reward: 64.000, Step: 64
2022-11-13 16:28:42 - r - INFO: - Episode: 88/200, Reward: 59.000, Step: 59
2022-11-13 16:28:43 - r - INFO: - Episode: 89/200, Reward: 200.000, Step: 200
2022-11-13 16:28:44 - r - INFO: - Episode: 90/200, Reward: 200.000, Step: 200
2022-11-13 16:28:46 - r - INFO: - Current episode 90 has the best eval reward: 200.000
2022-11-13 16:28:47 - r - INFO: - Episode: 91/200, Reward: 200.000, Step: 200
2022-11-13 16:28:48 - r - INFO: - Episode: 92/200, Reward: 200.000, Step: 200
2022-11-13 16:28:50 - r - INFO: - Episode: 93/200, Reward: 200.000, Step: 200
2022-11-13 16:28:51 - r - INFO: - Episode: 94/200, Reward: 200.000, Step: 200
2022-11-13 16:28:52 - r - INFO: - Episode: 95/200, Reward: 200.000, Step: 200
2022-11-13 16:28:54 - r - INFO: - Current episode 95 has the best eval reward: 200.000
2022-11-13 16:28:55 - r - INFO: - Episode: 96/200, Reward: 200.000, Step: 200
2022-11-13 16:28:56 - r - INFO: - Episode: 97/200, Reward: 200.000, Step: 200
2022-11-13 16:28:58 - r - INFO: - Episode: 98/200, Reward: 200.000, Step: 200
2022-11-13 16:28:59 - r - INFO: - Episode: 99/200, Reward: 200.000, Step: 200
2022-11-13 16:29:00 - r - INFO: - Episode: 100/200, Reward: 200.000, Step: 200
2022-11-13 16:29:02 - r - INFO: - Current episode 100 has the best eval reward: 200.000
2022-11-13 16:29:04 - r - INFO: - Episode: 101/200, Reward: 200.000, Step: 200
2022-11-13 16:29:05 - r - INFO: - Episode: 102/200, Reward: 200.000, Step: 200
2022-11-13 16:29:06 - r - INFO: - Episode: 103/200, Reward: 200.000, Step: 200
2022-11-13 16:29:07 - r - INFO: - Episode: 104/200, Reward: 200.000, Step: 200
2022-11-13 16:29:09 - r - INFO: - Episode: 105/200, Reward: 200.000, Step: 200
2022-11-13 16:29:10 - r - INFO: - Current episode 105 has the best eval reward: 200.000
2022-11-13 16:29:11 - r - INFO: - Episode: 106/200, Reward: 200.000, Step: 200
2022-11-13 16:29:13 - r - INFO: - Episode: 107/200, Reward: 200.000, Step: 200
2022-11-13 16:29:14 - r - INFO: - Episode: 108/200, Reward: 200.000, Step: 200
2022-11-13 16:29:16 - r - INFO: - Episode: 109/200, Reward: 200.000, Step: 200
2022-11-13 16:29:17 - r - INFO: - Episode: 110/200, Reward: 200.000, Step: 200
2022-11-13 16:29:20 - r - INFO: - Episode: 111/200, Reward: 200.000, Step: 200
2022-11-13 16:29:21 - r - INFO: - Episode: 112/200, Reward: 200.000, Step: 200
2022-11-13 16:29:22 - r - INFO: - Episode: 113/200, Reward: 200.000, Step: 200
2022-11-13 16:29:23 - r - INFO: - Episode: 114/200, Reward: 200.000, Step: 200
2022-11-13 16:29:25 - r - INFO: - Episode: 115/200, Reward: 200.000, Step: 200
2022-11-13 16:29:26 - r - INFO: - Current episode 115 has the best eval reward: 200.000
2022-11-13 16:29:27 - r - INFO: - Episode: 116/200, Reward: 200.000, Step: 200
2022-11-13 16:29:29 - r - INFO: - Episode: 117/200, Reward: 200.000, Step: 200
2022-11-13 16:29:30 - r - INFO: - Episode: 118/200, Reward: 200.000, Step: 200
2022-11-13 16:29:31 - r - INFO: - Episode: 119/200, Reward: 200.000, Step: 200
2022-11-13 16:29:33 - r - INFO: - Episode: 120/200, Reward: 200.000, Step: 200
2022-11-13 16:29:34 - r - INFO: - Current episode 120 has the best eval reward: 200.000
2022-11-13 16:29:35 - r - INFO: - Episode: 121/200, Reward: 200.000, Step: 200
