diff --git "a/ClassControl/CartPole-v1/Train_CartPole-v1_A2C_20230623-223515/logs/log.txt" "b/ClassControl/CartPole-v1/Train_CartPole-v1_A2C_20230623-223515/logs/log.txt" new file mode 100644--- /dev/null +++ "b/ClassControl/CartPole-v1/Train_CartPole-v1_A2C_20230623-223515/logs/log.txt" @@ -0,0 +1,1163 @@ +2023-06-23 22:35:15 - SimpleLog - INFO: - General Configs: +2023-06-23 22:35:15 - SimpleLog - INFO: - ================================================================================ +2023-06-23 22:35:15 - SimpleLog - INFO: - Name Value Type +2023-06-23 22:35:15 - SimpleLog - INFO: - env_name gym +2023-06-23 22:35:15 - SimpleLog - INFO: - algo_name A2C +2023-06-23 22:35:15 - SimpleLog - INFO: - mode train +2023-06-23 22:35:15 - SimpleLog - INFO: - device cpu +2023-06-23 22:35:15 - SimpleLog - INFO: - seed 1 +2023-06-23 22:35:15 - SimpleLog - INFO: - max_episode 1000 +2023-06-23 22:35:15 - SimpleLog - INFO: - max_step 200 +2023-06-23 22:35:15 - SimpleLog - INFO: - collect_traj 0 +2023-06-23 22:35:15 - SimpleLog - INFO: - mp_backend single +2023-06-23 22:35:15 - SimpleLog - INFO: - n_workers 2 +2023-06-23 22:35:15 - SimpleLog - INFO: - n_learners 1 +2023-06-23 22:35:15 - SimpleLog - INFO: - share_buffer 1 +2023-06-23 22:35:15 - SimpleLog - INFO: - online_eval 1 +2023-06-23 22:35:15 - SimpleLog - INFO: - online_eval_episode 10 +2023-06-23 22:35:15 - SimpleLog - INFO: - model_save_fre 10 +2023-06-23 22:35:15 - SimpleLog - INFO: - load_checkpoint 0 +2023-06-23 22:35:15 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_DQN_20230515-211721 +2023-06-23 22:35:15 - SimpleLog - INFO: - load_model_step best +2023-06-23 22:35:15 - SimpleLog - INFO: - interact_summary_fre 1 +2023-06-23 22:35:15 - SimpleLog - INFO: - model_summary_fre 1 +2023-06-23 22:35:15 - SimpleLog - INFO: - ================================================================================ +2023-06-23 22:35:15 - SimpleLog - INFO: - Algo Configs: +2023-06-23 22:35:15 - SimpleLog - INFO: - ================================================================================ +2023-06-23 22:35:15 - SimpleLog - INFO: - Name Value Type +2023-06-23 22:35:15 - SimpleLog - INFO: - independ_actor 1 +2023-06-23 22:35:15 - SimpleLog - INFO: - share_optimizer 0 +2023-06-23 22:35:15 - SimpleLog - INFO: - action_type discrete +2023-06-23 22:35:15 - SimpleLog - INFO: - gamma 0.98 +2023-06-23 22:35:15 - SimpleLog - INFO: - k_epochs 4 +2023-06-23 22:35:15 - SimpleLog - INFO: - lr 0.0001 +2023-06-23 22:35:15 - SimpleLog - INFO: - actor_lr 0.001 +2023-06-23 22:35:15 - SimpleLog - INFO: - critic_lr 0.01 +2023-06-23 22:35:15 - SimpleLog - INFO: - critic_loss_coef 0.5 +2023-06-23 22:35:15 - SimpleLog - INFO: - entropy_coef 0.01 +2023-06-23 22:35:15 - SimpleLog - INFO: - buffer_type ONPOLICY_QUE +2023-06-23 22:35:15 - SimpleLog - INFO: - batch_size 256 +2023-06-23 22:35:15 - SimpleLog - INFO: - sgd_batch_size 128 +2023-06-23 22:35:15 - SimpleLog - INFO: - actor_hidden_dim 256 +2023-06-23 22:35:15 - SimpleLog - INFO: - critic_hidden_dim 256 +2023-06-23 22:35:15 - SimpleLog - INFO: - min_policy 0 +2023-06-23 22:35:15 - SimpleLog - INFO: - n_steps_per_learn 1 +2023-06-23 22:35:15 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [128], 'activation': 'relu'}] +2023-06-23 22:35:15 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [128], 'activation': 'relu'}] +2023-06-23 22:35:15 - SimpleLog - INFO: - ================================================================================ +2023-06-23 22:35:15 - SimpleLog - INFO: - Env Configs: +2023-06-23 22:35:15 - SimpleLog - INFO: - ================================================================================ +2023-06-23 22:35:15 - SimpleLog - INFO: - Name Value Type +2023-06-23 22:35:15 - SimpleLog - INFO: - id CartPole-v1 +2023-06-23 22:35:15 - SimpleLog - INFO: - render_mode None +2023-06-23 22:35:15 - SimpleLog - INFO: - wrapper None +2023-06-23 22:35:15 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-06-23 22:35:15 - SimpleLog - INFO: - ================================================================================ +2023-06-23 22:35:15 - SimpleLog - INFO: - Start training! +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward 17.000 in 17 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 2 with reward 15.000 in 15 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward 23.000 in 23 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 4 with reward 18.000 in 18 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 29.000 in 29 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 6 with reward 55.000 in 55 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward 28.000 in 28 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 8 with reward 15.000 in 15 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 9 with reward 19.000 in 19 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 10 with reward 13.000 in 13 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 11 with reward 16.000 in 16 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward 46.000 in 46 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 13 with reward 49.000 in 49 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward 22.000 in 22 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 15 with reward 28.000 in 28 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 16 with reward 19.000 in 19 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 17 with reward 24.000 in 24 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 18 with reward 29.000 in 29 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 19 with reward 83.000 in 83 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 20 with reward 31.000 in 31 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 21 with reward 24.000 in 24 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 22 with reward 48.000 in 48 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 23 with reward 21.000 in 21 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 24 with reward 63.000 in 63 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 25 with reward 48.000 in 48 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward 39.000 in 39 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 27 with reward 26.000 in 26 steps +2023-06-23 22:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward 28.000 in 28 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 29 with reward 44.000 in 44 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 30 with reward 15.000 in 15 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward 31.000 in 31 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 32 with reward 24.000 in 24 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 33 with reward 16.000 in 16 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 34 with reward 26.000 in 26 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward 95.000 in 95 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 36 with reward 100.000 in 100 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 37 with reward 31.000 in 31 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward 86.000 in 86 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 39 with reward 50.000 in 50 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward 49.000 in 49 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 41 with reward 27.000 in 27 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 42 with reward 89.000 in 89 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 43 with reward 18.000 in 18 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 44 with reward 39.000 in 39 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 45 with reward 34.000 in 34 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 46 with reward 51.000 in 51 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward 28.000 in 28 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 48 with reward 54.000 in 54 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 49 with reward 63.000 in 63 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 50 with reward 43.000 in 43 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 51 with reward 52.000 in 52 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 52 with reward 21.000 in 21 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 53 with reward 21.000 in 21 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 54 with reward 60.000 in 60 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward 87.000 in 87 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 56 with reward 22.000 in 22 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward 40.000 in 40 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 58 with reward 17.000 in 17 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward 36.000 in 36 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 60 with reward 28.000 in 28 steps +2023-06-23 22:35:16 - SimpleLog - INFO: - Interactor 1 finished episode 61 with reward 38.000 in 38 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 62 with reward 87.000 in 87 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward 11.000 in 11 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 64 with reward 61.000 in 61 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 65 with reward 25.000 in 25 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - update_step: 10, online_eval_reward: 71.000 +2023-06-23 22:35:17 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 71.000, save the best model! +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 66 with reward 70.000 in 70 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 67 with reward 53.000 in 53 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 68 with reward 18.000 in 18 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 69 with reward 79.000 in 79 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 70 with reward 63.000 in 63 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 71 with reward 63.000 in 63 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 72 with reward 43.000 in 43 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 73 with reward 75.000 in 75 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward 35.000 in 35 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 75 with reward 79.000 in 79 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 76 with reward 34.000 in 34 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 77 with reward 51.000 in 51 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 78 with reward 32.000 in 32 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 79 with reward 42.000 in 42 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 80 with reward 109.000 in 109 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 81 with reward 34.000 in 34 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 1 finished episode 82 with reward 132.000 in 132 steps +2023-06-23 22:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward 92.000 in 92 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 84 with reward 72.000 in 72 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 85 with reward 114.000 in 114 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 86 with reward 45.000 in 45 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 87 with reward 112.000 in 112 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 88 with reward 132.000 in 132 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 89 with reward 24.000 in 24 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 90 with reward 93.000 in 93 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 91 with reward 91.000 in 91 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 92 with reward 78.000 in 78 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 93 with reward 53.000 in 53 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 94 with reward 107.000 in 107 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 95 with reward 72.000 in 72 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 96 with reward 95.000 in 95 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 97 with reward 75.000 in 75 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 0 finished episode 98 with reward 77.000 in 77 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 99 with reward 63.000 in 63 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 100 with reward 54.000 in 54 steps +2023-06-23 22:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 101 with reward 142.000 in 142 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - update_step: 20, online_eval_reward: 200.000 +2023-06-23 22:35:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 0 finished episode 102 with reward 81.000 in 81 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 0 finished episode 103 with reward 40.000 in 40 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 0 finished episode 104 with reward 106.000 in 106 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 1 finished episode 105 with reward 65.000 in 65 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 1 finished episode 106 with reward 83.000 in 83 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 1 finished episode 107 with reward 88.000 in 88 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 0 finished episode 108 with reward 36.000 in 36 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 0 finished episode 109 with reward 113.000 in 113 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 0 finished episode 110 with reward 101.000 in 101 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 1 finished episode 111 with reward 109.000 in 109 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 1 finished episode 112 with reward 53.000 in 53 steps +2023-06-23 22:35:19 - SimpleLog - INFO: - Interactor 1 finished episode 113 with reward 42.000 in 42 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 0 finished episode 114 with reward 93.000 in 93 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 