johnjim0816's picture
update CartPole-v1 NoisyDQN
54d82df
raw
history blame
20.8 kB
2022-12-17 20:40:03 - r - INFO: - Hyperparameters:
2022-12-17 20:40:03 - r - INFO: - ================================================================================
2022-12-17 20:40:03 - r - INFO: - Name Value Type
2022-12-17 20:40:03 - r - INFO: - env_name CartPole-v1 <class 'str'>
2022-12-17 20:40:03 - r - INFO: - new_step_api 1 <class 'bool'>
2022-12-17 20:40:03 - r - INFO: - wrapper None <class 'str'>
2022-12-17 20:40:03 - r - INFO: - render 0 <class 'bool'>
2022-12-17 20:40:03 - r - INFO: - algo_name PPO <class 'str'>
2022-12-17 20:40:03 - r - INFO: - mode train <class 'str'>
2022-12-17 20:40:03 - r - INFO: - seed 1 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - device cuda <class 'str'>
2022-12-17 20:40:03 - r - INFO: - train_eps 200 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - test_eps 10 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - eval_eps 10 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - eval_per_episode 5 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - max_steps 200 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - load_checkpoint 0 <class 'bool'>
2022-12-17 20:40:03 - r - INFO: - load_path Train_CartPole-v1_PPO-KL_20221206-054757 <class 'str'>
2022-12-17 20:40:03 - r - INFO: - show_fig 0 <class 'bool'>
2022-12-17 20:40:03 - r - INFO: - save_fig 1 <class 'bool'>
2022-12-17 20:40:03 - r - INFO: - ppo_type kl <class 'str'>
2022-12-17 20:40:03 - r - INFO: - continuous 0 <class 'bool'>
2022-12-17 20:40:03 - r - INFO: - gamma 0.99 <class 'float'>
2022-12-17 20:40:03 - r - INFO: - k_epochs 4 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - actor_lr 0.0003 <class 'float'>
2022-12-17 20:40:03 - r - INFO: - critic_lr 0.001 <class 'float'>
2022-12-17 20:40:03 - r - INFO: - eps_clip 0.2 <class 'float'>
2022-12-17 20:40:03 - r - INFO: - entropy_coef 0.01 <class 'float'>
2022-12-17 20:40:03 - r - INFO: - train_batch_size 100 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - sgd_batch_size 64 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - actor_hidden_dim 256 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - critic_hidden_dim 256 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - kl_alpha 2 <class 'int'>
2022-12-17 20:40:03 - r - INFO: - kl_beta 1.5 <class 'float'>
2022-12-17 20:40:03 - r - INFO: - kl_lambda 0.5 <class 'float'>
2022-12-17 20:40:03 - r - INFO: - kl_target 0.01 <class 'float'>
2022-12-17 20:40:03 - r - INFO: - ================================================================================
2022-12-17 20:40:03 - r - INFO: - n_states: 4, n_actions: 2
2022-12-17 20:40:03 - r - INFO: - Start training!
