| 2023-07-05 21:53:18 - SimpleLog - INFO: - General Configs: | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================ | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Name Value Type | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - env_name gym <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - algo_name SoftQ <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - mode train <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - device cpu <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - seed 1 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - max_episode 200 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - max_step 200 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - collect_traj 0 <class 'bool'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - mp_backend None <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - n_workers 2 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - n_learners 1 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - share_buffer 1 <class 'bool'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - online_eval 1 <class 'bool'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - model_save_fre 500 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - load_checkpoint 0 <class 'bool'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - load_path Train_CartPole-v1_SoftQ_20230702-191520 <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - load_model_step best <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================ | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Algo Configs: | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================ | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Name Value Type | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - epsilon_start 0.95 <class 'float'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - epsilon_end 0.01 <class 'float'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - epsilon_decay 500 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - gamma 0.95 <class 'float'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - lr 0.0001 <class 'float'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - buffer_size 100000 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - batch_size 128 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - alpha 4 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - target_update 4 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - value_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================ | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Env Configs: | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================ | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Name Value Type | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - id CartPole-v1 <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - render_mode None <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - wrapper None <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'> | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================ | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Start training! | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 1 with reward 12.000 in 12 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 2 with reward 20.000 in 20 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward 11.000 in 11 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward 30.000 in 30 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 22.000 in 22 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 6 with reward 12.000 in 12 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 7 with reward 26.000 in 26 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 8 with reward 33.000 in 33 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 9 with reward 48.000 in 48 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 10 with reward 32.000 in 32 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 11 with reward 15.000 in 15 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 12 with reward 14.000 in 14 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 13 with reward 30.000 in 30 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 14 with reward 25.000 in 25 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 15 with reward 11.000 in 11 steps | |
| 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 16 with reward 16.000 in 16 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 17 with reward 25.000 in 25 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 18 with reward 27.000 in 27 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 19 with reward 14.000 in 14 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward 42.000 in 42 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 21 with reward 10.000 in 10 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 22 with reward 40.000 in 40 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 23 with reward 24.000 in 24 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 24 with reward 19.000 in 19 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 25 with reward 15.000 in 15 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward 27.000 in 27 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 27 with reward 12.000 in 12 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward 17.000 in 17 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward 34.000 in 34 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward 10.000 in 10 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward 25.000 in 25 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 32 with reward 11.000 in 11 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 33 with reward 13.000 in 13 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 34 with reward 44.000 in 44 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward 16.000 in 16 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 36 with reward 19.000 in 19 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward 12.000 in 12 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward 15.000 in 15 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 39 with reward 11.000 in 11 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward 16.000 in 16 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 41 with reward 17.000 in 17 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 42 with reward 10.000 in 10 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 43 with reward 16.000 in 16 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 44 with reward 28.000 in 28 steps | |
| 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 45 with reward 9.000 in 9 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward 19.000 in 19 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward 26.000 in 26 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 48 with reward 9.000 in 9 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 49 with reward 10.000 in 10 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 50 with reward 18.000 in 18 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 51 with reward 12.000 in 12 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 52 with reward 14.000 in 14 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 53 with reward 13.000 in 13 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 54 with reward 21.000 in 21 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward 11.000 in 11 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward 17.000 in 17 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward 11.000 in 11 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 9.000 | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 9.000, save the best model! | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 58 with reward 21.000 in 21 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward 16.000 in 16 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 60 with reward 42.000 in 42 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 61 with reward 9.000 in 9 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 62 with reward 14.000 in 14 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward 29.000 in 29 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 64 with reward 16.000 in 16 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 65 with reward 21.000 in 21 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 66 with reward 24.000 in 24 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 67 with reward 20.000 in 20 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 68 with reward 12.000 in 12 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 69 with reward 15.000 in 15 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 70 with reward 27.000 in 27 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 71 with reward 26.000 in 26 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 72 with reward 23.000 in 23 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 73 with reward 22.000 in 22 steps | |