0 finished episode 115 with reward 91.000 in 91 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 116 with reward 95.000 in 95 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 117 with reward 49.000 in 49 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 118 with reward 135.000 in 135 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 0 finished episode 119 with reward 200.000 in 200 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 120 with reward 104.000 in 104 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 121 with reward 200.000 in 200 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 0 finished episode 122 with reward 180.000 in 180 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 0 finished episode 123 with reward 146.000 in 146 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 0 finished episode 124 with reward 65.000 in 65 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 125 with reward 32.000 in 32 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 126 with reward 40.000 in 40 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 127 with reward 113.000 in 113 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 128 with reward 35.000 in 35 steps +2023-06-23 22:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 129 with reward 21.000 in 21 steps +2023-06-23 22:35:21 - SimpleLog - INFO: - update_step: 30, online_eval_reward: 120.000 +2023-06-23 22:35:21 - SimpleLog - INFO: - Interactor 0 finished episode 130 with reward 91.000 in 91 steps +2023-06-23 22:35:21 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward 105.000 in 105 steps +2023-06-23 22:35:21 - SimpleLog - INFO: - Interactor 0 finished episode 132 with reward 90.000 in 90 steps +2023-06-23 22:35:21 - SimpleLog - INFO: - Interactor 1 finished episode 133 with reward 115.000 in 115 steps +2023-06-23 22:35:21 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward 90.000 in 90 steps +2023-06-23 22:35:21 - SimpleLog - INFO: - Interactor 1 finished episode 135 with reward 46.000 in 46 steps +2023-06-23 22:35:21 - SimpleLog - INFO: - Interactor 0 finished episode 136 with reward 169.000 in 169 steps +2023-06-23 22:35:21 - SimpleLog - INFO: - Interactor 1 finished episode 137 with reward 174.000 in 174 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 0 finished episode 138 with reward 200.000 in 200 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 1 finished episode 139 with reward 196.000 in 196 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 0 finished episode 140 with reward 200.000 in 200 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward 200.000 in 200 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward 200.000 in 200 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 1 finished episode 143 with reward 200.000 in 200 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 0 finished episode 144 with reward 199.000 in 199 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 1 finished episode 145 with reward 200.000 in 200 steps +2023-06-23 22:35:22 - SimpleLog - INFO: - Interactor 1 finished episode 146 with reward 72.000 in 72 steps +2023-06-23 22:35:23 - SimpleLog - INFO: - update_step: 40, online_eval_reward: 200.000 +2023-06-23 22:35:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:23 - SimpleLog - INFO: - Interactor 0 finished episode 147 with reward 200.000 in 200 steps +2023-06-23 22:35:23 - SimpleLog - INFO: - Interactor 1 finished episode 148 with reward 136.000 in 136 steps +2023-06-23 22:35:23 - SimpleLog - INFO: - Interactor 0 finished episode 149 with reward 200.000 in 200 steps +2023-06-23 22:35:23 - SimpleLog - INFO: - Interactor 1 finished episode 150 with reward 200.000 in 200 steps +2023-06-23 22:35:23 - SimpleLog - INFO: - Interactor 1 finished episode 151 with reward 185.000 in 185 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 0 finished episode 152 with reward 200.000 in 200 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 0 finished episode 153 with reward 200.000 in 200 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 1 finished episode 154 with reward 200.000 in 200 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 0 finished episode 155 with reward 200.000 in 200 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 1 finished episode 156 with reward 200.000 in 200 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 0 finished episode 157 with reward 145.000 in 145 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 0 finished episode 158 with reward 177.000 in 177 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 1 finished episode 159 with reward 163.000 in 163 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 1 finished episode 160 with reward 53.000 in 53 steps +2023-06-23 22:35:24 - SimpleLog - INFO: - Interactor 1 finished episode 161 with reward 142.000 in 142 steps +2023-06-23 22:35:25 - SimpleLog - INFO: - update_step: 50, online_eval_reward: 171.000 +2023-06-23 22:35:25 - SimpleLog - INFO: - Interactor 0 finished episode 162 with reward 181.000 in 181 steps +2023-06-23 22:35:25 - SimpleLog - INFO: - Interactor 1 finished episode 163 with reward 126.000 in 126 steps +2023-06-23 22:35:25 - SimpleLog - INFO: - Interactor 1 finished episode 164 with reward 102.000 in 102 steps +2023-06-23 22:35:25 - SimpleLog - INFO: - Interactor 0 finished episode 165 with reward 146.000 in 146 steps +2023-06-23 22:35:25 - SimpleLog - INFO: - Interactor 0 finished episode 166 with reward 200.000 in 200 steps +2023-06-23 22:35:25 - SimpleLog - INFO: - Interactor 1 finished episode 167 with reward 200.000 in 200 steps +2023-06-23 22:35:26 - SimpleLog - INFO: - Interactor 0 finished episode 168 with reward 169.000 in 169 steps +2023-06-23 22:35:26 - SimpleLog - INFO: - Interactor 1 finished episode 169 with reward 200.000 in 200 steps +2023-06-23 22:35:26 - SimpleLog - INFO: - Interactor 1 finished episode 170 with reward 130.000 in 130 steps +2023-06-23 22:35:26 - SimpleLog - INFO: - Interactor 0 finished episode 171 with reward 183.000 in 183 steps +2023-06-23 22:35:26 - SimpleLog - INFO: - Interactor 0 finished episode 172 with reward 105.000 in 105 steps +2023-06-23 22:35:26 - SimpleLog - INFO: - Interactor 1 finished episode 173 with reward 200.000 in 200 steps +2023-06-23 22:35:26 - SimpleLog - INFO: - Interactor 0 finished episode 174 with reward 200.000 in 200 steps +2023-06-23 22:35:26 - SimpleLog - INFO: - Interactor 1 finished episode 175 with reward 200.000 in 200 steps +2023-06-23 22:35:27 - SimpleLog - INFO: - update_step: 60, online_eval_reward: 151.000 +2023-06-23 22:35:27 - SimpleLog - INFO: - Interactor 0 finished episode 176 with reward 200.000 in 200 steps +2023-06-23 22:35:27 - SimpleLog - INFO: - Interactor 0 finished episode 177 with reward 119.000 in 119 steps +2023-06-23 22:35:27 - SimpleLog - INFO: - Interactor 1 finished episode 178 with reward 200.000 in 200 steps +2023-06-23 22:35:27 - SimpleLog - INFO: - Interactor 1 finished episode 179 with reward 72.000 in 72 steps +2023-06-23 22:35:27 - SimpleLog - INFO: - Interactor 0 finished episode 180 with reward 125.000 in 125 steps +2023-06-23 22:35:27 - SimpleLog - INFO: - Interactor 0 finished episode 181 with reward 145.000 in 145 steps +2023-06-23 22:35:27 - SimpleLog - INFO: - Interactor 1 finished episode 182 with reward 141.000 in 141 steps +2023-06-23 22:35:27 - SimpleLog - INFO: - Interactor 1 finished episode 183 with reward 153.000 in 153 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 0 finished episode 184 with reward 112.000 in 112 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 1 finished episode 185 with reward 132.000 in 132 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 1 finished episode 186 with reward 200.000 in 200 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 0 finished episode 187 with reward 200.000 in 200 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 0 finished episode 188 with reward 200.000 in 200 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 1 finished episode 189 with reward 123.000 in 123 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 0 finished episode 190 with reward 200.000 in 200 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 1 finished episode 191 with reward 200.000 in 200 steps +2023-06-23 22:35:28 - SimpleLog - INFO: - Interactor 1 finished episode 192 with reward 200.000 in 200 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - update_step: 70, online_eval_reward: 137.000 +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 0 finished episode 193 with reward 179.000 in 179 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 0 finished episode 194 with reward 31.000 in 31 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 0 finished episode 195 with reward 103.000 in 103 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 1 finished episode 196 with reward 108.000 in 108 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 1 finished episode 197 with reward 90.000 in 90 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 0 finished episode 198 with reward 111.000 in 111 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 0 finished episode 199 with reward 120.000 in 120 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 1 finished episode 200 with reward 116.000 in 116 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 1 finished episode 201 with reward 133.000 in 133 steps +2023-06-23 22:35:29 - SimpleLog - INFO: - Interactor 1 finished episode 202 with reward 48.000 in 48 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 203 with reward 111.000 in 111 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 204 with reward 111.000 in 111 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 1 finished episode 205 with reward 141.000 in 141 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 206 with reward 151.000 in 151 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 207 with reward 39.000 in 39 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 208 with reward 120.000 in 120 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 1 finished episode 209 with reward 142.000 in 142 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 1 finished episode 210 with reward 177.000 in 177 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 211 with reward 120.000 in 120 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 212 with reward 60.000 in 60 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 1 finished episode 213 with reward 137.000 in 137 steps +2023-06-23 22:35:30 - SimpleLog - INFO: - Interactor 1 finished episode 214 with reward 94.000 in 94 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - update_step: 80, online_eval_reward: 117.000 +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 0 finished episode 215 with reward 133.000 in 133 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 0 finished episode 216 with reward 97.000 in 97 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 0 finished episode 217 with reward 98.000 in 98 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 1 finished episode 218 with reward 133.000 in 133 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 1 finished episode 219 with reward 139.000 in 139 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 0 finished episode 220 with reward 113.000 in 113 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 0 finished episode 221 with reward 134.000 in 134 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 1 finished episode 222 with reward 126.000 in 126 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 1 finished episode 223 with reward 200.000 in 200 steps +2023-06-23 22:35:31 - SimpleLog - INFO: - Interactor 0 finished episode 224 with reward 135.000 in 135 steps +2023-06-23 22:35:32 - SimpleLog - INFO: - Interactor 0 finished episode 225 with reward 140.000 in 140 steps +2023-06-23 22:35:32 - SimpleLog - INFO: - Interactor 1 finished episode 226 with reward 200.000 in 200 steps +2023-06-23 22:35:32 - SimpleLog - INFO: - Interactor 0 finished episode 227 with reward 158.000 in 158 steps +2023-06-23 22:35:32 - SimpleLog - INFO: - Interactor 1 finished episode 228 with reward 159.000 in 159 steps +2023-06-23 22:35:32 - SimpleLog - INFO: - Interactor 0 finished episode 229 with reward 200.000 in 200 steps +2023-06-23 22:35:32 - SimpleLog - INFO: - Interactor 1 finished episode 230 with reward 200.000 in 200 steps +2023-06-23 22:35:32 - SimpleLog - INFO: - Interactor 1 finished episode 231 with reward 200.000 in 200 steps +2023-06-23 22:35:33 - SimpleLog - INFO: - update_step: 90, online_eval_reward: 200.000 +2023-06-23 22:35:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:33 - SimpleLog - INFO: - Interactor 0 finished episode 232 with reward 195.000 in 195 steps +2023-06-23 22:35:33 - SimpleLog - INFO: - Interactor 0 finished episode 233 with reward 200.000 in 200 steps +2023-06-23 22:35:33 - SimpleLog - INFO: - Interactor 1 finished episode 234 with reward 115.000 in 115 steps +2023-06-23 22:35:33 - SimpleLog - INFO: - Interactor 0 finished episode 235 with reward 200.000 in 200 steps +2023-06-23 22:35:33 - SimpleLog - INFO: - Interactor 1 finished episode 236 with reward 200.000 in 200 steps +2023-06-23 22:35:33 - SimpleLog - INFO: - Interactor 1 finished episode 237 with reward 185.000 in 185 steps +2023-06-23 22:35:34 - SimpleLog - INFO: - Interactor 0 finished episode 238 with reward 200.000 in 200 steps +2023-06-23 22:35:34 - SimpleLog - INFO: - Interactor 0 finished episode 239 with reward 148.000 in 148 steps +2023-06-23 22:35:34 - SimpleLog - INFO: - Interactor 1 finished episode 240 with reward 180.000 in 180 steps +2023-06-23 22:35:34 - SimpleLog - INFO: - Interactor 0 finished episode 241 with reward 195.000 in 195 steps +2023-06-23 22:35:34 - SimpleLog - INFO: - Interactor 1 finished episode 242 with reward 137.000 in 137 steps +2023-06-23 22:35:34 - SimpleLog - INFO: - Interactor 1 finished episode 243 with reward 