2022-12-17 20:40:03 - r - INFO: - Env: CartPole-v1, Algorithm: PPO, Device: cuda
2022-12-17 20:40:06 - r - INFO: - Episode: 1/200, Reward: 25.000, Step: 25
2022-12-17 20:40:06 - r - INFO: - Episode: 2/200, Reward: 15.000, Step: 15
2022-12-17 20:40:06 - r - INFO: - Episode: 3/200, Reward: 13.000, Step: 13
2022-12-17 20:40:06 - r - INFO: - Episode: 4/200, Reward: 14.000, Step: 14
2022-12-17 20:40:06 - r - INFO: - Episode: 5/200, Reward: 25.000, Step: 25
2022-12-17 20:40:06 - r - INFO: - Current episode 5 has the best eval reward: 23.900
2022-12-17 20:40:06 - r - INFO: - Episode: 6/200, Reward: 41.000, Step: 41
2022-12-17 20:40:06 - r - INFO: - Episode: 7/200, Reward: 25.000, Step: 25
2022-12-17 20:40:06 - r - INFO: - Episode: 8/200, Reward: 12.000, Step: 12
2022-12-17 20:40:06 - r - INFO: - Episode: 9/200, Reward: 37.000, Step: 37
2022-12-17 20:40:06 - r - INFO: - Episode: 10/200, Reward: 26.000, Step: 26
2022-12-17 20:40:07 - r - INFO: - Episode: 11/200, Reward: 12.000, Step: 12
2022-12-17 20:40:07 - r - INFO: - Episode: 12/200, Reward: 23.000, Step: 23
2022-12-17 20:40:07 - r - INFO: - Episode: 13/200, Reward: 27.000, Step: 27
2022-12-17 20:40:07 - r - INFO: - Episode: 14/200, Reward: 62.000, Step: 62
2022-12-17 20:40:07 - r - INFO: - Episode: 15/200, Reward: 13.000, Step: 13
2022-12-17 20:40:07 - r - INFO: - Current episode 15 has the best eval reward: 28.000
2022-12-17 20:40:07 - r - INFO: - Episode: 16/200, Reward: 81.000, Step: 81
2022-12-17 20:40:07 - r - INFO: - Episode: 17/200, Reward: 90.000, Step: 90
2022-12-17 20:40:07 - r - INFO: - Episode: 18/200, Reward: 41.000, Step: 41
2022-12-17 20:40:08 - r - INFO: - Episode: 19/200, Reward: 54.000, Step: 54
2022-12-17 20:40:08 - r - INFO: - Episode: 20/200, Reward: 100.000, Step: 100
2022-12-17 20:40:08 - r - INFO: - Current episode 20 has the best eval reward: 49.200
2022-12-17 20:40:08 - r - INFO: - Episode: 21/200, Reward: 19.000, Step: 19
2022-12-17 20:40:08 - r - INFO: - Episode: 22/200, Reward: 27.000, Step: 27
2022-12-17 20:40:08 - r - INFO: - Episode: 23/200, Reward: 61.000, Step: 61
2022-12-17 20:40:08 - r - INFO: - Episode: 24/200, Reward: 45.000, Step: 45
2022-12-17 20:40:09 - r - INFO: - Episode: 25/200, Reward: 36.000, Step: 36
2022-12-17 20:40:09 - r - INFO: - Current episode 25 has the best eval reward: 49.400
2022-12-17 20:40:09 - r - INFO: - Episode: 26/200, Reward: 90.000, Step: 90
2022-12-17 20:40:09 - r - INFO: - Episode: 27/200, Reward: 23.000, Step: 23
2022-12-17 20:40:09 - r - INFO: - Episode: 28/200, Reward: 42.000, Step: 42
2022-12-17 20:40:09 - r - INFO: - Episode: 29/200, Reward: 44.000, Step: 44
2022-12-17 20:40:10 - r - INFO: - Episode: 30/200, Reward: 110.000, Step: 110
2022-12-17 20:40:10 - r - INFO: - Current episode 30 has the best eval reward: 51.600
2022-12-17 20:40:10 - r - INFO: - Episode: 31/200, Reward: 21.000, Step: 21