2022-11-13 16:29:37 - r - INFO: - Episode: 122/200, Reward: 200.000, Step: 200
2022-11-13 16:29:38 - r - INFO: - Episode: 123/200, Reward: 200.000, Step: 200
2022-11-13 16:29:39 - r - INFO: - Episode: 124/200, Reward: 200.000, Step: 200
2022-11-13 16:29:41 - r - INFO: - Episode: 125/200, Reward: 200.000, Step: 200
2022-11-13 16:29:43 - r - INFO: - Episode: 126/200, Reward: 200.000, Step: 200
2022-11-13 16:29:45 - r - INFO: - Episode: 127/200, Reward: 200.000, Step: 200
2022-11-13 16:29:46 - r - INFO: - Episode: 128/200, Reward: 200.000, Step: 200
2022-11-13 16:29:47 - r - INFO: - Episode: 129/200, Reward: 200.000, Step: 200
2022-11-13 16:29:49 - r - INFO: - Episode: 130/200, Reward: 200.000, Step: 200
2022-11-13 16:29:51 - r - INFO: - Episode: 131/200, Reward: 200.000, Step: 200
2022-11-13 16:29:53 - r - INFO: - Episode: 132/200, Reward: 200.000, Step: 200
2022-11-13 16:29:54 - r - INFO: - Episode: 133/200, Reward: 200.000, Step: 200
2022-11-13 16:29:55 - r - INFO: - Episode: 134/200, Reward: 200.000, Step: 200
2022-11-13 16:29:57 - r - INFO: - Episode: 135/200, Reward: 200.000, Step: 200
2022-11-13 16:29:59 - r - INFO: - Episode: 136/200, Reward: 200.000, Step: 200
2022-11-13 16:30:01 - r - INFO: - Episode: 137/200, Reward: 185.000, Step: 185
2022-11-13 16:30:02 - r - INFO: - Episode: 138/200, Reward: 193.000, Step: 193
2022-11-13 16:30:03 - r - INFO: - Episode: 139/200, Reward: 192.000, Step: 192
2022-11-13 16:30:04 - r - INFO: - Episode: 140/200, Reward: 200.000, Step: 200
2022-11-13 16:30:07 - r - INFO: - Episode: 141/200, Reward: 200.000, Step: 200
2022-11-13 16:30:08 - r - INFO: - Episode: 142/200, Reward: 200.000, Step: 200
2022-11-13 16:30:10 - r - INFO: - Episode: 143/200, Reward: 200.000, Step: 200
2022-11-13 16:30:11 - r - INFO: - Episode: 144/200, Reward: 191.000, Step: 191
2022-11-13 16:30:12 - r - INFO: - Episode: 145/200, Reward: 200.000, Step: 200
2022-11-13 16:30:15 - r - INFO: - Episode: 146/200, Reward: 184.000, Step: 184
2022-11-13 16:30:17 - r - INFO: - Episode: 147/200, Reward: 198.000, Step: 198
2022-11-13 16:30:18 - r - INFO: - Episode: 148/200, Reward: 200.000, Step: 200
2022-11-13 16:30:19 - r - INFO: - Episode: 149/200, Reward: 200.000, Step: 200
2022-11-13 16:30:21 - r - INFO: - Episode: 150/200, Reward: 192.000, Step: 192
2022-11-13 16:30:23 - r - INFO: - Episode: 151/200, Reward: 186.000, Step: 186
2022-11-13 16:30:25 - r - INFO: - Episode: 152/200, Reward: 200.000, Step: 200
2022-11-13 16:30:26 - r - INFO: - Episode: 153/200, Reward: 194.000, Step: 194
2022-11-13 16:30:27 - r - INFO: - Episode: 154/200, Reward: 199.000, Step: 199
2022-11-13 16:30:29 - r - INFO: - Episode: 155/200, Reward: 183.000, Step: 183
2022-11-13 16:30:32 - r - INFO: - Episode: 156/200, Reward: 173.000, Step: 173
2022-11-13 16:30:33 - r - INFO: - Episode: 157/200, Reward: 197.000, Step: 197
2022-11-13 16:30:34 - r - INFO: - Episode: 158/200, Reward: 200.000, Step: 200
2022-11-13 16:30:36 - r - INFO: - Episode: 159/200, Reward: 200.000, Step: 200
2022-11-13 16:30:37 - r - INFO: - Episode: 160/200, Reward: 196.000, Step: 196
2022-11-13 16:30:40 - r - INFO: - Episode: 161/200, Reward: 200.000, Step: 200
2022-11-13 16:30:42 - r - INFO: - Episode: 162/200, Reward: 200.000, Step: 200
2022-11-13 16:30:43 - r - INFO: - Episode: 163/200, Reward: 194.000, Step: 194