162.000 in 162 steps +2023-06-23 22:35:34 - SimpleLog - INFO: - Interactor 0 finished episode 244 with reward 200.000 in 200 steps +2023-06-23 22:35:34 - SimpleLog - INFO: - Interactor 1 finished episode 245 with reward 188.000 in 188 steps +2023-06-23 22:35:35 - SimpleLog - INFO: - update_step: 100, online_eval_reward: 200.000 +2023-06-23 22:35:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:35 - SimpleLog - INFO: - Interactor 0 finished episode 246 with reward 178.000 in 178 steps +2023-06-23 22:35:35 - SimpleLog - INFO: - Interactor 0 finished episode 247 with reward 105.000 in 105 steps +2023-06-23 22:35:35 - SimpleLog - INFO: - Interactor 1 finished episode 248 with reward 200.000 in 200 steps +2023-06-23 22:35:35 - SimpleLog - INFO: - Interactor 0 finished episode 249 with reward 200.000 in 200 steps +2023-06-23 22:35:35 - SimpleLog - INFO: - Interactor 1 finished episode 250 with reward 200.000 in 200 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 1 finished episode 251 with reward 200.000 in 200 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 0 finished episode 252 with reward 200.000 in 200 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 0 finished episode 253 with reward 200.000 in 200 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 1 finished episode 254 with reward 200.000 in 200 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 0 finished episode 255 with reward 200.000 in 200 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 1 finished episode 256 with reward 200.000 in 200 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 0 finished episode 257 with reward 150.000 in 150 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 0 finished episode 258 with reward 122.000 in 122 steps +2023-06-23 22:35:36 - SimpleLog - INFO: - Interactor 1 finished episode 259 with reward 200.000 in 200 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 1 finished episode 260 with reward 153.000 in 153 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - update_step: 110, online_eval_reward: 114.000 +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 0 finished episode 261 with reward 90.000 in 90 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 0 finished episode 262 with reward 120.000 in 120 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 1 finished episode 263 with reward 166.000 in 166 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 1 finished episode 264 with reward 118.000 in 118 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 0 finished episode 265 with reward 118.000 in 118 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 0 finished episode 266 with reward 115.000 in 115 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 0 finished episode 267 with reward 73.000 in 73 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 1 finished episode 268 with reward 150.000 in 150 steps +2023-06-23 22:35:37 - SimpleLog - INFO: - Interactor 1 finished episode 269 with reward 108.000 in 108 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 0 finished episode 270 with reward 67.000 in 67 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 0 finished episode 271 with reward 124.000 in 124 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 0 finished episode 272 with reward 107.000 in 107 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 1 finished episode 273 with reward 175.000 in 175 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 0 finished episode 274 with reward 141.000 in 141 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 1 finished episode 275 with reward 190.000 in 190 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 1 finished episode 276 with reward 147.000 in 147 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 0 finished episode 277 with reward 135.000 in 135 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 0 finished episode 278 with reward 200.000 in 200 steps +2023-06-23 22:35:38 - SimpleLog - INFO: - Interactor 1 finished episode 279 with reward 139.000 in 139 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - update_step: 120, online_eval_reward: 117.000 +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 280 with reward 133.000 in 133 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 281 with reward 107.000 in 107 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 1 finished episode 282 with reward 179.000 in 179 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 1 finished episode 283 with reward 127.000 in 127 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 284 with reward 110.000 in 110 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 285 with reward 50.000 in 50 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 286 with reward 34.000 in 34 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 287 with reward 45.000 in 45 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 288 with reward 47.000 in 47 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 1 finished episode 289 with reward 126.000 in 126 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 1 finished episode 290 with reward 43.000 in 43 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 1 finished episode 291 with reward 73.000 in 73 steps +2023-06-23 22:35:39 - SimpleLog - INFO: - Interactor 1 finished episode 292 with reward 53.000 in 53 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 0 finished episode 293 with reward 115.000 in 115 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 0 finished episode 294 with reward 119.000 in 119 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 1 finished episode 295 with reward 75.000 in 75 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 1 finished episode 296 with reward 122.000 in 122 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 0 finished episode 297 with reward 121.000 in 121 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 0 finished episode 298 with reward 131.000 in 131 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 1 finished episode 299 with reward 145.000 in 145 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 1 finished episode 300 with reward 174.000 in 174 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 0 finished episode 301 with reward 180.000 in 180 steps +2023-06-23 22:35:40 - SimpleLog - INFO: - Interactor 1 finished episode 302 with reward 171.000 in 171 steps +2023-06-23 22:35:41 - SimpleLog - INFO: - update_step: 130, online_eval_reward: 183.000 +2023-06-23 22:35:41 - SimpleLog - INFO: - Interactor 0 finished episode 303 with reward 162.000 in 162 steps +2023-06-23 22:35:41 - SimpleLog - INFO: - Interactor 0 finished episode 304 with reward 161.000 in 161 steps +2023-06-23 22:35:41 - SimpleLog - INFO: - Interactor 1 finished episode 305 with reward 187.000 in 187 steps +2023-06-23 22:35:41 - SimpleLog - INFO: - Interactor 1 finished episode 306 with reward 190.000 in 190 steps +2023-06-23 22:35:41 - SimpleLog - INFO: - Interactor 0 finished episode 307 with reward 192.000 in 192 steps +2023-06-23 22:35:41 - SimpleLog - INFO: - Interactor 1 finished episode 308 with reward 200.000 in 200 steps +2023-06-23 22:35:42 - SimpleLog - INFO: - Interactor 0 finished episode 309 with reward 198.000 in 198 steps +2023-06-23 22:35:42 - SimpleLog - INFO: - Interactor 0 finished episode 310 with reward 165.000 in 165 steps +2023-06-23 22:35:42 - SimpleLog - INFO: - Interactor 1 finished episode 311 with reward 200.000 in 200 steps +2023-06-23 22:35:42 - SimpleLog - INFO: - Interactor 0 finished episode 312 with reward 160.000 in 160 steps +2023-06-23 22:35:42 - SimpleLog - INFO: - Interactor 1 finished episode 313 with reward 200.000 in 200 steps +2023-06-23 22:35:42 - SimpleLog - INFO: - Interactor 0 finished episode 314 with reward 200.000 in 200 steps +2023-06-23 22:35:42 - SimpleLog - INFO: - Interactor 1 finished episode 315 with reward 200.000 in 200 steps +2023-06-23 22:35:43 - SimpleLog - INFO: - Interactor 1 finished episode 316 with reward 200.000 in 200 steps +2023-06-23 22:35:43 - SimpleLog - INFO: - update_step: 140, online_eval_reward: 200.000 +2023-06-23 22:35:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:43 - SimpleLog - INFO: - Interactor 0 finished episode 317 with reward 200.000 in 200 steps +2023-06-23 22:35:43 - SimpleLog - INFO: - Interactor 0 finished episode 318 with reward 200.000 in 200 steps +2023-06-23 22:35:43 - SimpleLog - INFO: - Interactor 1 finished episode 319 with reward 200.000 in 200 steps +2023-06-23 22:35:43 - SimpleLog - INFO: - Interactor 0 finished episode 320 with reward 200.000 in 200 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 1 finished episode 321 with reward 200.000 in 200 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 0 finished episode 322 with reward 200.000 in 200 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 1 finished episode 323 with reward 200.000 in 200 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 1 finished episode 324 with reward 200.000 in 200 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 0 finished episode 325 with reward 200.000 in 200 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 1 finished episode 326 with reward 171.000 in 171 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 0 finished episode 327 with reward 200.000 in 200 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 0 finished episode 328 with reward 200.000 in 200 steps +2023-06-23 22:35:44 - SimpleLog - INFO: - Interactor 1 finished episode 329 with reward 164.000 in 164 steps +2023-06-23 22:35:45 - SimpleLog - INFO: - update_step: 150, online_eval_reward: 200.000 +2023-06-23 22:35:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:45 - SimpleLog - INFO: - Interactor 0 finished episode 330 with reward 200.000 in 200 steps +2023-06-23 22:35:45 - SimpleLog - INFO: - Interactor 1 finished episode 331 with reward 200.000 in 200 steps +2023-06-23 22:35:45 - SimpleLog - INFO: - Interactor 1 finished episode 332 with reward 197.000 in 197 steps +2023-06-23 22:35:45 - SimpleLog - INFO: - Interactor 0 finished episode 333 with reward 200.000 in 200 steps +2023-06-23 22:35:46 - SimpleLog - INFO: - Interactor 0 finished episode 334 with reward 160.000 in 160 steps +2023-06-23 22:35:46 - SimpleLog - INFO: - Interactor 1 finished episode 335 with reward 190.000 in 190 steps +2023-06-23 22:35:46 - SimpleLog - INFO: - Interactor 0 finished episode 336 with reward 200.000 in 200 steps +2023-06-23 22:35:46 - SimpleLog - INFO: - Interactor 1 finished episode 337 with reward 171.000 in 171 steps +2023-06-23 22:35:46 - SimpleLog - INFO: - Interactor 1 finished episode 338 with reward 152.000 in 152 steps +2023-06-23 22:35:46 - SimpleLog - INFO: - Interactor 0 finished episode 339 with reward 158.000 in 158 steps +2023-06-23 22:35:46 - SimpleLog - INFO: - Interactor 1 finished episode 340 with reward 170.000 in 170 steps +2023-06-23 22:35:46 - SimpleLog - INFO: - Interactor 0 finished episode 341 with reward 200.000 in 200 steps +2023-06-23 22:35:47 - SimpleLog - INFO: - Interactor 0 finished episode 342 with reward 178.000 in 178 steps +2023-06-23 22:35:47 - SimpleLog - INFO: - Interactor 1 finished episode 343 with reward 200.000 in 200 steps +2023-06-23 22:35:47 - SimpleLog - INFO: - Interactor 1 finished episode 344 with reward 160.000 in 160 steps +2023-06-23 22:35:47 - SimpleLog - INFO: - update_step: 160, online_eval_reward: 200.000 +2023-06-23 22:35:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:47 - SimpleLog - INFO: - Interactor 0 finished episode 345 with reward 200.000 in 200 steps +2023-06-23 22:35:47 - SimpleLog - INFO: - Interactor 1 finished episode 346 with reward 144.000 in 144 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 0 finished episode 347 with reward 182.000 in 182 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 1 finished episode 348 with reward 200.000 in 200 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 1 finished episode 349 with reward 163.000 in 163 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 0 finished episode 350 with reward 181.000 in 181 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 0 finished episode 351 with reward 187.000 in 187 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 1 finished episode 352 with reward 200.000 in 200 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 0 finished episode 353 with reward 200.000 in 200 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 1 finished episode 354 with reward 141.000 in 141 steps +2023-06-23 22:35:48 - SimpleLog - INFO: - Interactor 1 finished episode 355 with reward 200.000 in 200 steps +2023-06-23 22:35:49 - SimpleLog - INFO: - Interactor 0 finished episode 356 with reward 200.000 in 200 steps +2023-06-23 22:35:49 - SimpleLog - INFO: - Interactor 1 finished episode 357 with reward 200.000 in 200 steps +2023-06-23 22:35:49 - SimpleLog - INFO: - update_step: 170, online_eval_reward: 200.000 +2023-06-23 22:35:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:49 - SimpleLog - INFO: - Interactor 0 finished episode 358 with reward 200.000 in 200 steps +2023-06-23 22:35:49 - SimpleLog - INFO: - Interactor 0 finished episode 359 with reward 200.000 in 200 steps +2023-06-23 22:35:49 - SimpleLog - INFO: - Interactor 1 finished episode 360 with reward 200.000 in 200 steps +2023-06-23 22:35:50 - SimpleLog - INFO: - Interactor 0 finished episode 361 with reward 200.000 in 200 steps +2023-06-23 22:35:50 - SimpleLog - INFO: - Interactor 1 finished episode 362 with reward 200.000 in 200 steps +2023-06-23 22:35:50 - SimpleLog - INFO: - Interactor 0 finished episode 363 with reward 200.000 in 200 steps +2023-06-23 22:35:50 - SimpleLog - INFO: - Interactor 1 finished episode 364 with reward 200.000 in 200 steps +2023-06-23 22:35:50 - SimpleLog - INFO: - Interactor 1 finished episode 365 with reward 200.000 in 200 steps +2023-06-23 22:35:50 - SimpleLog - INFO: - Interactor 0 finished episode 366 with reward 200.000 in 200 steps +2023-06-23 22:35:51 - SimpleLog - INFO: - Interactor 1 finished episode 367 with reward 200.000 in 200 steps +2023-06-23 22:35:51 - SimpleLog - INFO: - Interactor 0 finished episode 368 with reward 200.000 in 200 steps +2023-06-23 22:35:51 - SimpleLog - INFO: - Interactor 0 finished episode 369 with reward 167.000 in 167 steps +2023-06-23 22:35:51 - SimpleLog - INFO: - Interactor 1 finished episode 370 with reward 196.000 in 196 steps +2023-06-23 22:35:51 - SimpleLog - INFO: - update_step: 180, online_eval_reward: 200.000 +2023-06-23 22:35:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:35:51 - SimpleLog - INFO: - Interactor 0 finished episode 371 with reward 181.000 in 181 steps +2023-06-23 22:35:52 - SimpleLog - INFO: - Interactor 1 finished episode 372 with reward 195.000 in 195 steps +2023-06-23 22:35:52 - SimpleLog - INFO: - Interactor 1 finished episode 373 with reward 200.000 in 200 steps +2023-06-23 22:35:52 - SimpleLog - INFO: - Interactor 0 finished episode 374 with reward 183.000 in 183 steps +2023-06-23 22:35:52 - SimpleLog - INFO: - Interactor 0 finished episode 375 with reward 200.000 in 200 steps +2023-06-23 22:35:52 - SimpleLog - INFO: - Interactor 1 finished episode 376 with reward 200.000 in 200 steps +2023-06-23 22:35:52 - SimpleLog - INFO: - Interactor 0 finished episode 377 with reward 200.000 in 200 steps +2023-06-23 22:35:52 - SimpleLog - INFO: - Interactor 1 finished episode 378 with reward 200.000 in 200 steps +2023-06-23 22:35:52 - SimpleLog - INFO: - Interactor 0 finished episode 379 with reward 200.000 in 200 steps +2023-06-23 22:35:53 - SimpleLog - INFO: - Interactor 1 finished episode 380 with reward 200.000 in 200 steps +2023-06-23 22:35:53 - SimpleLog - INFO: - Interactor 0 finished episode 381 with reward 200.000 in 200 steps +2023-06-23 22:35:53 - SimpleLog - INFO: - Interactor 1 finished episode 382 with reward 200.000 in 200 steps +2023-06-23 22:35:53 - SimpleLog - INFO: - Interactor 1 finished episode 383 with reward 200.000 in 200 steps +2023-06-23 22:35:53 - SimpleLog - INFO: - update_step: 190, online_eval_reward: 149.000 +2023-06-23 22:35:53 - SimpleLog - INFO: - Interactor 0 finished episode 384 with reward 200.000 in 200 steps +2023-06-23 22:35:53 - SimpleLog - INFO: - Interactor 0 finished episode 385 with reward 162.000 in 162 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 1 finished episode 386 with reward 154.000 in 154 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 0 finished episode 387 with reward 144.000 in 144 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 0 finished episode 388 with reward 158.000 in 158 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 1 finished episode 389 with reward 169.000 in 169 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 1 finished episode 390 with reward 159.000 in 159 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 0 finished episode 391 with reward 137.000 in 137 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 0 finished episode 392 with reward 133.000 in 133 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 1 finished episode 393 with reward 147.000 in 147 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 1 finished episode 394 with reward 135.000 in 135 steps +2023-06-23 22:35:54 - SimpleLog - INFO: - Interactor 0 finished episode 395 with reward 133.000 in 133 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 0 finished episode 396 with reward 114.000 in 114 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 1 finished episode 397 with reward 129.000 in 129 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 1 finished episode 398 with reward 142.000 in 142 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 0 finished episode 399 with reward 122.000 in 122 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 0 finished episode 400 with reward 116.000 in 116 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 1 finished episode 401 with reward 127.000 in 127 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 1 finished episode 402 with reward 123.000 in 123 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - update_step: 200, online_eval_reward: 120.000 +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 0 finished episode 403 with reward 125.000 in 125 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 0 finished episode 404 with reward 129.000 in 129 steps +2023-06-23 22:35:55 - SimpleLog - INFO: - Interactor 1 finished episode 405 with reward 122.000 in 122 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 1 finished episode 406 with reward 129.000 in 129 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 0 finished episode 407 with reward 111.000 in 111 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 0 finished episode 408 with reward 144.000 in 144 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 1 finished episode 409 with reward 132.000 in 132 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 1 finished episode 410 with reward 134.000 in 134 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 0 finished episode 411 with reward 134.000 in 134 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 0 finished episode 412 with reward 155.000 in 155 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 1 finished episode 413 with reward 138.000 in 138 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 0 finished episode 414 with reward 157.000 in 157 steps +2023-06-23 22:35:56 - SimpleLog - INFO: - Interactor 1 finished episode 415 with reward 155.000 in 155 steps +2023-06-23 22:35:57 - SimpleLog - INFO: - Interactor 1 finished episode 416 with reward 183.000 in 183 steps +2023-06-23 22:35:57 - SimpleLog - INFO: - Interactor 0 finished episode 417 with reward 186.000 in 186 steps +2023-06-23 22:35:57 - SimpleLog - INFO: - Interactor 0 finished episode 418 with reward 176.000 in 176 steps +2023-06-23 22:35:57 - SimpleLog - INFO: - Interactor 1 finished episode 419 with reward 200.000 in 200 steps +2023-06-23 22:35:57 - SimpleLog - INFO: - update_step: 210, online_eval_reward: 153.000 +2023-06-23 22:35:57 - SimpleLog - INFO: - Interactor 0 finished episode 420 with reward 180.000 in 180 steps +2023-06-23 22:35:57 - SimpleLog - INFO: - Interactor 1 finished episode 421 with reward 179.000 in 179 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 1 finished episode 422 with reward 147.000 in 147 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 0 finished episode 423 with reward 148.000 in 148 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 0 finished episode 424 with reward 146.000 in 146 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 1 finished episode 425 with reward 160.000 in 160 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 0 finished episode 426 with reward 145.000 in 145 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 0 finished episode 427 with reward 132.000 in 132 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 1 finished episode 428 with reward 166.000 in 166 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 1 finished episode 429 with reward 170.000 in 170 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 0 finished episode 430 with reward 152.000 in 152 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 0 finished episode 431 with reward 141.000 in 141 steps +2023-06-23 22:35:58 - SimpleLog - INFO: - Interactor 1 finished episode 432 with reward 125.000 in 125 steps +2023-06-23 22:35:59 - SimpleLog - INFO: - Interactor 1 finished episode 433 with reward 174.000 in 174 steps +2023-06-23 22:35:59 - SimpleLog - INFO: - Interactor 0 finished episode 434 with reward 151.000 in 151 steps +2023-06-23 22:35:59 - SimpleLog - INFO: - Interactor 1 finished episode 435 with reward 147.000 in 147 steps +2023-06-23 22:35:59 - SimpleLog - INFO: - update_step: 220, online_eval_reward: 144.000 +2023-06-23 22:35:59 - SimpleLog - INFO: - Interactor 0 finished episode 436 with reward 149.000 in 149 steps +2023-06-23 22:35:59 - SimpleLog - INFO: - Interactor 0 finished episode 437 with reward 120.000 in 120 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 1 finished episode 438 with reward 151.000 in 151 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 1 finished episode 439 with reward 156.000 in 156 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 0 finished episode 440 with reward 136.000 in 136 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 0 finished episode 441 with reward 109.000 in 109 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 1 finished episode 442 with reward 135.000 in 135 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 1 finished episode 443 with reward 132.000 in 132 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 0 finished episode 444 with reward 115.000 in 115 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 0 finished episode 445 with reward 99.000 in 99 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 0 finished episode 446 with reward 115.000 in 115 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 1 finished episode 447 with reward 129.000 in 129 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 1 finished episode 448 with reward 119.000 in 119 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 0 finished episode 449 with reward 109.000 in 109 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 0 finished episode 450 with reward 64.000 in 64 steps +2023-06-23 22:36:00 - SimpleLog - INFO: - Interactor 0 finished episode 451 with reward 47.000 in 47 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 1 finished episode 452 with reward 128.000 in 128 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 1 finished episode 453 with reward 120.000 in 120 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 0 finished episode 454 with reward 116.000 in 116 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 0 finished episode 455 with reward 119.000 in 119 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 1 finished episode 456 with reward 110.000 in 110 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 1 finished episode 457 with reward 129.000 in 129 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - update_step: 230, online_eval_reward: 133.000 +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 0 finished episode 458 with reward 107.000 in 107 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 0 finished episode 459 with reward 141.000 in 141 steps +2023-06-23 22:36:01 - SimpleLog - INFO: - Interactor 1 finished episode 460 with reward 107.000 in 107 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 1 finished episode 461 with reward 131.000 in 131 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 0 finished episode 462 with reward 117.000 in 117 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 0 finished episode 463 with reward 131.000 in 131 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 1 finished episode 464 with reward 145.000 in 145 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 1 finished episode 465 with reward 176.000 in 176 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 0 finished episode 466 with reward 162.000 in 162 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 1 finished episode 467 with reward 187.000 in 187 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 0 finished episode 468 with reward 200.000 in 200 steps +2023-06-23 22:36:02 - SimpleLog - INFO: - Interactor 0 finished episode 469 with reward 200.000 in 200 steps +2023-06-23 22:36:03 - SimpleLog - INFO: - Interactor 1 finished episode 470 with reward 200.000 in 200 steps +2023-06-23 22:36:03 - SimpleLog - INFO: - Interactor 0 finished episode 471 with reward 200.000 in 200 steps +2023-06-23 22:36:03 - SimpleLog - INFO: - Interactor 1 finished episode 472 with reward 200.000 in 200 steps +2023-06-23 22:36:03 - SimpleLog - INFO: - Interactor 1 finished episode 473 with reward 200.000 in 200 steps +2023-06-23 22:36:03 - SimpleLog - INFO: - update_step: 240, online_eval_reward: 200.000 +2023-06-23 22:36:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:03 - SimpleLog - INFO: - Interactor 0 finished episode 474 with reward 200.000 in 200 steps +2023-06-23 22:36:04 - SimpleLog - INFO: - Interactor 0 finished episode 475 with reward 163.000 in 163 steps +2023-06-23 22:36:04 - SimpleLog - INFO: - Interactor 1 finished episode 476 with reward 200.000 in 200 steps +2023-06-23 22:36:04 - SimpleLog - INFO: - Interactor 0 finished episode 477 with reward 156.000 in 156 steps +2023-06-23 22:36:04 - SimpleLog - INFO: - Interactor 1 finished episode 478 with reward 200.000 in 200 steps +2023-06-23 22:36:04 - SimpleLog - INFO: - Interactor 0 finished episode 479 with reward 200.000 in 200 steps +2023-06-23 22:36:04 - SimpleLog - INFO: - Interactor 1 finished episode 480 with reward 200.000 in 200 steps +2023-06-23 22:36:04 - SimpleLog - INFO: - Interactor 0 finished episode 481 with reward 200.000 in 200 steps +2023-06-23 22:36:05 - SimpleLog - INFO: - Interactor 0 finished episode 482 with reward 200.000 in 200 steps +2023-06-23 22:36:05 - SimpleLog - INFO: - Interactor 1 finished episode 483 with reward 200.000 in 200 steps +2023-06-23 22:36:05 - SimpleLog - INFO: - Interactor 1 finished episode 484 with reward 200.000 in 200 steps +2023-06-23 22:36:05 - SimpleLog - INFO: - Interactor 0 finished episode 485 with reward 188.000 in 188 steps +2023-06-23 22:36:05 - SimpleLog - INFO: - Interactor 1 finished episode 486 with reward 200.000 in 200 steps +2023-06-23 22:36:05 - SimpleLog - INFO: - update_step: 250, online_eval_reward: 179.000 +2023-06-23 22:36:06 - SimpleLog - INFO: - Interactor 0 finished episode 487 with reward 186.000 in 186 steps +2023-06-23 22:36:06 - SimpleLog - INFO: - Interactor 1 finished episode 488 with reward 200.000 in 200 steps +2023-06-23 22:36:06 - SimpleLog - INFO: - Interactor 0 finished episode 489 with reward 180.000 in 180 steps +2023-06-23 22:36:06 - SimpleLog - INFO: - Interactor 0 finished episode 490 with reward 