2022-12-17 20:40:10 - r - INFO: - Episode: 32/200, Reward: 28.000, Step: 28
2022-12-17 20:40:10 - r - INFO: - Episode: 33/200, Reward: 44.000, Step: 44
2022-12-17 20:40:10 - r - INFO: - Episode: 34/200, Reward: 27.000, Step: 27
2022-12-17 20:40:11 - r - INFO: - Episode: 35/200, Reward: 45.000, Step: 45
2022-12-17 20:40:11 - r - INFO: - Current episode 35 has the best eval reward: 69.100
2022-12-17 20:40:11 - r - INFO: - Episode: 36/200, Reward: 29.000, Step: 29
2022-12-17 20:40:11 - r - INFO: - Episode: 37/200, Reward: 40.000, Step: 40
2022-12-17 20:40:12 - r - INFO: - Episode: 38/200, Reward: 66.000, Step: 66
2022-12-17 20:40:12 - r - INFO: - Episode: 39/200, Reward: 27.000, Step: 27
2022-12-17 20:40:12 - r - INFO: - Episode: 40/200, Reward: 75.000, Step: 75
2022-12-17 20:40:12 - r - INFO: - Episode: 41/200, Reward: 34.000, Step: 34
2022-12-17 20:40:12 - r - INFO: - Episode: 42/200, Reward: 153.000, Step: 153
2022-12-17 20:40:13 - r - INFO: - Episode: 43/200, Reward: 35.000, Step: 35
2022-12-17 20:40:13 - r - INFO: - Episode: 44/200, Reward: 86.000, Step: 86
2022-12-17 20:40:13 - r - INFO: - Episode: 45/200, Reward: 27.000, Step: 27
2022-12-17 20:40:14 - r - INFO: - Episode: 46/200, Reward: 141.000, Step: 141
2022-12-17 20:40:14 - r - INFO: - Episode: 47/200, Reward: 42.000, Step: 42
2022-12-17 20:40:14 - r - INFO: - Episode: 48/200, Reward: 53.000, Step: 53
2022-12-17 20:40:14 - r - INFO: - Episode: 49/200, Reward: 61.000, Step: 61
2022-12-17 20:40:14 - r - INFO: - Episode: 50/200, Reward: 178.000, Step: 178
2022-12-17 20:40:15 - r - INFO: - Current episode 50 has the best eval reward: 93.100
2022-12-17 20:40:16 - r - INFO: - Episode: 51/200, Reward: 81.000, Step: 81
2022-12-17 20:40:16 - r - INFO: - Episode: 52/200, Reward: 53.000, Step: 53
2022-12-17 20:40:16 - r - INFO: - Episode: 53/200, Reward: 100.000, Step: 100
2022-12-17 20:40:16 - r - INFO: - Episode: 54/200, Reward: 113.000, Step: 113
2022-12-17 20:40:16 - r - INFO: - Episode: 55/200, Reward: 143.000, Step: 143
2022-12-17 20:40:18 - r - INFO: - Current episode 55 has the best eval reward: 116.500
2022-12-17 20:40:18 - r - INFO: - Episode: 56/200, Reward: 38.000, Step: 38
2022-12-17 20:40:18 - r - INFO: - Episode: 57/200, Reward: 66.000, Step: 66
2022-12-17 20:40:18 - r - INFO: - Episode: 58/200, Reward: 68.000, Step: 68
2022-12-17 20:40:18 - r - INFO: - Episode: 59/200, Reward: 129.000, Step: 129
2022-12-17 20:40:18 - r - INFO: - Episode: 60/200, Reward: 32.000, Step: 32
2022-12-17 20:40:19 - r - INFO: - Episode: 61/200, Reward: 42.000, Step: 42
2022-12-17 20:40:19 - r - INFO: - Episode: 62/200, Reward: 121.000, Step: 121
2022-12-17 20:40:19 - r - INFO: - Episode: 63/200, Reward: 30.000, Step: 30
2022-12-17 20:40:20 - r - INFO: - Episode: 64/200, Reward: 93.000, Step: 93
2022-12-17 20:40:20 - r - INFO: - Episode: 65/200, Reward: 30.000, Step: 30
