| 2023-05-17 22:41:29 - SimpleLog - INFO: - General Configs: | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================ | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - Name Value Type | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - env_name gym <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - algo_name DuelingDQN <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - mode train <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - device cpu <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - seed 1 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - max_episode 100 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - max_step 200 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - collect_traj 0 <class 'bool'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - mp_backend ray <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - n_workers 2 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - online_eval 1 <class 'bool'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - model_save_fre 500 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - load_checkpoint 0 <class 'bool'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_DQN_20230515-211721 <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - load_model_step best <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================ | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - Algo Configs: | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================ | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - Name Value Type | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - dueling 1 <class 'bool'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - epsilon_start 0.95 <class 'float'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - epsilon_end 0.01 <class 'float'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - epsilon_decay 500 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - gamma 0.95 <class 'float'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - lr 0.0001 <class 'float'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - buffer_size 100000 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - batch_size 64 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - target_update 4 <class 'int'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - value_layers [{'layer_type': 'linear', 'layer_dim': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_dim': [256], 'activation': 'relu'}] <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================ | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - Env Configs: | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================ | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - Name Value Type | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - id CartPole-v1 <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - render_mode None <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - wrapper None <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'> | |
| 2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================ | |
| 2023-05-17 22:41:35 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2) | |
| 2023-05-17 22:41:38 - RayLog - INFO: - Worker 1 finished episode 0 with reward 22.0 in 22 steps | |
| 2023-05-17 22:41:38 - RayLog - INFO: - Worker 0 finished episode 0 with reward 23.0 in 23 steps | |
| 2023-05-17 22:41:38 - RayLog - INFO: - Worker 0 finished episode 2 with reward 10.0 in 10 steps | |
| 2023-05-17 22:41:38 - RayLog - INFO: - Worker 0 finished episode 3 with reward 9.0 in 9 steps | |
| 2023-05-17 22:41:38 - RayLog - INFO: - Worker 1 finished episode 2 with reward 29.0 in 29 steps | |
| 2023-05-17 22:41:38 - RayLog - INFO: - Worker 0 finished episode 4 with reward 11.0 in 11 steps | |
| 2023-05-17 22:41:39 - RayLog - INFO: - Worker 0 finished episode 6 with reward 15.0 in 15 steps | |