173.000 in 173 steps +2023-06-23 22:36:06 - SimpleLog - INFO: - Interactor 1 finished episode 491 with reward 200.000 in 200 steps +2023-06-23 22:36:06 - SimpleLog - INFO: - Interactor 1 finished episode 492 with reward 200.000 in 200 steps +2023-06-23 22:36:06 - SimpleLog - INFO: - Interactor 0 finished episode 493 with reward 182.000 in 182 steps +2023-06-23 22:36:06 - SimpleLog - INFO: - Interactor 1 finished episode 494 with reward 177.000 in 177 steps +2023-06-23 22:36:07 - SimpleLog - INFO: - Interactor 0 finished episode 495 with reward 171.000 in 171 steps +2023-06-23 22:36:07 - SimpleLog - INFO: - Interactor 0 finished episode 496 with reward 169.000 in 169 steps +2023-06-23 22:36:07 - SimpleLog - INFO: - Interactor 1 finished episode 497 with reward 151.000 in 151 steps +2023-06-23 22:36:07 - SimpleLog - INFO: - Interactor 1 finished episode 498 with reward 170.000 in 170 steps +2023-06-23 22:36:07 - SimpleLog - INFO: - Interactor 0 finished episode 499 with reward 181.000 in 181 steps +2023-06-23 22:36:07 - SimpleLog - INFO: - Interactor 1 finished episode 500 with reward 151.000 in 151 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - update_step: 260, online_eval_reward: 158.000 +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 0 finished episode 501 with reward 132.000 in 132 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 0 finished episode 502 with reward 152.000 in 152 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 1 finished episode 503 with reward 195.000 in 195 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 1 finished episode 504 with reward 174.000 in 174 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 0 finished episode 505 with reward 162.000 in 162 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 0 finished episode 506 with reward 177.000 in 177 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 1 finished episode 507 with reward 171.000 in 171 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 0 finished episode 508 with reward 200.000 in 200 steps +2023-06-23 22:36:08 - SimpleLog - INFO: - Interactor 1 finished episode 509 with reward 168.000 in 168 steps +2023-06-23 22:36:09 - SimpleLog - INFO: - Interactor 0 finished episode 510 with reward 200.000 in 200 steps +2023-06-23 22:36:09 - SimpleLog - INFO: - Interactor 1 finished episode 511 with reward 200.000 in 200 steps +2023-06-23 22:36:09 - SimpleLog - INFO: - Interactor 1 finished episode 512 with reward 200.000 in 200 steps +2023-06-23 22:36:09 - SimpleLog - INFO: - Interactor 0 finished episode 513 with reward 200.000 in 200 steps +2023-06-23 22:36:09 - SimpleLog - INFO: - Interactor 1 finished episode 514 with reward 200.000 in 200 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - update_step: 270, online_eval_reward: 200.000 +2023-06-23 22:36:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 0 finished episode 515 with reward 200.000 in 200 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 0 finished episode 516 with reward 200.000 in 200 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 1 finished episode 517 with reward 200.000 in 200 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 0 finished episode 518 with reward 200.000 in 200 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 1 finished episode 519 with reward 200.000 in 200 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 1 finished episode 520 with reward 197.000 in 197 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 0 finished episode 521 with reward 185.000 in 185 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 0 finished episode 522 with reward 159.000 in 159 steps +2023-06-23 22:36:10 - SimpleLog - INFO: - Interactor 1 finished episode 523 with reward 195.000 in 195 steps +2023-06-23 22:36:11 - SimpleLog - INFO: - Interactor 0 finished episode 524 with reward 186.000 in 186 steps +2023-06-23 22:36:11 - SimpleLog - INFO: - Interactor 1 finished episode 525 with reward 168.000 in 168 steps +2023-06-23 22:36:11 - SimpleLog - INFO: - Interactor 0 finished episode 526 with reward 200.000 in 200 steps +2023-06-23 22:36:11 - SimpleLog - INFO: - Interactor 1 finished episode 527 with reward 195.000 in 195 steps +2023-06-23 22:36:11 - SimpleLog - INFO: - Interactor 1 finished episode 528 with reward 200.000 in 200 steps +2023-06-23 22:36:12 - SimpleLog - INFO: - update_step: 280, online_eval_reward: 200.000 +2023-06-23 22:36:12 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:12 - SimpleLog - INFO: - Interactor 0 finished episode 529 with reward 200.000 in 200 steps +2023-06-23 22:36:12 - SimpleLog - INFO: - Interactor 1 finished episode 530 with reward 200.000 in 200 steps +2023-06-23 22:36:12 - SimpleLog - INFO: - Interactor 0 finished episode 531 with reward 200.000 in 200 steps +2023-06-23 22:36:12 - SimpleLog - INFO: - Interactor 0 finished episode 532 with reward 178.000 in 178 steps +2023-06-23 22:36:12 - SimpleLog - INFO: - Interactor 1 finished episode 533 with reward 200.000 in 200 steps +2023-06-23 22:36:12 - SimpleLog - INFO: - Interactor 0 finished episode 534 with reward 161.000 in 161 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 0 finished episode 535 with reward 123.000 in 123 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 1 finished episode 536 with reward 196.000 in 196 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 1 finished episode 537 with reward 140.000 in 140 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 0 finished episode 538 with reward 123.000 in 123 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 0 finished episode 539 with reward 121.000 in 121 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 1 finished episode 540 with reward 132.000 in 132 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 1 finished episode 541 with reward 131.000 in 131 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 0 finished episode 542 with reward 115.000 in 115 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 0 finished episode 543 with reward 140.000 in 140 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 1 finished episode 544 with reward 130.000 in 130 steps +2023-06-23 22:36:13 - SimpleLog - INFO: - Interactor 1 finished episode 545 with reward 151.000 in 151 steps +2023-06-23 22:36:14 - SimpleLog - INFO: - update_step: 290, online_eval_reward: 145.000 +2023-06-23 22:36:14 - SimpleLog - INFO: - Interactor 0 finished episode 546 with reward 140.000 in 140 steps +2023-06-23 22:36:14 - SimpleLog - INFO: - Interactor 0 finished episode 547 with reward 133.000 in 133 steps +2023-06-23 22:36:14 - SimpleLog - INFO: - Interactor 1 finished episode 548 with reward 146.000 in 146 steps +2023-06-23 22:36:14 - SimpleLog - INFO: - Interactor 1 finished episode 549 with reward 134.000 in 134 steps +2023-06-23 22:36:14 - SimpleLog - INFO: - Interactor 0 finished episode 550 with reward 141.000 in 141 steps +2023-06-23 22:36:14 - SimpleLog - INFO: - Interactor 0 finished episode 551 with reward 140.000 in 140 steps +2023-06-23 22:36:14 - SimpleLog - INFO: - Interactor 1 finished episode 552 with reward 152.000 in 152 steps +2023-06-23 22:36:14 - SimpleLog - INFO: - Interactor 0 finished episode 553 with reward 141.000 in 141 steps +2023-06-23 22:36:15 - SimpleLog - INFO: - Interactor 1 finished episode 554 with reward 148.000 in 148 steps +2023-06-23 22:36:15 - SimpleLog - INFO: - Interactor 1 finished episode 555 with reward 176.000 in 176 steps +2023-06-23 22:36:15 - SimpleLog - INFO: - Interactor 0 finished episode 556 with reward 137.000 in 137 steps +2023-06-23 22:36:15 - SimpleLog - INFO: - Interactor 0 finished episode 557 with reward 148.000 in 148 steps +2023-06-23 22:36:15 - SimpleLog - INFO: - Interactor 1 finished episode 558 with reward 167.000 in 167 steps +2023-06-23 22:36:15 - SimpleLog - INFO: - Interactor 0 finished episode 559 with reward 179.000 in 179 steps +2023-06-23 22:36:15 - SimpleLog - INFO: - Interactor 1 finished episode 560 with reward 155.000 in 155 steps +2023-06-23 22:36:15 - SimpleLog - INFO: - Interactor 1 finished episode 561 with reward 200.000 in 200 steps +2023-06-23 22:36:16 - SimpleLog - INFO: - update_step: 300, online_eval_reward: 200.000 +2023-06-23 22:36:16 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:16 - SimpleLog - INFO: - Interactor 0 finished episode 562 with reward 200.000 in 200 steps +2023-06-23 22:36:16 - SimpleLog - INFO: - Interactor 0 finished episode 563 with reward 200.000 in 200 steps +2023-06-23 22:36:16 - SimpleLog - INFO: - Interactor 1 finished episode 564 with reward 200.000 in 200 steps +2023-06-23 22:36:16 - SimpleLog - INFO: - Interactor 0 finished episode 565 with reward 183.000 in 183 steps +2023-06-23 22:36:16 - SimpleLog - INFO: - Interactor 1 finished episode 566 with reward 200.000 in 200 steps +2023-06-23 22:36:17 - SimpleLog - INFO: - Interactor 0 finished episode 567 with reward 173.000 in 173 steps +2023-06-23 22:36:17 - SimpleLog - INFO: - Interactor 0 finished episode 568 with reward 166.000 in 166 steps +2023-06-23 22:36:17 - SimpleLog - INFO: - Interactor 1 finished episode 569 with reward 200.000 in 200 steps +2023-06-23 22:36:17 - SimpleLog - INFO: - Interactor 1 finished episode 570 with reward 166.000 in 166 steps +2023-06-23 22:36:17 - SimpleLog - INFO: - Interactor 0 finished episode 571 with reward 166.000 in 166 steps +2023-06-23 22:36:17 - SimpleLog - INFO: - Interactor 1 finished episode 572 with reward 185.000 in 185 steps +2023-06-23 22:36:17 - SimpleLog - INFO: - Interactor 0 finished episode 573 with reward 200.000 in 200 steps +2023-06-23 22:36:17 - SimpleLog - INFO: - Interactor 1 finished episode 574 with reward 200.000 in 200 steps +2023-06-23 22:36:18 - SimpleLog - INFO: - update_step: 310, online_eval_reward: 200.000 +2023-06-23 22:36:18 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:18 - SimpleLog - INFO: - Interactor 0 finished episode 575 with reward 200.000 in 200 steps +2023-06-23 22:36:18 - SimpleLog - INFO: - Interactor 0 finished episode 576 with reward 200.000 in 200 steps +2023-06-23 22:36:18 - SimpleLog - INFO: - Interactor 1 finished episode 577 with reward 200.000 in 200 steps +2023-06-23 22:36:18 - SimpleLog - INFO: - Interactor 1 finished episode 578 with reward 200.000 in 200 steps +2023-06-23 22:36:18 - SimpleLog - INFO: - Interactor 0 finished episode 579 with reward 200.000 in 200 steps +2023-06-23 22:36:18 - SimpleLog - INFO: - Interactor 1 finished episode 580 with reward 200.000 in 200 steps +2023-06-23 22:36:19 - SimpleLog - INFO: - Interactor 0 finished episode 581 with reward 200.000 in 200 steps +2023-06-23 22:36:19 - SimpleLog - INFO: - Interactor 1 finished episode 582 with reward 200.000 in 200 steps +2023-06-23 22:36:19 - SimpleLog - INFO: - Interactor 0 finished episode 583 with reward 200.000 in 200 steps +2023-06-23 22:36:19 - SimpleLog - INFO: - Interactor 1 finished episode 584 with reward 200.000 in 200 steps +2023-06-23 22:36:19 - SimpleLog - INFO: - Interactor 0 finished episode 585 with reward 200.000 in 200 steps +2023-06-23 22:36:19 - SimpleLog - INFO: - Interactor 0 finished episode 586 with reward 200.000 in 200 steps +2023-06-23 22:36:19 - SimpleLog - INFO: - Interactor 1 finished episode 587 with reward 200.000 in 200 steps +2023-06-23 22:36:20 - SimpleLog - INFO: - Interactor 1 finished episode 588 with reward 200.000 in 200 steps +2023-06-23 22:36:20 - SimpleLog - INFO: - update_step: 320, online_eval_reward: 200.000 +2023-06-23 22:36:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:20 - SimpleLog - INFO: - Interactor 0 finished episode 589 with reward 200.000 in 200 steps +2023-06-23 22:36:20 - SimpleLog - INFO: - Interactor 1 finished episode 590 with reward 200.000 in 200 steps +2023-06-23 22:36:20 - SimpleLog - INFO: - Interactor 0 finished episode 591 with reward 200.000 in 200 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 1 finished episode 592 with reward 200.000 in 200 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 0 finished episode 593 with reward 200.000 in 200 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 0 finished episode 594 with reward 200.000 in 200 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 1 finished episode 595 with reward 200.000 in 200 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 1 finished episode 596 with reward 200.000 in 200 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 0 finished episode 597 with reward 183.000 in 183 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 1 finished episode 598 with reward 175.000 in 175 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 0 finished episode 599 with reward 171.000 in 171 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 0 finished episode 600 with reward 17.000 in 17 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 0 finished episode 601 with reward 14.000 in 14 steps +2023-06-23 22:36:21 - SimpleLog - INFO: - Interactor 0 finished episode 602 with reward 13.000 in 13 steps +2023-06-23 22:36:22 - SimpleLog - INFO: - Interactor 1 finished episode 603 with reward 179.000 in 179 steps +2023-06-23 22:36:22 - SimpleLog - INFO: - update_step: 330, online_eval_reward: 200.000 +2023-06-23 22:36:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:22 - SimpleLog - INFO: - Interactor 0 finished episode 604 with reward 176.000 in 176 steps +2023-06-23 22:36:22 - SimpleLog - INFO: - Interactor 0 finished episode 605 with reward 200.000 in 200 steps +2023-06-23 22:36:22 - SimpleLog - INFO: - Interactor 1 finished episode 606 with reward 194.000 in 194 steps +2023-06-23 22:36:22 - SimpleLog - INFO: - Interactor 1 finished episode 607 with reward 200.000 in 200 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 0 finished episode 608 with reward 191.000 in 191 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 1 finished episode 609 with reward 200.000 in 200 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 0 finished episode 610 with reward 187.000 in 187 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 