| 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward 18.000 in 18 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 75 with reward 18.000 in 18 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 76 with reward 17.000 in 17 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 77 with reward 9.000 in 9 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 78 with reward 28.000 in 28 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 79 with reward 19.000 in 19 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 80 with reward 39.000 in 39 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 81 with reward 26.000 in 26 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 82 with reward 53.000 in 53 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward 28.000 in 28 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 84 with reward 12.000 in 12 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 85 with reward 52.000 in 52 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 86 with reward 20.000 in 20 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 87 with reward 66.000 in 66 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 88 with reward 22.000 in 22 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 89 with reward 15.000 in 15 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 90 with reward 15.000 in 15 steps | |
| 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 91 with reward 27.000 in 27 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 92 with reward 49.000 in 49 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 93 with reward 31.000 in 31 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 66.000 | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 66.000, save the best model! | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 0 finished episode 94 with reward 96.000 in 96 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 95 with reward 65.000 in 65 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 0 finished episode 96 with reward 46.000 in 46 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 97 with reward 33.000 in 33 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 0 finished episode 98 with reward 25.000 in 25 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 99 with reward 34.000 in 34 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 0 finished episode 100 with reward 54.000 in 54 steps | |
| 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 101 with reward 27.000 in 27 steps | |
| 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 0 finished episode 102 with reward 36.000 in 36 steps | |
| 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 103 with reward 36.000 in 36 steps | |
| 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 104 with reward 37.000 in 37 steps | |
| 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 105 with reward 37.000 in 37 steps | |
| 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 0 finished episode 106 with reward 107.000 in 107 steps | |
| 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 107 with reward 44.000 in 44 steps | |
| 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 108 with reward 99.000 in 99 steps | |
| 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 0 finished episode 109 with reward 118.000 in 118 steps | |
| 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 1 finished episode 110 with reward 68.000 in 68 steps | |
| 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 0 finished episode 111 with reward 75.000 in 75 steps | |
| 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 1 finished episode 112 with reward 17.000 in 17 steps | |
| 2023-07-05 21:53:24 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 93.000 | |
| 2023-07-05 21:53:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 93.000, save the best model! | |
| 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 0 finished episode 113 with reward 65.000 in 65 steps | |
| 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 0 finished episode 114 with reward 33.000 in 33 steps | |
| 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 0 finished episode 115 with reward 40.000 in 40 steps | |
| 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 0 finished episode 116 with reward 57.000 in 57 steps | |
| 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 1 finished episode 117 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 1 finished episode 118 with reward 75.000 in 75 steps | |
| 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 0 finished episode 119 with reward 91.000 in 91 steps | |
| 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 0 finished episode 120 with reward 47.000 in 47 steps | |
| 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 0 finished episode 121 with reward 76.000 in 76 steps | |
| 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 1 finished episode 122 with reward 127.000 in 127 steps | |
| 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 0 finished episode 123 with reward 100.000 in 100 steps | |
| 2023-07-05 21:53:26 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: 129.000 | |
| 2023-07-05 21:53:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 129.000, save the best model! | |
| 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 0 finished episode 124 with reward 26.000 in 26 steps | |
| 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 1 finished episode 125 with reward 146.000 in 146 steps | |
| 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 1 finished episode 126 with reward 39.000 in 39 steps | |
| 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 0 finished episode 127 with reward 84.000 in 84 steps | |
| 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 1 finished episode 128 with reward 80.000 in 80 steps | |
| 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 0 finished episode 129 with reward 116.000 in 116 steps | |
| 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 1 finished episode 130 with reward 124.000 in 124 steps | |
| 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward 75.000 in 75 steps | |
| 2023-07-05 21:53:28 - SimpleLog - INFO: - Interactor 1 finished episode 132 with reward 68.000 in 68 steps | |
| 2023-07-05 21:53:28 - SimpleLog - INFO: - Interactor 0 finished episode 133 with reward 89.000 in 89 steps | |
| 2023-07-05 21:53:28 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward 121.000 in 121 steps | |
| 2023-07-05 21:53:28 - SimpleLog - INFO: - Interactor 0 finished episode 135 with reward 129.000 in 129 steps | |
| 2023-07-05 21:53:28 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 168.000 | |
| 2023-07-05 21:53:28 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 168.000, save the best model! | |
| 2023-07-05 21:53:29 - SimpleLog - INFO: - Interactor 1 finished episode 136 with reward 90.000 in 90 steps | |
| 2023-07-05 21:53:29 - SimpleLog - INFO: - Interactor 0 finished episode 137 with reward 77.000 in 77 steps | |