2022-11-13 16:30:44 - r - INFO: - Episode: 164/200, Reward: 185.000, Step: 185
2022-11-13 16:30:45 - r - INFO: - Episode: 165/200, Reward: 173.000, Step: 173
2022-11-13 16:30:48 - r - INFO: - Episode: 166/200, Reward: 192.000, Step: 192
2022-11-13 16:30:49 - r - INFO: - Episode: 167/200, Reward: 164.000, Step: 164
2022-11-13 16:30:50 - r - INFO: - Episode: 168/200, Reward: 188.000, Step: 188
2022-11-13 16:30:52 - r - INFO: - Episode: 169/200, Reward: 189.000, Step: 189
2022-11-13 16:30:53 - r - INFO: - Episode: 170/200, Reward: 197.000, Step: 197
2022-11-13 16:30:55 - r - INFO: - Episode: 171/200, Reward: 187.000, Step: 187
2022-11-13 16:30:57 - r - INFO: - Episode: 172/200, Reward: 200.000, Step: 200
2022-11-13 16:30:58 - r - INFO: - Episode: 173/200, Reward: 195.000, Step: 195
2022-11-13 16:30:59 - r - INFO: - Episode: 174/200, Reward: 200.000, Step: 200
2022-11-13 16:31:01 - r - INFO: - Episode: 175/200, Reward: 195.000, Step: 195
2022-11-13 16:31:03 - r - INFO: - Episode: 176/200, Reward: 200.000, Step: 200
2022-11-13 16:31:05 - r - INFO: - Episode: 177/200, Reward: 200.000, Step: 200
2022-11-13 16:31:06 - r - INFO: - Episode: 178/200, Reward: 200.000, Step: 200
2022-11-13 16:31:07 - r - INFO: - Episode: 179/200, Reward: 200.000, Step: 200
2022-11-13 16:31:09 - r - INFO: - Episode: 180/200, Reward: 200.000, Step: 200
2022-11-13 16:31:11 - r - INFO: - Episode: 181/200, Reward: 200.000, Step: 200
2022-11-13 16:31:13 - r - INFO: - Episode: 182/200, Reward: 200.000, Step: 200
2022-11-13 16:31:14 - r - INFO: - Episode: 183/200, Reward: 200.000, Step: 200
2022-11-13 16:31:15 - r - INFO: - Episode: 184/200, Reward: 200.000, Step: 200
2022-11-13 16:31:17 - r - INFO: - Episode: 185/200, Reward: 173.000, Step: 173
2022-11-13 16:31:19 - r - INFO: - Episode: 186/200, Reward: 200.000, Step: 200
2022-11-13 16:31:21 - r - INFO: - Episode: 187/200, Reward: 200.000, Step: 200
2022-11-13 16:31:22 - r - INFO: - Episode: 188/200, Reward: 200.000, Step: 200
2022-11-13 16:31:23 - r - INFO: - Episode: 189/200, Reward: 200.000, Step: 200
2022-11-13 16:31:24 - r - INFO: - Episode: 190/200, Reward: 200.000, Step: 200
2022-11-13 16:31:26 - r - INFO: - Current episode 190 has the best eval reward: 200.000
2022-11-13 16:31:27 - r - INFO: - Episode: 191/200, Reward: 200.000, Step: 200
2022-11-13 16:31:29 - r - INFO: - Episode: 192/200, Reward: 200.000, Step: 200
2022-11-13 16:31:30 - r - INFO: - Episode: 193/200, Reward: 200.000, Step: 200
2022-11-13 16:31:31 - r - INFO: - Episode: 194/200, Reward: 200.000, Step: 200
2022-11-13 16:31:33 - r - INFO: - Episode: 195/200, Reward: 200.000, Step: 200
2022-11-13 16:31:34 - r - INFO: - Current episode 195 has the best eval reward: 200.000
2022-11-13 16:31:35 - r - INFO: - Episode: 196/200, Reward: 200.000, Step: 200
2022-11-13 16:31:37 - r - INFO: - Episode: 197/200, Reward: 200.000, Step: 200
2022-11-13 16:31:38 - r - INFO: - Episode: 198/200, Reward: 200.000, Step: 200
2022-11-13 16:31:39 - r - INFO: - Episode: 199/200, Reward: 200.000, Step: 200
2022-11-13 16:31:40 - r - INFO: - Episode: 200/200, Reward: 200.000, Step: 200
2022-11-13 16:31:42 - r - INFO: - Current episode 200 has the best eval reward: 200.000
2022-11-13 16:31:42 - r - INFO: - Finish training!