1 finished episode 611 with reward 190.000 in 190 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 0 finished episode 612 with reward 159.000 in 159 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 0 finished episode 613 with reward 19.000 in 19 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 0 finished episode 614 with reward 14.000 in 14 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 0 finished episode 615 with reward 159.000 in 159 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 0 finished episode 616 with reward 28.000 in 28 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 1 finished episode 617 with reward 166.000 in 166 steps +2023-06-23 22:36:23 - SimpleLog - INFO: - Interactor 1 finished episode 618 with reward 148.000 in 148 steps +2023-06-23 22:36:24 - SimpleLog - INFO: - Interactor 0 finished episode 619 with reward 184.000 in 184 steps +2023-06-23 22:36:24 - SimpleLog - INFO: - Interactor 1 finished episode 620 with reward 162.000 in 162 steps +2023-06-23 22:36:24 - SimpleLog - INFO: - update_step: 340, online_eval_reward: 200.000 +2023-06-23 22:36:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:24 - SimpleLog - INFO: - Interactor 0 finished episode 621 with reward 189.000 in 189 steps +2023-06-23 22:36:24 - SimpleLog - INFO: - Interactor 1 finished episode 622 with reward 194.000 in 194 steps +2023-06-23 22:36:24 - SimpleLog - INFO: - Interactor 1 finished episode 623 with reward 200.000 in 200 steps +2023-06-23 22:36:25 - SimpleLog - INFO: - Interactor 0 finished episode 624 with reward 200.000 in 200 steps +2023-06-23 22:36:25 - SimpleLog - INFO: - Interactor 0 finished episode 625 with reward 199.000 in 199 steps +2023-06-23 22:36:25 - SimpleLog - INFO: - Interactor 1 finished episode 626 with reward 200.000 in 200 steps +2023-06-23 22:36:25 - SimpleLog - INFO: - Interactor 0 finished episode 627 with reward 200.000 in 200 steps +2023-06-23 22:36:25 - SimpleLog - INFO: - Interactor 1 finished episode 628 with reward 188.000 in 188 steps +2023-06-23 22:36:25 - SimpleLog - INFO: - Interactor 0 finished episode 629 with reward 200.000 in 200 steps +2023-06-23 22:36:25 - SimpleLog - INFO: - Interactor 1 finished episode 630 with reward 188.000 in 188 steps +2023-06-23 22:36:25 - SimpleLog - INFO: - Interactor 1 finished episode 631 with reward 200.000 in 200 steps +2023-06-23 22:36:26 - SimpleLog - INFO: - Interactor 0 finished episode 632 with reward 200.000 in 200 steps +2023-06-23 22:36:26 - SimpleLog - INFO: - Interactor 1 finished episode 633 with reward 200.000 in 200 steps +2023-06-23 22:36:26 - SimpleLog - INFO: - update_step: 350, online_eval_reward: 200.000 +2023-06-23 22:36:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:26 - SimpleLog - INFO: - Interactor 0 finished episode 634 with reward 200.000 in 200 steps +2023-06-23 22:36:26 - SimpleLog - INFO: - Interactor 0 finished episode 635 with reward 200.000 in 200 steps +2023-06-23 22:36:27 - SimpleLog - INFO: - Interactor 1 finished episode 636 with reward 200.000 in 200 steps +2023-06-23 22:36:27 - SimpleLog - INFO: - Interactor 0 finished episode 637 with reward 200.000 in 200 steps +2023-06-23 22:36:27 - SimpleLog - INFO: - Interactor 1 finished episode 638 with reward 200.000 in 200 steps +2023-06-23 22:36:27 - SimpleLog - INFO: - Interactor 1 finished episode 639 with reward 200.000 in 200 steps +2023-06-23 22:36:27 - SimpleLog - INFO: - Interactor 0 finished episode 640 with reward 200.000 in 200 steps +2023-06-23 22:36:27 - SimpleLog - INFO: - Interactor 1 finished episode 641 with reward 200.000 in 200 steps +2023-06-23 22:36:27 - SimpleLog - INFO: - Interactor 0 finished episode 642 with reward 200.000 in 200 steps +2023-06-23 22:36:27 - SimpleLog - INFO: - Interactor 0 finished episode 643 with reward 200.000 in 200 steps +2023-06-23 22:36:28 - SimpleLog - INFO: - Interactor 1 finished episode 644 with reward 200.000 in 200 steps +2023-06-23 22:36:28 - SimpleLog - INFO: - Interactor 0 finished episode 645 with reward 200.000 in 200 steps +2023-06-23 22:36:28 - SimpleLog - INFO: - Interactor 1 finished episode 646 with reward 200.000 in 200 steps +2023-06-23 22:36:28 - SimpleLog - INFO: - update_step: 360, online_eval_reward: 200.000 +2023-06-23 22:36:28 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:28 - SimpleLog - INFO: - Interactor 0 finished episode 647 with reward 200.000 in 200 steps +2023-06-23 22:36:29 - SimpleLog - INFO: - Interactor 1 finished episode 648 with reward 200.000 in 200 steps +2023-06-23 22:36:29 - SimpleLog - INFO: - Interactor 1 finished episode 649 with reward 200.000 in 200 steps +2023-06-23 22:36:29 - SimpleLog - INFO: - Interactor 0 finished episode 650 with reward 200.000 in 200 steps +2023-06-23 22:36:29 - SimpleLog - INFO: - Interactor 1 finished episode 651 with reward 200.000 in 200 steps +2023-06-23 22:36:29 - SimpleLog - INFO: - Interactor 0 finished episode 652 with reward 200.000 in 200 steps +2023-06-23 22:36:29 - SimpleLog - INFO: - Interactor 0 finished episode 653 with reward 200.000 in 200 steps +2023-06-23 22:36:29 - SimpleLog - INFO: - Interactor 1 finished episode 654 with reward 200.000 in 200 steps +2023-06-23 22:36:30 - SimpleLog - INFO: - Interactor 0 finished episode 655 with reward 200.000 in 200 steps +2023-06-23 22:36:30 - SimpleLog - INFO: - Interactor 1 finished episode 656 with reward 200.000 in 200 steps +2023-06-23 22:36:30 - SimpleLog - INFO: - Interactor 1 finished episode 657 with reward 200.000 in 200 steps +2023-06-23 22:36:30 - SimpleLog - INFO: - Interactor 0 finished episode 658 with reward 200.000 in 200 steps +2023-06-23 22:36:30 - SimpleLog - INFO: - Interactor 1 finished episode 659 with reward 200.000 in 200 steps +2023-06-23 22:36:31 - SimpleLog - INFO: - update_step: 370, online_eval_reward: 200.000 +2023-06-23 22:36:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:31 - SimpleLog - INFO: - Interactor 0 finished episode 660 with reward 200.000 in 200 steps +2023-06-23 22:36:31 - SimpleLog - INFO: - Interactor 1 finished episode 661 with reward 200.000 in 200 steps +2023-06-23 22:36:31 - SimpleLog - INFO: - Interactor 0 finished episode 662 with reward 200.000 in 200 steps +2023-06-23 22:36:31 - SimpleLog - INFO: - Interactor 0 finished episode 663 with reward 200.000 in 200 steps +2023-06-23 22:36:31 - SimpleLog - INFO: - Interactor 1 finished episode 664 with reward 200.000 in 200 steps +2023-06-23 22:36:31 - SimpleLog - INFO: - Interactor 0 finished episode 665 with reward 200.000 in 200 steps +2023-06-23 22:36:31 - SimpleLog - INFO: - Interactor 1 finished episode 666 with reward 200.000 in 200 steps +2023-06-23 22:36:31 - SimpleLog - INFO: - Interactor 1 finished episode 667 with reward 200.000 in 200 steps +2023-06-23 22:36:32 - SimpleLog - INFO: - Interactor 0 finished episode 668 with reward 200.000 in 200 steps +2023-06-23 22:36:32 - SimpleLog - INFO: - Interactor 1 finished episode 669 with reward 200.000 in 200 steps +2023-06-23 22:36:32 - SimpleLog - INFO: - Interactor 0 finished episode 670 with reward 200.000 in 200 steps +2023-06-23 22:36:32 - SimpleLog - INFO: - Interactor 0 finished episode 671 with reward 200.000 in 200 steps +2023-06-23 22:36:32 - SimpleLog - INFO: - Interactor 1 finished episode 672 with reward 200.000 in 200 steps +2023-06-23 22:36:33 - SimpleLog - INFO: - update_step: 380, online_eval_reward: 200.000 +2023-06-23 22:36:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:33 - SimpleLog - INFO: - Interactor 0 finished episode 673 with reward 200.000 in 200 steps +2023-06-23 22:36:33 - SimpleLog - INFO: - Interactor 1 finished episode 674 with reward 200.000 in 200 steps +2023-06-23 22:36:33 - SimpleLog - INFO: - Interactor 0 finished episode 675 with reward 200.000 in 200 steps +2023-06-23 22:36:33 - SimpleLog - INFO: - Interactor 1 finished episode 676 with reward 200.000 in 200 steps +2023-06-23 22:36:33 - SimpleLog - INFO: - Interactor 1 finished episode 677 with reward 200.000 in 200 steps +2023-06-23 22:36:33 - SimpleLog - INFO: - Interactor 0 finished episode 678 with reward 200.000 in 200 steps +2023-06-23 22:36:33 - SimpleLog - INFO: - Interactor 1 finished episode 679 with reward 200.000 in 200 steps +2023-06-23 22:36:34 - SimpleLog - INFO: - Interactor 0 finished episode 680 with reward 200.000 in 200 steps +2023-06-23 22:36:34 - SimpleLog - INFO: - Interactor 0 finished episode 681 with reward 200.000 in 200 steps +2023-06-23 22:36:34 - SimpleLog - INFO: - Interactor 1 finished episode 682 with reward 167.000 in 167 steps +2023-06-23 22:36:34 - SimpleLog - INFO: - Interactor 0 finished episode 683 with reward 200.000 in 200 steps +2023-06-23 22:36:34 - SimpleLog - INFO: - Interactor 0 finished episode 684 with reward 23.000 in 23 steps +2023-06-23 22:36:34 - SimpleLog - INFO: - Interactor 1 finished episode 685 with reward 200.000 in 200 steps +2023-06-23 22:36:34 - SimpleLog - INFO: - Interactor 1 finished episode 686 with reward 200.000 in 200 steps +2023-06-23 22:36:35 - SimpleLog - INFO: - update_step: 390, online_eval_reward: 200.000 +2023-06-23 22:36:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:35 - SimpleLog - INFO: - Interactor 0 finished episode 687 with reward 200.000 in 200 steps +2023-06-23 22:36:35 - SimpleLog - INFO: - Interactor 0 finished episode 688 with reward 74.000 in 74 steps +2023-06-23 22:36:35 - SimpleLog - INFO: - Interactor 1 finished episode 689 with reward 200.000 in 200 steps +2023-06-23 22:36:35 - SimpleLog - INFO: - Interactor 0 finished episode 690 with reward 72.000 in 72 steps +2023-06-23 22:36:35 - SimpleLog - INFO: - Interactor 0 finished episode 691 with reward 200.000 in 200 steps +2023-06-23 22:36:35 - SimpleLog - INFO: - Interactor 1 finished episode 692 with reward 200.000 in 200 steps +2023-06-23 22:36:35 - SimpleLog - INFO: - Interactor 0 finished episode 693 with reward 200.000 in 200 steps +2023-06-23 22:36:36 - SimpleLog - INFO: - Interactor 1 finished episode 694 with reward 200.000 in 200 steps +2023-06-23 22:36:36 - SimpleLog - INFO: - Interactor 1 finished episode 695 with reward 200.000 in 200 steps +2023-06-23 22:36:36 - SimpleLog - INFO: - Interactor 0 finished episode 696 with reward 160.000 in 160 steps +2023-06-23 22:36:36 - SimpleLog - INFO: - Interactor 1 finished episode 697 with reward 200.000 in 200 steps +2023-06-23 22:36:36 - SimpleLog - INFO: - Interactor 0 finished episode 698 with reward 200.000 in 200 steps +2023-06-23 22:36:36 - SimpleLog - INFO: - Interactor 0 finished episode 699 with reward 200.000 in 200 steps +2023-06-23 22:36:36 - SimpleLog - INFO: - Interactor 1 finished episode 700 with reward 200.000 in 200 steps +2023-06-23 22:36:36 - SimpleLog - INFO: - Interactor 1 finished episode 701 with reward 82.000 in 82 steps +2023-06-23 22:36:37 - SimpleLog - INFO: - update_step: 400, online_eval_reward: 200.000 +2023-06-23 22:36:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:37 - SimpleLog - INFO: - Interactor 0 finished episode 702 with reward 200.000 in 200 steps +2023-06-23 22:36:37 - SimpleLog - INFO: - Interactor 1 finished episode 703 with reward 200.000 in 200 steps +2023-06-23 22:36:37 - SimpleLog - INFO: - Interactor 0 finished episode 704 with reward 200.000 in 200 steps +2023-06-23 22:36:37 - SimpleLog - INFO: - Interactor 1 finished episode 705 with reward 200.000 in 200 steps +2023-06-23 22:36:38 - SimpleLog - INFO: - Interactor 0 finished episode 706 with reward 200.000 in 200 steps +2023-06-23 22:36:38 - SimpleLog - INFO: - Interactor 0 finished episode 707 with reward 200.000 in 200 steps +2023-06-23 22:36:38 - SimpleLog - INFO: - Interactor 1 finished episode 708 with reward 200.000 in 200 steps +2023-06-23 22:36:38 - SimpleLog - INFO: - Interactor 1 finished episode 709 with reward 200.000 in 200 steps +2023-06-23 22:36:38 - SimpleLog - INFO: - Interactor 0 finished episode 710 with reward 200.000 in 200 steps +2023-06-23 22:36:38 - SimpleLog - INFO: - Interactor 1 finished episode 711 with reward 200.000 in 200 steps +2023-06-23 22:36:38 - SimpleLog - INFO: - Interactor 0 finished episode 712 with reward 200.000 in 200 steps +2023-06-23 22:36:38 - SimpleLog - INFO: - Interactor 1 finished episode 713 with reward 200.000 in 200 steps +2023-06-23 22:36:39 - SimpleLog - INFO: - update_step: 410, online_eval_reward: 200.000 +2023-06-23 22:36:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:39 - SimpleLog - INFO: - Interactor 0 finished episode 714 with reward 200.000 in 200 steps +2023-06-23 22:36:39 - SimpleLog - INFO: - Interactor 1 finished episode 715 with reward 200.000 in 200 steps +2023-06-23 22:36:39 - SimpleLog - INFO: - Interactor 0 finished episode 716 with reward 200.000 in 200 steps +2023-06-23 22:36:39 - SimpleLog - INFO: - Interactor 0 finished episode 717 with reward 200.000 in 200 steps +2023-06-23 22:36:39 - SimpleLog - INFO: - Interactor 1 finished episode 718 with reward 200.000 in 200 steps +2023-06-23 22:36:40 - SimpleLog - INFO: - Interactor 1 finished episode 719 with reward 200.000 in 200 steps +2023-06-23 22:36:40 - SimpleLog - INFO: - Interactor 0 finished episode 720 with reward 200.000 in 200 steps +2023-06-23 22:36:40 - SimpleLog - INFO: - Interactor 1 finished episode 721 with reward 200.000 in 200 steps +2023-06-23 22:36:40 - SimpleLog - INFO: - Interactor 0 finished episode 722 with reward 200.000 in 200 steps +2023-06-23 22:36:40 - SimpleLog - INFO: - Interactor 1 finished episode 723 with reward 200.000 in 200 steps +2023-06-23 22:36:40 - SimpleLog - INFO: - Interactor 0 finished episode 724 with reward 200.000 in 200 steps +2023-06-23 22:36:40 - SimpleLog - INFO: - Interactor 0 finished episode 725 with reward 200.000 in 200 steps +2023-06-23 22:36:40 - SimpleLog - INFO: - Interactor 1 finished episode 726 with reward 200.000 in 200 steps +2023-06-23 22:36:41 - SimpleLog - INFO: - Interactor 1 finished episode 727 with reward 200.000 in 200 steps +2023-06-23 22:36:41 - SimpleLog - INFO: - update_step: 420, online_eval_reward: 200.000 +2023-06-23 