2022-12-17 20:40:21 - r - INFO: - Episode: 66/200, Reward: 49.000, Step: 49
2022-12-17 20:40:21 - r - INFO: - Episode: 67/200, Reward: 102.000, Step: 102
2022-12-17 20:40:21 - r - INFO: - Episode: 68/200, Reward: 200.000, Step: 200
2022-12-17 20:40:21 - r - INFO: - Episode: 69/200, Reward: 72.000, Step: 72
2022-12-17 20:40:21 - r - INFO: - Episode: 70/200, Reward: 164.000, Step: 164
2022-12-17 20:40:23 - r - INFO: - Current episode 70 has the best eval reward: 147.000
2022-12-17 20:40:23 - r - INFO: - Episode: 71/200, Reward: 97.000, Step: 97
2022-12-17 20:40:23 - r - INFO: - Episode: 72/200, Reward: 16.000, Step: 16
2022-12-17 20:40:24 - r - INFO: - Episode: 73/200, Reward: 184.000, Step: 184
2022-12-17 20:40:24 - r - INFO: - Episode: 74/200, Reward: 103.000, Step: 103
2022-12-17 20:40:24 - r - INFO: - Episode: 75/200, Reward: 157.000, Step: 157
2022-12-17 20:40:26 - r - INFO: - Current episode 75 has the best eval reward: 152.700
2022-12-17 20:40:26 - r - INFO: - Episode: 76/200, Reward: 142.000, Step: 142
2022-12-17 20:40:26 - r - INFO: - Episode: 77/200, Reward: 46.000, Step: 46
2022-12-17 20:40:26 - r - INFO: - Episode: 78/200, Reward: 123.000, Step: 123
2022-12-17 20:40:26 - r - INFO: - Episode: 79/200, Reward: 128.000, Step: 128
2022-12-17 20:40:27 - r - INFO: - Episode: 80/200, Reward: 121.000, Step: 121
2022-12-17 20:40:28 - r - INFO: - Episode: 81/200, Reward: 150.000, Step: 150
2022-12-17 20:40:28 - r - INFO: - Episode: 82/200, Reward: 134.000, Step: 134
2022-12-17 20:40:28 - r - INFO: - Episode: 83/200, Reward: 132.000, Step: 132
2022-12-17 20:40:29 - r - INFO: - Episode: 84/200, Reward: 127.000, Step: 127
2022-12-17 20:40:29 - r - INFO: - Episode: 85/200, Reward: 199.000, Step: 199
2022-12-17 20:40:31 - r - INFO: - Current episode 85 has the best eval reward: 174.800
2022-12-17 20:40:31 - r - INFO: - Episode: 86/200, Reward: 164.000, Step: 164
2022-12-17 20:40:32 - r - INFO: - Episode: 87/200, Reward: 200.000, Step: 200
2022-12-17 20:40:32 - r - INFO: - Episode: 88/200, Reward: 97.000, Step: 97
2022-12-17 20:40:32 - r - INFO: - Episode: 89/200, Reward: 177.000, Step: 177
2022-12-17 20:40:32 - r - INFO: - Episode: 90/200, Reward: 77.000, Step: 77
2022-12-17 20:40:33 - r - INFO: - Episode: 91/200, Reward: 62.000, Step: 62
2022-12-17 20:40:33 - r - INFO: - Episode: 92/200, Reward: 48.000, Step: 48
2022-12-17 20:40:33 - r - INFO: - Episode: 93/200, Reward: 98.000, Step: 98
2022-12-17 20:40:33 - r - INFO: - Episode: 94/200, Reward: 25.000, Step: 25
2022-12-17 20:40:33 - r - INFO: - Episode: 95/200, Reward: 200.000, Step: 200
2022-12-17 20:40:38 - r - INFO: - Current episode 95 has the best eval reward: 178.200
2022-12-17 20:40:38 - r - INFO: - Episode: 96/200, Reward: 144.000, Step: 144
2022-12-17 20:40:38 - r - INFO: - Episode: 97/200, Reward: 200.000, Step: 200