| 2023-07-05 21:53:29 - SimpleLog - INFO: - Interactor 1 finished episode 138 with reward 188.000 in 188 steps | |
| 2023-07-05 21:53:29 - SimpleLog - INFO: - Interactor 0 finished episode 139 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:30 - SimpleLog - INFO: - Interactor 1 finished episode 140 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:30 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:30 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward 49.000 in 49 steps | |
| 2023-07-05 21:53:31 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:31 - SimpleLog - INFO: - Interactor 0 finished episode 143 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:31 - SimpleLog - INFO: - Interactor 1 finished episode 144 with reward 195.000 in 195 steps | |
| 2023-07-05 21:53:32 - SimpleLog - INFO: - Interactor 0 finished episode 145 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:32 - SimpleLog - INFO: - Interactor 1 finished episode 146 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:33 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:33 - SimpleLog - INFO: - Interactor 1 finished episode 147 with reward 167.000 in 167 steps | |
| 2023-07-05 21:53:33 - SimpleLog - INFO: - Interactor 0 finished episode 148 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:34 - SimpleLog - INFO: - Interactor 1 finished episode 149 with reward 133.000 in 133 steps | |
| 2023-07-05 21:53:34 - SimpleLog - INFO: - Interactor 0 finished episode 150 with reward 135.000 in 135 steps | |
| 2023-07-05 21:53:34 - SimpleLog - INFO: - Interactor 1 finished episode 151 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:35 - SimpleLog - INFO: - Interactor 0 finished episode 152 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:35 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:35 - SimpleLog - INFO: - Interactor 1 finished episode 153 with reward 129.000 in 129 steps | |
| 2023-07-05 21:53:35 - SimpleLog - INFO: - Interactor 0 finished episode 154 with reward 114.000 in 114 steps | |
| 2023-07-05 21:53:36 - SimpleLog - INFO: - Interactor 0 finished episode 155 with reward 143.000 in 143 steps | |
| 2023-07-05 21:53:36 - SimpleLog - INFO: - Interactor 1 finished episode 156 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:37 - SimpleLog - INFO: - Interactor 0 finished episode 157 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:37 - SimpleLog - INFO: - Interactor 1 finished episode 158 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:38 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:38 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:38 - SimpleLog - INFO: - Interactor 0 finished episode 159 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:38 - SimpleLog - INFO: - Interactor 1 finished episode 160 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:39 - SimpleLog - INFO: - Interactor 0 finished episode 161 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:39 - SimpleLog - INFO: - Interactor 1 finished episode 162 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:39 - SimpleLog - INFO: - Interactor 0 finished episode 163 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:40 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:40 - SimpleLog - INFO: - Interactor 1 finished episode 164 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:41 - SimpleLog - INFO: - Interactor 0 finished episode 165 with reward 181.000 in 181 steps | |
| 2023-07-05 21:53:41 - SimpleLog - INFO: - Interactor 1 finished episode 166 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:41 - SimpleLog - INFO: - Interactor 0 finished episode 167 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:42 - SimpleLog - INFO: - Interactor 1 finished episode 168 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:42 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:42 - SimpleLog - INFO: - Interactor 0 finished episode 169 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:43 - SimpleLog - INFO: - Interactor 1 finished episode 170 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:43 - SimpleLog - INFO: - Interactor 0 finished episode 171 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:43 - SimpleLog - INFO: - Interactor 1 finished episode 172 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:44 - SimpleLog - INFO: - Interactor 0 finished episode 173 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:44 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:44 - SimpleLog - INFO: - Interactor 1 finished episode 174 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:45 - SimpleLog - INFO: - Interactor 0 finished episode 175 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:45 - SimpleLog - INFO: - Interactor 1 finished episode 176 with reward 167.000 in 167 steps | |
| 2023-07-05 21:53:46 - SimpleLog - INFO: - Interactor 0 finished episode 177 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:46 - SimpleLog - INFO: - Interactor 1 finished episode 178 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:47 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:47 - SimpleLog - INFO: - Interactor 0 finished episode 179 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:47 - SimpleLog - INFO: - Interactor 1 finished episode 180 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:48 - SimpleLog - INFO: - Interactor 0 finished episode 181 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:48 - SimpleLog - INFO: - Interactor 1 finished episode 182 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:48 - SimpleLog - INFO: - Interactor 0 finished episode 183 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:49 - SimpleLog - INFO: - Interactor 1 finished episode 184 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:49 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:50 - SimpleLog - INFO: - Interactor 0 finished episode 185 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:50 - SimpleLog - INFO: - Interactor 1 finished episode 186 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:51 - SimpleLog - INFO: - Interactor 0 finished episode 187 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:51 - SimpleLog - INFO: - Interactor 1 finished episode 188 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:51 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:52 - SimpleLog - INFO: - Interactor 0 finished episode 189 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:52 - SimpleLog - INFO: - Interactor 1 finished episode 190 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:52 - SimpleLog - INFO: - Interactor 0 finished episode 191 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:53 - SimpleLog - INFO: - Interactor 1 finished episode 192 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:53 - SimpleLog - INFO: - Interactor 0 finished episode 193 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:53 - SimpleLog - INFO: - Interactor 1 finished episode 194 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:54 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:54 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:54 - SimpleLog - INFO: - Interactor 0 finished episode 195 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:55 - SimpleLog - INFO: - Interactor 1 finished episode 196 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:55 - SimpleLog - INFO: - Interactor 0 finished episode 197 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:55 - SimpleLog - INFO: - Interactor 1 finished episode 198 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:56 - SimpleLog - INFO: - update_step: 8500, online_eval_reward: 200.000 | |
| 2023-07-05 21:53:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! | |
| 2023-07-05 21:53:57 - SimpleLog - INFO: - Interactor 0 finished episode 199 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:57 - SimpleLog - INFO: - Interactor 1 finished episode 200 with reward 200.000 in 200 steps | |
| 2023-07-05 21:53:57 - SimpleLog - INFO: - Finish training! Time cost: 38.512 s | |