| 2023-05-17 22:41:39 - RayLog - INFO: - Worker 1 finished episode 5 with reward 18.0 in 18 steps | |
| 2023-05-17 22:41:39 - RayLog - INFO: - Worker 0 finished episode 7 with reward 9.0 in 9 steps | |
| 2023-05-17 22:41:39 - RayLog - INFO: - Worker 1 finished episode 8 with reward 11.0 in 11 steps | |
| 2023-05-17 22:41:39 - RayLog - INFO: - Worker 1 finished episode 10 with reward 13.0 in 13 steps | |
| 2023-05-17 22:41:39 - RayLog - INFO: - Worker 0 finished episode 9 with reward 25.0 in 25 steps | |
| 2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 12 with reward 12.0 in 12 steps | |
| 2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 13 with reward 10.0 in 10 steps | |
| 2023-05-17 22:41:40 - RayLog - INFO: - Worker 1 finished episode 11 with reward 33.0 in 33 steps | |
| 2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 14 with reward 9.0 in 9 steps | |
| 2023-05-17 22:41:40 - RayLog - INFO: - Worker 1 finished episode 15 with reward 10.0 in 10 steps | |
| 2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 16 with reward 13.0 in 13 steps | |
| 2023-05-17 22:41:40 - RayLog - INFO: - Worker 1 finished episode 17 with reward 16.0 in 16 steps | |
| 2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 18 with reward 9.0 in 9 steps | |
| 2023-05-17 22:41:41 - RayLog - INFO: - Worker 0 finished episode 20 with reward 11.0 in 11 steps | |
| 2023-05-17 22:41:41 - RayLog - INFO: - Worker 1 finished episode 19 with reward 16.0 in 16 steps | |
| 2023-05-17 22:41:41 - RayLog - INFO: - Worker 0 finished episode 21 with reward 18.0 in 18 steps | |
| 2023-05-17 22:41:41 - RayLog - INFO: - Worker 1 finished episode 22 with reward 18.0 in 18 steps | |
| 2023-05-17 22:41:41 - RayLog - INFO: - Worker 0 finished episode 23 with reward 11.0 in 11 steps | |
| 2023-05-17 22:41:41 - RayLog - INFO: - Worker 1 finished episode 24 with reward 9.0 in 9 steps | |
| 2023-05-17 22:41:41 - RayLog - INFO: - Worker 1 finished episode 26 with reward 9.0 in 9 steps | |
| 2023-05-17 22:41:41 - RayLog - INFO: - Worker 0 finished episode 25 with reward 10.0 in 10 steps | |
| 2023-05-17 22:41:42 - RayLog - INFO: - Worker 0 finished episode 28 with reward 11.0 in 11 steps | |
| 2023-05-17 22:41:42 - RayLog - INFO: - Worker 1 finished episode 27 with reward 12.0 in 12 steps | |
| 2023-05-17 22:41:42 - RayLog - INFO: - Worker 0 finished episode 29 with reward 15.0 in 15 steps | |
| 2023-05-17 22:41:42 - RayLog - INFO: - Worker 1 finished episode 30 with reward 19.0 in 19 steps | |
| 2023-05-17 22:41:42 - RayLog - INFO: - Worker 0 finished episode 31 with reward 10.0 in 10 steps | |
| 2023-05-17 22:41:42 - RayLog - INFO: - Worker 1 finished episode 32 with reward 13.0 in 13 steps | |
| 2023-05-17 22:41:44 - RayLog - INFO: - update_step: 500, online_eval_reward: 200.000 | |
| 2023-05-17 22:41:44 - RayLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-05-17 22:41:45 - RayLog - INFO: - Worker 0 finished episode 33 with reward 97.0 in 97 steps | |
| 2023-05-17 22:41:45 - RayLog - INFO: - Worker 1 finished episode 34 with reward 96.0 in 96 steps | |
| 2023-05-17 22:41:46 - RayLog - INFO: - Worker 1 finished episode 36 with reward 24.0 in 24 steps | |
| 2023-05-17 22:41:46 - RayLog - INFO: - Worker 0 finished episode 35 with reward 34.0 in 34 steps | |
| 2023-05-17 22:41:46 - RayLog - INFO: - Worker 1 finished episode 37 with reward 17.0 in 17 steps | |
| 2023-05-17 22:41:46 - RayLog - INFO: - Worker 0 finished episode 38 with reward 23.0 in 23 steps | |
| 2023-05-17 22:41:46 - RayLog - INFO: - Worker 1 finished episode 39 with reward 16.0 in 16 steps | |
| 2023-05-17 22:41:47 - RayLog - INFO: - Worker 1 finished episode 41 with reward 17.0 in 17 steps | |
| 2023-05-17 22:41:47 - RayLog - INFO: - Worker 0 finished episode 40 with reward 24.0 in 24 steps | |
| 2023-05-17 22:41:47 - RayLog - INFO: - Worker 1 finished episode 42 with reward 21.0 in 21 steps | |
| 2023-05-17 22:41:47 - RayLog - INFO: - Worker 0 finished episode 43 with reward 29.0 in 29 steps | |