Binary file not shown.

After

Width:  |  Height:  |  Size: 48 KiB

View File

@@ -0,0 +1,201 @@
episodes,rewards,steps
0,18.0,18
1,35.0,35
2,13.0,13
3,20.0,20
4,24.0,24
5,10.0,10
6,20.0,20
7,19.0,19
8,30.0,30
9,10.0,10
10,16.0,16
11,16.0,16
12,12.0,12
13,28.0,28
14,22.0,22
15,14.0,14
16,9.0,9
17,13.0,13
18,19.0,19
19,10.0,10
20,10.0,10
21,12.0,12
22,9.0,9
23,12.0,12
24,11.0,11
25,11.0,11
26,13.0,13
27,11.0,11
28,13.0,13
29,20.0,20
30,16.0,16
31,9.0,9
32,16.0,16
33,15.0,15
34,12.0,12
35,12.0,12
36,16.0,16
37,13.0,13
38,18.0,18
39,18.0,18
40,48.0,48
41,52.0,52
42,33.0,33
43,15.0,15
44,18.0,18
45,22.0,22
46,19.0,19
47,19.0,19
48,11.0,11
49,9.0,9
50,10.0,10
51,10.0,10
52,10.0,10
53,10.0,10
54,9.0,9
55,17.0,17
56,75.0,75
57,28.0,28
58,30.0,30
59,54.0,54
60,22.0,22
61,28.0,28
62,26.0,26
63,32.0,32
64,30.0,30
65,29.0,29
66,28.0,28
67,38.0,38
68,28.0,28
69,22.0,22
70,40.0,40
71,27.0,27
72,24.0,24
73,47.0,47
74,127.0,127
75,48.0,48
76,27.0,27
77,65.0,65
78,75.0,75
79,47.0,47
80,34.0,34
81,38.0,38
82,24.0,24
83,47.0,47
84,35.0,35
85,103.0,103
86,64.0,64
87,59.0,59
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
100,200.0,200
101,200.0,200
102,200.0,200
103,200.0,200
104,200.0,200
105,200.0,200
106,200.0,200
107,200.0,200
108,200.0,200
109,200.0,200
110,200.0,200
111,200.0,200
112,200.0,200
113,200.0,200
114,200.0,200
115,200.0,200
116,200.0,200
117,200.0,200
118,200.0,200
119,200.0,200
120,200.0,200
121,200.0,200
122,200.0,200
123,200.0,200
124,200.0,200
125,200.0,200
126,200.0,200
127,200.0,200
128,200.0,200
129,200.0,200
130,200.0,200
131,200.0,200
132,200.0,200
133,200.0,200
134,200.0,200
135,200.0,200
136,185.0,185
137,193.0,193
138,192.0,192
139,200.0,200
140,200.0,200
141,200.0,200
142,200.0,200
143,191.0,191
144,200.0,200
145,184.0,184
146,198.0,198
147,200.0,200
148,200.0,200
149,192.0,192
150,186.0,186
151,200.0,200
152,194.0,194
153,199.0,199
154,183.0,183
155,173.0,173
156,197.0,197
157,200.0,200
158,200.0,200
159,196.0,196
160,200.0,200
161,200.0,200
162,194.0,194
163,185.0,185
164,173.0,173
165,192.0,192
166,164.0,164
167,188.0,188
168,189.0,189
169,197.0,197
170,187.0,187
171,200.0,200
172,195.0,195
173,200.0,200
174,195.0,195
175,200.0,200
176,200.0,200
177,200.0,200
178,200.0,200
179,200.0,200
180,200.0,200
181,200.0,200
182,200.0,200
183,200.0,200
184,173.0,173
185,200.0,200
186,200.0,200
187,200.0,200
188,200.0,200
189,200.0,200
190,200.0,200
191,200.0,200
192,200.0,200
193,200.0,200
194,200.0,200
195,200.0,200
196,200.0,200
197,200.0,200
198,200.0,200
199,200.0,200
1 episodes rewards steps
2 0 18.0 18
3 1 35.0 35
4 2 13.0 13
5 3 20.0 20
6 4 24.0 24
7 5 10.0 10
8 6 20.0 20
9 7 19.0 19
10 8 30.0 30
11 9 10.0 10
12 10 16.0 16
13 11 16.0 16
14 12 12.0 12
15 13 28.0 28
16 14 22.0 22
17 15 14.0 14
18 16 9.0 9
19 17 13.0 13
20 18 19.0 19
21 19 10.0 10