2022-12-17 20:40:38 - r - INFO: - Episode: 98/200, Reward: 171.000, Step: 171
2022-12-17 20:40:39 - r - INFO: - Episode: 99/200, Reward: 200.000, Step: 200
2022-12-17 20:40:39 - r - INFO: - Episode: 100/200, Reward: 159.000, Step: 159
2022-12-17 20:40:42 - r - INFO: - Episode: 101/200, Reward: 200.000, Step: 200
2022-12-17 20:40:42 - r - INFO: - Episode: 102/200, Reward: 200.000, Step: 200
2022-12-17 20:40:42 - r - INFO: - Episode: 103/200, Reward: 200.000, Step: 200
2022-12-17 20:40:42 - r - INFO: - Episode: 104/200, Reward: 200.000, Step: 200
2022-12-17 20:40:43 - r - INFO: - Episode: 105/200, Reward: 200.000, Step: 200
2022-12-17 20:40:45 - r - INFO: - Current episode 105 has the best eval reward: 199.000
2022-12-17 20:40:46 - r - INFO: - Episode: 106/200, Reward: 200.000, Step: 200
2022-12-17 20:40:46 - r - INFO: - Episode: 107/200, Reward: 115.000, Step: 115
2022-12-17 20:40:46 - r - INFO: - Episode: 108/200, Reward: 145.000, Step: 145
2022-12-17 20:40:46 - r - INFO: - Episode: 109/200, Reward: 142.000, Step: 142
2022-12-17 20:40:46 - r - INFO: - Episode: 110/200, Reward: 200.000, Step: 200
2022-12-17 20:40:49 - r - INFO: - Episode: 111/200, Reward: 200.000, Step: 200
2022-12-17 20:40:49 - r - INFO: - Episode: 112/200, Reward: 200.000, Step: 200
2022-12-17 20:40:49 - r - INFO: - Episode: 113/200, Reward: 200.000, Step: 200
2022-12-17 20:40:50 - r - INFO: - Episode: 114/200, Reward: 72.000, Step: 72
2022-12-17 20:40:50 - r - INFO: - Episode: 115/200, Reward: 198.000, Step: 198
2022-12-17 20:40:51 - r - INFO: - Episode: 116/200, Reward: 26.000, Step: 26
2022-12-17 20:40:52 - r - INFO: - Episode: 117/200, Reward: 166.000, Step: 166
2022-12-17 20:40:52 - r - INFO: - Episode: 118/200, Reward: 18.000, Step: 18
2022-12-17 20:40:52 - r - INFO: - Episode: 119/200, Reward: 18.000, Step: 18
2022-12-17 20:40:52 - r - INFO: - Episode: 120/200, Reward: 35.000, Step: 35
2022-12-17 20:40:53 - r - INFO: - Episode: 121/200, Reward: 37.000, Step: 37
2022-12-17 20:40:53 - r - INFO: - Episode: 122/200, Reward: 123.000, Step: 123
2022-12-17 20:40:54 - r - INFO: - Episode: 123/200, Reward: 108.000, Step: 108
2022-12-17 20:40:54 - r - INFO: - Episode: 124/200, Reward: 108.000, Step: 108
2022-12-17 20:40:54 - r - INFO: - Episode: 125/200, Reward: 131.000, Step: 131
2022-12-17 20:40:55 - r - INFO: - Episode: 126/200, Reward: 106.000, Step: 106
2022-12-17 20:40:55 - r - INFO: - Episode: 127/200, Reward: 43.000, Step: 43
2022-12-17 20:40:56 - r - INFO: - Episode: 128/200, Reward: 68.000, Step: 68
2022-12-17 20:40:56 - r - INFO: - Episode: 129/200, Reward: 83.000, Step: 83
2022-12-17 20:40:56 - r - INFO: - Episode: 130/200, Reward: 178.000, Step: 178
2022-12-17 20:40:58 - r - INFO: - Episode: 131/200, Reward: 200.000, Step: 200
2022-12-17 20:40:59 - r - INFO: - Episode: 132/200, Reward: 200.000, Step: 200