| 2023-05-17 22:41:47 - RayLog - INFO: - Worker 1 finished episode 44 with reward 22.0 in 22 steps | |
| 2023-05-17 22:41:49 - RayLog - INFO: - update_step: 1000, online_eval_reward: 100.000 | |
| 2023-05-17 22:41:49 - RayLog - INFO: - Worker 0 finished episode 45 with reward 84.0 in 84 steps | |
| 2023-05-17 22:41:49 - RayLog - INFO: - Worker 1 finished episode 46 with reward 75.0 in 75 steps | |
| 2023-05-17 22:41:50 - RayLog - INFO: - Worker 1 finished episode 48 with reward 52.0 in 52 steps | |
| 2023-05-17 22:41:50 - RayLog - INFO: - Worker 0 finished episode 47 with reward 66.0 in 66 steps | |
| 2023-05-17 22:41:51 - RayLog - INFO: - Worker 1 finished episode 49 with reward 63.0 in 63 steps | |
| 2023-05-17 22:41:52 - RayLog - INFO: - Worker 0 finished episode 50 with reward 94.0 in 94 steps | |
| 2023-05-17 22:41:53 - RayLog - INFO: - Worker 1 finished episode 51 with reward 75.0 in 75 steps | |
| 2023-05-17 22:41:54 - RayLog - INFO: - update_step: 1500, online_eval_reward: 120.000 | |
| 2023-05-17 22:41:54 - RayLog - INFO: - Worker 0 finished episode 52 with reward 102.0 in 102 steps | |
| 2023-05-17 22:41:55 - RayLog - INFO: - Worker 1 finished episode 53 with reward 93.0 in 93 steps | |
| 2023-05-17 22:41:57 - RayLog - INFO: - Worker 1 finished episode 55 with reward 126.0 in 126 steps | |
| 2023-05-17 22:41:58 - RayLog - INFO: - Worker 0 finished episode 54 with reward 200.0 in 200 steps | |
| 2023-05-17 22:41:59 - RayLog - INFO: - update_step: 2000, online_eval_reward: 200.000 | |
| 2023-05-17 22:42:01 - RayLog - INFO: - Worker 1 finished episode 56 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:02 - RayLog - INFO: - Worker 0 finished episode 57 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:04 - RayLog - INFO: - update_step: 2500, online_eval_reward: 167.000 | |
| 2023-05-17 22:42:05 - RayLog - INFO: - Worker 1 finished episode 58 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:06 - RayLog - INFO: - Worker 0 finished episode 59 with reward 168.0 in 168 steps | |
| 2023-05-17 22:42:09 - RayLog - INFO: - Worker 0 finished episode 61 with reward 164.0 in 164 steps | |
| 2023-05-17 22:42:09 - RayLog - INFO: - update_step: 3000, online_eval_reward: 145.000 | |
| 2023-05-17 22:42:09 - RayLog - INFO: - Worker 1 finished episode 60 with reward 189.0 in 189 steps | |
| 2023-05-17 22:42:12 - RayLog - INFO: - Worker 0 finished episode 62 with reward 152.0 in 152 steps | |
| 2023-05-17 22:42:12 - RayLog - INFO: - Worker 1 finished episode 63 with reward 162.0 in 162 steps | |
| 2023-05-17 22:42:14 - RayLog - INFO: - update_step: 3500, online_eval_reward: 151.000 | |
| 2023-05-17 22:42:15 - RayLog - INFO: - Worker 0 finished episode 64 with reward 143.0 in 143 steps | |
| 2023-05-17 22:42:16 - RayLog - INFO: - Worker 1 finished episode 65 with reward 163.0 in 163 steps | |
| 2023-05-17 22:42:19 - RayLog - INFO: - Worker 0 finished episode 66 with reward 187.0 in 187 steps | |
| 2023-05-17 22:42:19 - RayLog - INFO: - update_step: 4000, online_eval_reward: 189.000 | |
| 2023-05-17 22:42:20 - RayLog - INFO: - Worker 1 finished episode 67 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:22 - RayLog - INFO: - Worker 0 finished episode 68 with reward 173.0 in 173 steps | |
| 2023-05-17 22:42:23 - RayLog - INFO: - Worker 1 finished episode 69 with reward 170.0 in 170 steps | |
| 2023-05-17 22:42:24 - RayLog - INFO: - update_step: 4500, online_eval_reward: 178.000 | |
| 2023-05-17 22:42:26 - RayLog - INFO: - Worker 0 finished episode 70 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:27 - RayLog - INFO: - Worker 1 finished episode 71 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:30 - RayLog - INFO: - update_step: 5000, online_eval_reward: 197.000 | |
| 2023-05-17 22:42:30 - RayLog - INFO: - Worker 0 finished episode 72 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:31 - RayLog - INFO: - Worker 1 finished episode 73 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:35 - RayLog - INFO: - Worker 0 finished episode 74 with reward 197.0 in 197 steps | |