22 20 10.0 10
23 21 12.0 12
24 22 9.0 9
25 23 12.0 12
26 24 11.0 11
27 25 11.0 11
28 26 13.0 13
29 27 11.0 11
30 28 13.0 13
31 29 20.0 20
32 30 16.0 16
33 31 9.0 9
34 32 16.0 16
35 33 15.0 15
36 34 12.0 12
37 35 12.0 12
38 36 16.0 16
39 37 13.0 13
40 38 18.0 18
41 39 18.0 18
42 40 48.0 48
43 41 52.0 52
44 42 33.0 33
45 43 15.0 15
46 44 18.0 18
47 45 22.0 22
48 46 19.0 19
49 47 19.0 19
50 48 11.0 11
51 49 9.0 9
52 50 10.0 10
53 51 10.0 10
54 52 10.0 10
55 53 10.0 10
56 54 9.0 9
57 55 17.0 17
58 56 75.0 75
59 57 28.0 28
60 58 30.0 30
61 59 54.0 54
62 60 22.0 22
63 61 28.0 28
64 62 26.0 26
65 63 32.0 32
66 64 30.0 30
67 65 29.0 29
68 66 28.0 28
69 67 38.0 38
70 68 28.0 28
71 69 22.0 22
72 70 40.0 40
73 71 27.0 27
74 72 24.0 24
75 73 47.0 47
76 74 127.0 127
77 75 48.0 48
78 76 27.0 27
79 77 65.0 65
80 78 75.0 75
81 79 47.0 47
82 80 34.0 34
83 81 38.0 38
84 82 24.0 24
85 83 47.0 47
86 84 35.0 35
87 85 103.0 103
88 86 64.0 64
89 87 59.0 59
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
102 100 200.0 200
103 101 200.0 200
104 102 200.0 200
105 103 200.0 200
106 104 200.0 200
107 105 200.0 200
108 106 200.0 200
109 107 200.0 200
110 108 200.0 200
111 109 200.0 200
112 110 200.0 200
113 111 200.0 200
114 112 200.0 200
115 113 200.0 200
116 114 200.0 200
117 115 200.0 200
118 116 200.0 200
119 117 200.0 200
120 118 200.0 200
121 119 200.0 200
122 120 200.0 200
123 121 200.0 200
124 122 200.0 200
125 123 200.0 200
126 124 200.0 200
127 125 200.0 200
128 126 200.0 200
129 127 200.0 200
130 128 200.0 200
131 129 200.0 200
132 130 200.0 200
133 131 200.0 200
134 132 200.0 200
135 133 200.0 200
136 134 200.0 200
137 135 200.0 200
138 136 185.0 185
139 137 193.0 193
140 138 192.0 192
141 139 200.0 200
142 140 200.0 200
143 141 200.0 200
144 142 200.0 200
145 143 191.0 191
146 144 200.0 200
147 145 184.0 184
148 146 198.0 198
149 147 200.0 200
150 148 200.0 200
151 149 192.0 192
152 150 186.0 186
153 151 200.0 200
154 152 194.0 194
155 153 199.0 199
156 154 183.0 183
157 155 173.0 173
158 156 197.0 197
159 157 200.0 200
160 158 200.0 200
161 159 196.0 196
162 160 200.0 200
163 161 200.0 200
164 162 194.0 194
165 163 185.0 185
166 164 173.0 173
167 165 192.0 192
168 166 164.0 164
169 167 188.0 188
170 168 189.0 189
171 169 197.0 197
172 170 187.0 187
173 171 200.0 200
174 172 195.0 195
175 173 200.0 200
176 174 195.0 195
177 175 200.0 200
178 176 200.0 200
179 177 200.0 200
180 178 200.0 200
181 179 200.0 200
182 180 200.0 200
183 181 200.0 200
184 182 200.0 200
185 183 200.0 200
186 184 173.0 173
187 185 200.0 200
188 186 200.0 200
189 187 200.0 200
190 188 200.0 200
191 189 200.0 200
192 190 200.0 200
193 191 200.0 200
194 192 200.0 200
195 193 200.0 200
196 194 200.0 200
197 195 200.0 200
198 196 200.0 200
199 197 200.0 200
200 198 200.0 200
201 199 200.0 200