2022-12-17 20:40:59 - r - INFO: - Episode: 133/200, Reward: 200.000, Step: 200
2022-12-17 20:40:59 - r - INFO: - Episode: 134/200, Reward: 200.000, Step: 200
2022-12-17 20:41:00 - r - INFO: - Episode: 135/200, Reward: 163.000, Step: 163
2022-12-17 20:41:02 - r - INFO: - Episode: 136/200, Reward: 141.000, Step: 141
2022-12-17 20:41:02 - r - INFO: - Episode: 137/200, Reward: 194.000, Step: 194
2022-12-17 20:41:03 - r - INFO: - Episode: 138/200, Reward: 200.000, Step: 200
2022-12-17 20:41:03 - r - INFO: - Episode: 139/200, Reward: 200.000, Step: 200
2022-12-17 20:41:03 - r - INFO: - Episode: 140/200, Reward: 200.000, Step: 200
2022-12-17 20:41:06 - r - INFO: - Current episode 140 has the best eval reward: 200.000
2022-12-17 20:41:06 - r - INFO: - Episode: 141/200, Reward: 200.000, Step: 200
2022-12-17 20:41:06 - r - INFO: - Episode: 142/200, Reward: 177.000, Step: 177
2022-12-17 20:41:07 - r - INFO: - Episode: 143/200, Reward: 105.000, Step: 105
2022-12-17 20:41:07 - r - INFO: - Episode: 144/200, Reward: 101.000, Step: 101
2022-12-17 20:41:07 - r - INFO: - Episode: 145/200, Reward: 158.000, Step: 158
2022-12-17 20:41:09 - r - INFO: - Episode: 146/200, Reward: 148.000, Step: 148
2022-12-17 20:41:09 - r - INFO: - Episode: 147/200, Reward: 177.000, Step: 177
2022-12-17 20:41:10 - r - INFO: - Episode: 148/200, Reward: 200.000, Step: 200
2022-12-17 20:41:10 - r - INFO: - Episode: 149/200, Reward: 200.000, Step: 200
2022-12-17 20:41:10 - r - INFO: - Episode: 150/200, Reward: 200.000, Step: 200
2022-12-17 20:41:13 - r - INFO: - Current episode 150 has the best eval reward: 200.000
2022-12-17 20:41:13 - r - INFO: - Episode: 151/200, Reward: 200.000, Step: 200
2022-12-17 20:41:13 - r - INFO: - Episode: 152/200, Reward: 200.000, Step: 200
2022-12-17 20:41:14 - r - INFO: - Episode: 153/200, Reward: 200.000, Step: 200
2022-12-17 20:41:14 - r - INFO: - Episode: 154/200, Reward: 157.000, Step: 157
2022-12-17 20:41:14 - r - INFO: - Episode: 155/200, Reward: 96.000, Step: 96
2022-12-17 20:41:16 - r - INFO: - Episode: 156/200, Reward: 150.000, Step: 150
2022-12-17 20:41:17 - r - INFO: - Episode: 157/200, Reward: 171.000, Step: 171
2022-12-17 20:41:17 - r - INFO: - Episode: 158/200, Reward: 200.000, Step: 200
2022-12-17 20:41:17 - r - INFO: - Episode: 159/200, Reward: 200.000, Step: 200
2022-12-17 20:41:18 - r - INFO: - Episode: 160/200, Reward: 200.000, Step: 200
2022-12-17 20:41:20 - r - INFO: - Current episode 160 has the best eval reward: 200.000
2022-12-17 20:41:20 - r - INFO: - Episode: 161/200, Reward: 200.000, Step: 200
2022-12-17 20:41:21 - r - INFO: - Episode: 162/200, Reward: 200.000, Step: 200
2022-12-17 20:41:21 - r - INFO: - Episode: 163/200, Reward: 200.000, Step: 200
2022-12-17 20:41:21 - r - INFO: - Episode: 164/200, Reward: 200.000, Step: 200
2022-12-17 20:41:22 - r - INFO: - Episode: 165/200, Reward: 200.000, Step: 200