| 2023-05-17 22:42:35 - RayLog - INFO: - update_step: 5500, online_eval_reward: 200.000 | |
| 2023-05-17 22:42:36 - RayLog - INFO: - Worker 1 finished episode 75 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:39 - RayLog - INFO: - Worker 0 finished episode 76 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:40 - RayLog - INFO: - Worker 1 finished episode 77 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:40 - RayLog - INFO: - update_step: 6000, online_eval_reward: 200.000 | |
| 2023-05-17 22:42:43 - RayLog - INFO: - Worker 0 finished episode 78 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:44 - RayLog - INFO: - Worker 1 finished episode 79 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:45 - RayLog - INFO: - update_step: 6500, online_eval_reward: 200.000 | |
| 2023-05-17 22:42:47 - RayLog - INFO: - Worker 0 finished episode 80 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:48 - RayLog - INFO: - Worker 1 finished episode 81 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:51 - RayLog - INFO: - update_step: 7000, online_eval_reward: 200.000 | |
| 2023-05-17 22:42:52 - RayLog - INFO: - Worker 0 finished episode 82 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:53 - RayLog - INFO: - Worker 1 finished episode 83 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:56 - RayLog - INFO: - Worker 0 finished episode 84 with reward 200.0 in 200 steps | |
| 2023-05-17 22:42:56 - RayLog - INFO: - update_step: 7500, online_eval_reward: 200.000 | |
| 2023-05-17 22:42:57 - RayLog - INFO: - Worker 1 finished episode 85 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:00 - RayLog - INFO: - Worker 0 finished episode 86 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:01 - RayLog - INFO: - Worker 1 finished episode 87 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:02 - RayLog - INFO: - update_step: 8000, online_eval_reward: 200.000 | |
| 2023-05-17 22:43:05 - RayLog - INFO: - Worker 0 finished episode 88 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:06 - RayLog - INFO: - Worker 1 finished episode 89 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:07 - RayLog - INFO: - update_step: 8500, online_eval_reward: 200.000 | |
| 2023-05-17 22:43:09 - RayLog - INFO: - Worker 0 finished episode 90 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:10 - RayLog - INFO: - Worker 1 finished episode 91 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:12 - RayLog - INFO: - update_step: 9000, online_eval_reward: 200.000 | |
| 2023-05-17 22:43:13 - RayLog - INFO: - Worker 0 finished episode 92 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:14 - RayLog - INFO: - Worker 1 finished episode 93 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:18 - RayLog - INFO: - Worker 0 finished episode 94 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:18 - RayLog - INFO: - update_step: 9500, online_eval_reward: 200.000 | |
| 2023-05-17 22:43:19 - RayLog - INFO: - Worker 1 finished episode 95 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:22 - RayLog - INFO: - Worker 0 finished episode 96 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:23 - RayLog - INFO: - Worker 1 finished episode 97 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:23 - RayLog - INFO: - update_step: 10000, online_eval_reward: 200.000 | |
| 2023-05-17 22:43:26 - RayLog - INFO: - Worker 0 finished episode 98 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:27 - RayLog - INFO: - Worker 1 finished episode 99 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:29 - RayLog - INFO: - update_step: 10500, online_eval_reward: 200.000 | |
| 2023-05-17 22:43:30 - RayLog - INFO: - Worker 0 finished episode 100 with reward 200.0 in 200 steps | |
| 2023-05-17 22:43:32 - SimpleLog - INFO: - Finish training! total time consumed: 122.69s | |