2022-12-17 20:41:24 - r - INFO: - Episode: 166/200, Reward: 200.000, Step: 200
2022-12-17 20:41:25 - r - INFO: - Episode: 167/200, Reward: 169.000, Step: 169
2022-12-17 20:41:25 - r - INFO: - Episode: 168/200, Reward: 200.000, Step: 200
2022-12-17 20:41:25 - r - INFO: - Episode: 169/200, Reward: 200.000, Step: 200
2022-12-17 20:41:26 - r - INFO: - Episode: 170/200, Reward: 200.000, Step: 200
2022-12-17 20:41:28 - r - INFO: - Episode: 171/200, Reward: 195.000, Step: 195
2022-12-17 20:41:28 - r - INFO: - Episode: 172/200, Reward: 69.000, Step: 69
2022-12-17 20:41:29 - r - INFO: - Episode: 173/200, Reward: 194.000, Step: 194
2022-12-17 20:41:29 - r - INFO: - Episode: 174/200, Reward: 179.000, Step: 179
2022-12-17 20:41:29 - r - INFO: - Episode: 175/200, Reward: 137.000, Step: 137
2022-12-17 20:41:31 - r - INFO: - Episode: 176/200, Reward: 139.000, Step: 139
2022-12-17 20:41:31 - r - INFO: - Episode: 177/200, Reward: 142.000, Step: 142
2022-12-17 20:41:31 - r - INFO: - Episode: 178/200, Reward: 149.000, Step: 149
2022-12-17 20:41:32 - r - INFO: - Episode: 179/200, Reward: 186.000, Step: 186
2022-12-17 20:41:32 - r - INFO: - Episode: 180/200, Reward: 154.000, Step: 154
2022-12-17 20:41:34 - r - INFO: - Episode: 181/200, Reward: 172.000, Step: 172
2022-12-17 20:41:35 - r - INFO: - Episode: 182/200, Reward: 200.000, Step: 200
2022-12-17 20:41:35 - r - INFO: - Episode: 183/200, Reward: 172.000, Step: 172
2022-12-17 20:41:35 - r - INFO: - Episode: 184/200, Reward: 197.000, Step: 197
2022-12-17 20:41:36 - r - INFO: - Episode: 185/200, Reward: 167.000, Step: 167
2022-12-17 20:41:38 - r - INFO: - Episode: 186/200, Reward: 171.000, Step: 171
2022-12-17 20:41:38 - r - INFO: - Episode: 187/200, Reward: 181.000, Step: 181
2022-12-17 20:41:38 - r - INFO: - Episode: 188/200, Reward: 200.000, Step: 200
2022-12-17 20:41:39 - r - INFO: - Episode: 189/200, Reward: 145.000, Step: 145
2022-12-17 20:41:39 - r - INFO: - Episode: 190/200, Reward: 200.000, Step: 200
2022-12-17 20:41:42 - r - INFO: - Episode: 191/200, Reward: 189.000, Step: 189
2022-12-17 20:41:42 - r - INFO: - Episode: 192/200, Reward: 164.000, Step: 164
2022-12-17 20:41:42 - r - INFO: - Episode: 193/200, Reward: 160.000, Step: 160
2022-12-17 20:41:42 - r - INFO: - Episode: 194/200, Reward: 121.000, Step: 121
2022-12-17 20:41:42 - r - INFO: - Episode: 195/200, Reward: 63.000, Step: 63
2022-12-17 20:41:44 - r - INFO: - Episode: 196/200, Reward: 100.000, Step: 100
2022-12-17 20:41:44 - r - INFO: - Episode: 197/200, Reward: 119.000, Step: 119
2022-12-17 20:41:44 - r - INFO: - Episode: 198/200, Reward: 138.000, Step: 138
2022-12-17 20:41:44 - r - INFO: - Episode: 199/200, Reward: 123.000, Step: 123
2022-12-17 20:41:44 - r - INFO: - Episode: 200/200, Reward: 113.000, Step: 113
2022-12-17 20:41:46 - r - INFO: - Finish training!