22:36:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:41 - SimpleLog - INFO: - Interactor 0 finished episode 728 with reward 200.000 in 200 steps +2023-06-23 22:36:41 - SimpleLog - INFO: - Interactor 1 finished episode 729 with reward 200.000 in 200 steps +2023-06-23 22:36:41 - SimpleLog - INFO: - Interactor 0 finished episode 730 with reward 200.000 in 200 steps +2023-06-23 22:36:42 - SimpleLog - INFO: - Interactor 1 finished episode 731 with reward 200.000 in 200 steps +2023-06-23 22:36:42 - SimpleLog - INFO: - Interactor 0 finished episode 732 with reward 200.000 in 200 steps +2023-06-23 22:36:42 - SimpleLog - INFO: - Interactor 1 finished episode 733 with reward 200.000 in 200 steps +2023-06-23 22:36:42 - SimpleLog - INFO: - Interactor 0 finished episode 734 with reward 200.000 in 200 steps +2023-06-23 22:36:42 - SimpleLog - INFO: - Interactor 0 finished episode 735 with reward 200.000 in 200 steps +2023-06-23 22:36:42 - SimpleLog - INFO: - Interactor 1 finished episode 736 with reward 200.000 in 200 steps +2023-06-23 22:36:42 - SimpleLog - INFO: - Interactor 1 finished episode 737 with reward 200.000 in 200 steps +2023-06-23 22:36:42 - SimpleLog - INFO: - Interactor 0 finished episode 738 with reward 200.000 in 200 steps +2023-06-23 22:36:43 - SimpleLog - INFO: - Interactor 1 finished episode 739 with reward 200.000 in 200 steps +2023-06-23 22:36:43 - SimpleLog - INFO: - update_step: 430, online_eval_reward: 200.000 +2023-06-23 22:36:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:43 - SimpleLog - INFO: - Interactor 0 finished episode 740 with reward 200.000 in 200 steps +2023-06-23 22:36:43 - SimpleLog - INFO: - Interactor 1 finished episode 741 with reward 200.000 in 200 steps +2023-06-23 22:36:43 - SimpleLog - INFO: - Interactor 0 finished episode 742 with reward 200.000 in 200 steps +2023-06-23 22:36:44 - SimpleLog - INFO: - Interactor 0 finished episode 743 with reward 200.000 in 200 steps +2023-06-23 22:36:44 - SimpleLog - INFO: - Interactor 1 finished episode 744 with reward 200.000 in 200 steps +2023-06-23 22:36:44 - SimpleLog - INFO: - Interactor 1 finished episode 745 with reward 200.000 in 200 steps +2023-06-23 22:36:44 - SimpleLog - INFO: - Interactor 0 finished episode 746 with reward 200.000 in 200 steps +2023-06-23 22:36:44 - SimpleLog - INFO: - Interactor 1 finished episode 747 with reward 200.000 in 200 steps +2023-06-23 22:36:44 - SimpleLog - INFO: - Interactor 0 finished episode 748 with reward 200.000 in 200 steps +2023-06-23 22:36:44 - SimpleLog - INFO: - Interactor 1 finished episode 749 with reward 200.000 in 200 steps +2023-06-23 22:36:45 - SimpleLog - INFO: - Interactor 0 finished episode 750 with reward 200.000 in 200 steps +2023-06-23 22:36:45 - SimpleLog - INFO: - Interactor 1 finished episode 751 with reward 200.000 in 200 steps +2023-06-23 22:36:45 - SimpleLog - INFO: - update_step: 440, online_eval_reward: 200.000 +2023-06-23 22:36:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:45 - SimpleLog - INFO: - Interactor 0 finished episode 752 with reward 200.000 in 200 steps +2023-06-23 22:36:45 - SimpleLog - INFO: - Interactor 0 finished episode 753 with reward 200.000 in 200 steps +2023-06-23 22:36:45 - SimpleLog - INFO: - Interactor 1 finished episode 754 with reward 200.000 in 200 steps +2023-06-23 22:36:45 - SimpleLog - INFO: - Interactor 1 finished episode 755 with reward 200.000 in 200 steps +2023-06-23 22:36:46 - SimpleLog - INFO: - Interactor 0 finished episode 756 with reward 200.000 in 200 steps +2023-06-23 22:36:46 - SimpleLog - INFO: - Interactor 1 finished episode 757 with reward 200.000 in 200 steps +2023-06-23 22:36:46 - SimpleLog - INFO: - Interactor 0 finished episode 758 with reward 200.000 in 200 steps +2023-06-23 22:36:46 - SimpleLog - INFO: - Interactor 1 finished episode 759 with reward 200.000 in 200 steps +2023-06-23 22:36:46 - SimpleLog - INFO: - Interactor 0 finished episode 760 with reward 200.000 in 200 steps +2023-06-23 22:36:46 - SimpleLog - INFO: - Interactor 1 finished episode 761 with reward 200.000 in 200 steps +2023-06-23 22:36:47 - SimpleLog - INFO: - Interactor 0 finished episode 762 with reward 200.000 in 200 steps +2023-06-23 22:36:47 - SimpleLog - INFO: - Interactor 0 finished episode 763 with reward 200.000 in 200 steps +2023-06-23 22:36:47 - SimpleLog - INFO: - Interactor 1 finished episode 764 with reward 200.000 in 200 steps +2023-06-23 22:36:47 - SimpleLog - INFO: - Interactor 1 finished episode 765 with reward 200.000 in 200 steps +2023-06-23 22:36:47 - SimpleLog - INFO: - update_step: 450, online_eval_reward: 200.000 +2023-06-23 22:36:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:47 - SimpleLog - INFO: - Interactor 0 finished episode 766 with reward 200.000 in 200 steps +2023-06-23 22:36:48 - SimpleLog - INFO: - Interactor 1 finished episode 767 with reward 200.000 in 200 steps +2023-06-23 22:36:48 - SimpleLog - INFO: - Interactor 0 finished episode 768 with reward 200.000 in 200 steps +2023-06-23 22:36:48 - SimpleLog - INFO: - Interactor 1 finished episode 769 with reward 200.000 in 200 steps +2023-06-23 22:36:48 - SimpleLog - INFO: - Interactor 0 finished episode 770 with reward 200.000 in 200 steps +2023-06-23 22:36:48 - SimpleLog - INFO: - Interactor 0 finished episode 771 with reward 200.000 in 200 steps +2023-06-23 22:36:48 - SimpleLog - INFO: - Interactor 1 finished episode 772 with reward 200.000 in 200 steps +2023-06-23 22:36:48 - SimpleLog - INFO: - Interactor 1 finished episode 773 with reward 200.000 in 200 steps +2023-06-23 22:36:49 - SimpleLog - INFO: - Interactor 0 finished episode 774 with reward 200.000 in 200 steps +2023-06-23 22:36:49 - SimpleLog - INFO: - Interactor 1 finished episode 775 with reward 200.000 in 200 steps +2023-06-23 22:36:49 - SimpleLog - INFO: - Interactor 0 finished episode 776 with reward 200.000 in 200 steps +2023-06-23 22:36:49 - SimpleLog - INFO: - Interactor 1 finished episode 777 with reward 200.000 in 200 steps +2023-06-23 22:36:49 - SimpleLog - INFO: - update_step: 460, online_eval_reward: 200.000 +2023-06-23 22:36:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 0 finished episode 778 with reward 200.000 in 200 steps +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 1 finished episode 779 with reward 200.000 in 200 steps +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 0 finished episode 780 with reward 200.000 in 200 steps +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 0 finished episode 781 with reward 200.000 in 200 steps +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 1 finished episode 782 with reward 200.000 in 200 steps +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 1 finished episode 783 with reward 200.000 in 200 steps +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 0 finished episode 784 with reward 200.000 in 200 steps +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 1 finished episode 785 with reward 200.000 in 200 steps +2023-06-23 22:36:50 - SimpleLog - INFO: - Interactor 0 finished episode 786 with reward 200.000 in 200 steps +2023-06-23 22:36:51 - SimpleLog - INFO: - Interactor 0 finished episode 787 with reward 127.000 in 127 steps +2023-06-23 22:36:51 - SimpleLog - INFO: - Interactor 1 finished episode 788 with reward 200.000 in 200 steps +2023-06-23 22:36:51 - SimpleLog - INFO: - Interactor 1 finished episode 789 with reward 72.000 in 72 steps +2023-06-23 22:36:51 - SimpleLog - INFO: - Interactor 0 finished episode 790 with reward 200.000 in 200 steps +2023-06-23 22:36:51 - SimpleLog - INFO: - Interactor 1 finished episode 791 with reward 200.000 in 200 steps +2023-06-23 22:36:51 - SimpleLog - INFO: - Interactor 1 finished episode 792 with reward 123.000 in 123 steps +2023-06-23 22:36:52 - SimpleLog - INFO: - update_step: 470, online_eval_reward: 200.000 +2023-06-23 22:36:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:52 - SimpleLog - INFO: - Interactor 0 finished episode 793 with reward 200.000 in 200 steps +2023-06-23 22:36:52 - SimpleLog - INFO: - Interactor 1 finished episode 794 with reward 86.000 in 86 steps +2023-06-23 22:36:52 - SimpleLog - INFO: - Interactor 0 finished episode 795 with reward 200.000 in 200 steps +2023-06-23 22:36:52 - SimpleLog - INFO: - Interactor 0 finished episode 796 with reward 77.000 in 77 steps +2023-06-23 22:36:52 - SimpleLog - INFO: - Interactor 1 finished episode 797 with reward 200.000 in 200 steps +2023-06-23 22:36:52 - SimpleLog - INFO: - Interactor 1 finished episode 798 with reward 200.000 in 200 steps +2023-06-23 22:36:52 - SimpleLog - INFO: - Interactor 0 finished episode 799 with reward 200.000 in 200 steps +2023-06-23 22:36:52 - SimpleLog - INFO: - Interactor 1 finished episode 800 with reward 200.000 in 200 steps +2023-06-23 22:36:53 - SimpleLog - INFO: - Interactor 0 finished episode 801 with reward 200.000 in 200 steps +2023-06-23 22:36:53 - SimpleLog - INFO: - Interactor 0 finished episode 802 with reward 200.000 in 200 steps +2023-06-23 22:36:53 - SimpleLog - INFO: - Interactor 1 finished episode 803 with reward 200.000 in 200 steps +2023-06-23 22:36:53 - SimpleLog - INFO: - Interactor 0 finished episode 804 with reward 200.000 in 200 steps +2023-06-23 22:36:53 - SimpleLog - INFO: - Interactor 1 finished episode 805 with reward 200.000 in 200 steps +2023-06-23 22:36:53 - SimpleLog - INFO: - Interactor 1 finished episode 806 with reward 200.000 in 200 steps +2023-06-23 22:36:54 - SimpleLog - INFO: - update_step: 480, online_eval_reward: 200.000 +2023-06-23 22:36:54 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:54 - SimpleLog - INFO: - Interactor 0 finished episode 807 with reward 200.000 in 200 steps +2023-06-23 22:36:54 - SimpleLog - INFO: - Interactor 1 finished episode 808 with reward 200.000 in 200 steps +2023-06-23 22:36:54 - SimpleLog - INFO: - Interactor 0 finished episode 809 with reward 200.000 in 200 steps +2023-06-23 22:36:54 - SimpleLog - INFO: - Interactor 1 finished episode 810 with reward 200.000 in 200 steps +2023-06-23 22:36:54 - SimpleLog - INFO: - Interactor 0 finished episode 811 with reward 200.000 in 200 steps +2023-06-23 22:36:54 - SimpleLog - INFO: - Interactor 0 finished episode 812 with reward 200.000 in 200 steps +2023-06-23 22:36:55 - SimpleLog - INFO: - Interactor 1 finished episode 813 with reward 200.000 in 200 steps +2023-06-23 22:36:55 - SimpleLog - INFO: - Interactor 0 finished episode 814 with reward 200.000 in 200 steps +2023-06-23 22:36:55 - SimpleLog - INFO: - Interactor 1 finished episode 815 with reward 200.000 in 200 steps +2023-06-23 22:36:55 - SimpleLog - INFO: - Interactor 1 finished episode 816 with reward 200.000 in 200 steps +2023-06-23 22:36:55 - SimpleLog - INFO: - Interactor 0 finished episode 817 with reward 200.000 in 200 steps +2023-06-23 22:36:55 - SimpleLog - INFO: - Interactor 1 finished episode 818 with reward 200.000 in 200 steps +2023-06-23 22:36:56 - SimpleLog - INFO: - update_step: 490, online_eval_reward: 200.000 +2023-06-23 22:36:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:56 - SimpleLog - INFO: - Interactor 0 finished episode 819 with reward 200.000 in 200 steps +2023-06-23 22:36:56 - SimpleLog - INFO: - Interactor 0 finished episode 820 with reward 200.000 in 200 steps +2023-06-23 22:36:56 - SimpleLog - INFO: - Interactor 1 finished episode 821 with reward 200.000 in 200 steps +2023-06-23 22:36:56 - SimpleLog - INFO: - Interactor 0 finished episode 822 with reward 200.000 in 200 steps +2023-06-23 22:36:56 - SimpleLog - INFO: - Interactor 1 finished episode 823 with reward 200.000 in 200 steps +2023-06-23 22:36:56 - SimpleLog - INFO: - Interactor 1 finished episode 824 with reward 200.000 in 200 steps +2023-06-23 22:36:57 - SimpleLog - INFO: - Interactor 0 finished episode 825 with reward 200.000 in 200 steps +2023-06-23 22:36:57 - SimpleLog - INFO: - Interactor 1 finished episode 826 with reward 200.000 in 200 steps +2023-06-23 22:36:57 - SimpleLog - INFO: - Interactor 0 finished episode 827 with reward 200.000 in 200 steps +2023-06-23 22:36:57 - SimpleLog - INFO: - Interactor 1 finished episode 828 with reward 200.000 in 200 steps +2023-06-23 22:36:57 - SimpleLog - INFO: - Interactor 0 finished episode 829 with reward 200.000 in 200 steps +2023-06-23 22:36:57 - SimpleLog - INFO: - Interactor 0 finished episode 830 with reward 200.000 in 200 steps +2023-06-23 22:36:57 - SimpleLog - INFO: - Interactor 1 finished episode 831 with reward 200.000 in 200 steps +2023-06-23 22:36:58 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 200.000 +2023-06-23 22:36:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:36:58 - SimpleLog - INFO: - Interactor 0 finished episode 832 with reward 200.000 in 200 steps +2023-06-23 22:36:58 - SimpleLog - INFO: - Interactor 1 finished episode 833 with reward 200.000 in 200 steps +2023-06-23 22:36:58 - SimpleLog - INFO: - Interactor 1 finished episode 834 with reward 200.000 in 200 steps +2023-06-23 22:36:58 - SimpleLog - INFO: - Interactor 0 finished episode 835 with reward 200.000 in 200 steps +2023-06-23 22:36:58 - SimpleLog - INFO: - Interactor 1 finished episode 836 with reward 75.000 in 75 steps +2023-06-23 22:36:58 - SimpleLog - INFO: - Interactor 1 finished episode 837 with reward 200.000 in 200 steps +2023-06-23 22:36:59 - SimpleLog - INFO: - Interactor 0 finished episode 838 with reward 200.000 in 200 steps +2023-06-23 22:36:59 - SimpleLog - INFO: - Interactor 0 finished episode 839 with reward 200.000 in 200 steps +2023-06-23 22:36:59 - SimpleLog - INFO: - Interactor 1 finished episode 840 with reward 200.000 in 200 steps +2023-06-23 22:36:59 - SimpleLog - INFO: - Interactor 0 finished episode 841 with reward 200.000 in 200 steps +2023-06-23 22:36:59 - SimpleLog - INFO: - Interactor 1 finished episode 842 with reward 200.000 in 200 steps +2023-06-23 22:36:59 - SimpleLog - INFO: - Interactor 0 finished episode 843 with reward 200.000 in 200 steps +2023-06-23 22:36:59 - SimpleLog - INFO: - Interactor 1 finished episode 844 with reward 200.000 in 200 steps +2023-06-23 22:37:00 - SimpleLog - INFO: - update_step: 510, online_eval_reward: 200.000 +2023-06-23 22:37:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:00 - SimpleLog - INFO: - Interactor 0 finished episode 845 with reward 200.000 in 200 steps +2023-06-23 22:37:00 - SimpleLog - INFO: - Interactor 1 finished episode 846 with reward 200.000 in 200 steps +2023-06-23 22:37:00 - SimpleLog - INFO: - Interactor 1 finished episode 847 with reward 200.000 in 200 steps +2023-06-23 22:37:00 - SimpleLog - INFO: - Interactor 0 finished episode 848 with reward 200.000 in 200 steps +2023-06-23 22:37:00 - SimpleLog - INFO: - Interactor 0 finished episode 849 with reward 200.000 in 200 steps +2023-06-23 22:37:00 - SimpleLog - INFO: - Interactor 1 finished episode 850 with reward 200.000 in 200 steps +2023-06-23 22:37:01 - SimpleLog - INFO: - Interactor 0 finished episode 851 with reward 200.000 in 200 steps +2023-06-23 22:37:01 - SimpleLog - INFO: - Interactor 1 finished episode 852 with reward 200.000 in 200 steps +2023-06-23 22:37:01 - SimpleLog - INFO: - Interactor 0 finished episode 853 with reward 200.000 in 200 steps +2023-06-23 22:37:01 - SimpleLog - INFO: - Interactor 1 finished episode 854 with reward 200.000 in 200 steps +2023-06-23 22:37:01 - SimpleLog - INFO: - Interactor 1 finished episode 855 with reward 200.000 in 200 steps +2023-06-23 22:37:01 - SimpleLog - INFO: - Interactor 0 finished episode 856 with reward 200.000 in 200 steps +2023-06-23 22:37:01 - SimpleLog - INFO: - Interactor 0 finished episode 857 with reward 200.000 in 200 steps +2023-06-23 22:37:02 - SimpleLog - INFO: - Interactor 1 finished episode 858 with reward 200.000 in 200 steps +2023-06-23 22:37:02 - SimpleLog - INFO: - update_step: 520, online_eval_reward: 200.000 +2023-06-23 22:37:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:02 - SimpleLog - INFO: - Interactor 0 finished episode 859 with reward 200.000 in 200 steps +2023-06-23 22:37:02 - SimpleLog - INFO: - Interactor 1 finished episode 860 with reward 200.000 in 200 steps +2023-06-23 22:37:02 - SimpleLog - INFO: - Interactor 0 finished episode 861 with reward 200.000 in 200 steps +2023-06-23 22:37:03 - SimpleLog - INFO: - Interactor 1 finished episode 862 with reward 200.000 in 200 steps +2023-06-23 22:37:03 - SimpleLog - INFO: - Interactor 0 finished episode 863 with reward 200.000 in 200 steps +2023-06-23 22:37:03 - SimpleLog - INFO: - Interactor 1 finished episode 864 with reward 200.000 in 200 steps +2023-06-23 22:37:03 - SimpleLog - INFO: - Interactor 1 finished episode 865 with reward 200.000 in 200 steps +2023-06-23 22:37:03 - SimpleLog - INFO: - Interactor 0 finished episode 866 with reward 200.000 in 200 steps +2023-06-23 22:37:03 - SimpleLog - INFO: - Interactor 0 finished episode 867 with reward 200.000 in 200 steps +2023-06-23 22:37:03 - SimpleLog - INFO: - Interactor 1 finished episode 868 with reward 200.000 in 200 steps +2023-06-23 22:37:04 - SimpleLog - INFO: - Interactor 0 finished episode 869 with reward 200.000 in 200 steps +2023-06-23 22:37:04 - SimpleLog - INFO: - Interactor 1 finished episode 870 with reward 200.000 in 200 steps +2023-06-23 22:37:04 - SimpleLog - INFO: - update_step: 530, online_eval_reward: 200.000 +2023-06-23 22:37:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:04 - SimpleLog - INFO: - Interactor 0 finished episode 871 with reward 200.000 in 200 steps +2023-06-23 22:37:04 - SimpleLog - INFO: - Interactor 1 finished episode 872 with reward 200.000 in 200 steps +2023-06-23 22:37:05 - SimpleLog - INFO: - Interactor 0 finished episode 873 with reward 200.000 in 200 steps +2023-06-23 22:37:05 - SimpleLog - INFO: - Interactor 1 finished episode 874 with reward 200.000 in 200 steps +2023-06-23 22:37:05 - SimpleLog - INFO: - Interactor 1 finished episode 875 with reward 200.000 in 200 steps +2023-06-23 22:37:05 - SimpleLog - INFO: - Interactor 0 finished episode 876 with reward 200.000 in 200 steps +2023-06-23 22:37:05 - SimpleLog - INFO: - Interactor 0 finished episode 877 with reward 200.000 in 200 steps +2023-06-23 22:37:05 - SimpleLog - INFO: - Interactor 1 finished episode 878 with reward 200.000 in 200 steps +2023-06-23 22:37:05 - SimpleLog - INFO: - Interactor 0 finished episode 879 with reward 200.000 in 200 steps +2023-06-23 22:37:05 - SimpleLog - INFO: - Interactor 1 finished episode 880 with reward 200.000 in 200 steps +2023-06-23 22:37:06 - SimpleLog - INFO: - Interactor 0 finished episode 881 with reward 200.000 in 200 steps +2023-06-23 22:37:06 - SimpleLog - INFO: - Interactor 1 finished episode 882 with reward 200.000 in 200 steps +2023-06-23 22:37:06 - SimpleLog - INFO: - Interactor 1 finished episode 883 with reward 200.000 in 200 steps +2023-06-23 22:37:06 - SimpleLog - INFO: - update_step: 540, online_eval_reward: 200.000 +2023-06-23 22:37:06 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:06 - SimpleLog - INFO: - Interactor 0 finished episode 884 with reward 200.000 in 200 steps +2023-06-23 22:37:06 - SimpleLog - INFO: - Interactor 0 finished episode 885 with reward 200.000 in 200 steps +2023-06-23 22:37:07 - SimpleLog - INFO: - Interactor 1 finished episode 886 with reward 200.000 in 200 steps +2023-06-23 22:37:07 - SimpleLog - INFO: - Interactor 0 finished episode 887 with reward 200.000 in 200 steps +2023-06-23 22:37:07 - SimpleLog - INFO: - Interactor 1 finished episode 888 with reward 200.000 in 200 steps +2023-06-23 22:37:07 - SimpleLog - INFO: - Interactor 0 finished episode 889 with reward 200.000 in 200 steps +2023-06-23 22:37:07 - SimpleLog - INFO: - Interactor 1 finished episode 890 with reward 200.000 in 200 steps +2023-06-23 22:37:07 - SimpleLog - INFO: - Interactor 0 finished episode 891 with reward 200.000 in 200 steps +2023-06-23 22:37:07 - SimpleLog - INFO: - Interactor 1 finished episode 892 with reward 200.000 in 200 steps +2023-06-23 22:37:07 - SimpleLog - INFO: - Interactor 1 finished episode 893 with reward 200.000 in 200 steps +2023-06-23 22:37:08 - SimpleLog - INFO: - Interactor 0 finished episode 894 with reward 200.000 in 200 steps +2023-06-23 22:37:08 - SimpleLog - INFO: - Interactor 0 finished episode 895 with reward 200.000 in 200 steps +2023-06-23 22:37:08 - SimpleLog - INFO: - Interactor 1 finished episode 896 with reward 200.000 in 200 steps +2023-06-23 22:37:08 - SimpleLog - INFO: - update_step: 550, online_eval_reward: 200.000 +2023-06-23 22:37:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:08 - SimpleLog - INFO: - Interactor 0 finished episode 897 with reward 200.000 in 200 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 1 finished episode 898 with reward 200.000 in 200 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 0 finished episode 899 with reward 200.000 in 200 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 0 finished episode 900 with reward 115.000 in 115 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 1 finished episode 901 with reward 200.000 in 200 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 1 finished episode 902 with reward 200.000 in 200 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 0 finished episode 903 with reward 200.000 in 200 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 0 finished episode 904 with reward 58.000 in 58 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 1 finished episode 905 with reward 200.000 in 200 steps +2023-06-23 22:37:09 - SimpleLog - INFO: - Interactor 0 finished episode 906 with reward 200.000 in 200 steps +2023-06-23 22:37:10 - SimpleLog - INFO: - Interactor 1 finished episode 907 with reward 200.000 in 200 steps +2023-06-23 22:37:10 - SimpleLog - INFO: - Interactor 0 finished episode 908 with reward 200.000 in 200 steps +2023-06-23 22:37:10 - SimpleLog - INFO: - Interactor 0 finished episode 909 with reward 73.000 in 73 steps +2023-06-23 22:37:10 - SimpleLog - INFO: - Interactor 0 finished episode 910 with reward 71.000 in 71 steps +2023-06-23 22:37:10 - SimpleLog - INFO: - Interactor 1 finished episode 911 with reward 200.000 in 200 steps +2023-06-23 22:37:10 - SimpleLog - INFO: - update_step: 560, online_eval_reward: 200.000 +2023-06-23 22:37:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 0 finished episode 912 with reward 200.000 in 200 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 1 finished episode 913 with reward 200.000 in 200 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 1 finished episode 914 with reward 80.000 in 80 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 0 finished episode 915 with reward 69.000 in 69 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 0 finished episode 916 with reward 68.000 in 68 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 1 finished episode 917 with reward 200.000 in 200 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 1 finished episode 918 with reward 171.000 in 171 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 0 finished episode 919 with reward 200.000 in 200 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 0 finished episode 920 with reward 68.000 in 68 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 1 finished episode 921 with reward 200.000 in 200 steps +2023-06-23 22:37:11 - SimpleLog - INFO: - Interactor 1 finished episode 922 with reward 75.000 in 75 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 0 finished episode 923 with reward 200.000 in 200 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 0 finished episode 924 with reward 70.000 in 70 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 0 finished episode 925 with reward 25.000 in 25 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 0 finished episode 926 with reward 70.000 in 70 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 0 finished episode 927 with reward 21.000 in 21 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 1 finished episode 928 with reward 77.000 in 77 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 0 finished episode 929 with reward 200.000 in 200 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 0 finished episode 930 with reward 77.000 in 77 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 1 finished episode 931 with reward 200.000 in 200 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 1 finished episode 932 with reward 25.000 in 25 steps +2023-06-23 22:37:12 - SimpleLog - INFO: - Interactor 1 finished episode 933 with reward 200.000 in 200 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - update_step: 570, online_eval_reward: 200.000 +2023-06-23 22:37:13 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 0 finished episode 934 with reward 200.000 in 200 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 1 finished episode 935 with reward 200.000 in 200 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 0 finished episode 936 with reward 76.000 in 76 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 0 finished episode 937 with reward 200.000 in 200 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 1 finished episode 938 with reward 200.000 in 200 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 0 finished episode 939 with reward 76.000 in 76 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 0 finished episode 940 with reward 24.000 in 24 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 0 finished episode 941 with reward 67.000 in 67 steps +2023-06-23 22:37:13 - SimpleLog - INFO: - Interactor 1 finished episode 942 with reward 200.000 in 200 steps +2023-06-23 22:37:14 - SimpleLog - INFO: - Interactor 0 finished episode 943 with reward 200.000 in 200 steps +2023-06-23 22:37:14 - SimpleLog - INFO: - Interactor 0 finished episode 944 with reward 200.000 in 200 steps +2023-06-23 22:37:14 - SimpleLog - INFO: - Interactor 1 finished episode 945 with reward 200.000 in 200 steps +2023-06-23 22:37:14 - SimpleLog - INFO: - Interactor 1 finished episode 946 with reward 200.000 in 200 steps +2023-06-23 22:37:14 - SimpleLog - INFO: - Interactor 0 finished episode 947 with reward 200.000 in 200 steps +2023-06-23 22:37:14 - SimpleLog - INFO: - Interactor 1 finished episode 948 with reward 200.000 in 200 steps +2023-06-23 22:37:15 - SimpleLog - INFO: - update_step: 580, online_eval_reward: 200.000 +2023-06-23 22:37:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:15 - SimpleLog - INFO: - Interactor 0 finished episode 949 with reward 200.000 in 200 steps +2023-06-23 22:37:15 - SimpleLog - INFO: - Interactor 1 finished episode 950 with reward 200.000 in 200 steps +2023-06-23 22:37:15 - SimpleLog - INFO: - Interactor 0 finished episode 951 with reward 200.000 in 200 steps +2023-06-23 22:37:15 - SimpleLog - INFO: - Interactor 1 finished episode 952 with reward 200.000 in 200 steps +2023-06-23 22:37:15 - SimpleLog - INFO: - Interactor 1 finished episode 953 with reward 200.000 in 200 steps +2023-06-23 22:37:15 - SimpleLog - INFO: - Interactor 0 finished episode 954 with reward 200.000 in 200 steps +2023-06-23 22:37:15 - SimpleLog - INFO: - Interactor 0 finished episode 955 with reward 200.000 in 200 steps +2023-06-23 22:37:16 - SimpleLog - INFO: - Interactor 1 finished episode 956 with reward 200.000 in 200 steps +2023-06-23 22:37:16 - SimpleLog - INFO: - Interactor 0 finished episode 957 with reward 200.000 in 200 steps +2023-06-23 22:37:16 - SimpleLog - INFO: - Interactor 0 finished episode 958 with reward 22.000 in 22 steps +2023-06-23 22:37:16 - SimpleLog - INFO: - Interactor 1 finished episode 959 with reward 200.000 in 200 steps +2023-06-23 22:37:16 - SimpleLog - INFO: - Interactor 0 finished episode 960 with reward 200.000 in 200 steps +2023-06-23 22:37:16 - SimpleLog - INFO: - Interactor 1 finished episode 961 with reward 200.000 in 200 steps +2023-06-23 22:37:17 - SimpleLog - INFO: - update_step: 590, online_eval_reward: 200.000 +2023-06-23 22:37:17 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:17 - SimpleLog - INFO: - Interactor 0 finished episode 962 with reward 200.000 in 200 steps +2023-06-23 22:37:17 - SimpleLog - INFO: - Interactor 0 finished episode 963 with reward 62.000 in 62 steps +2023-06-23 22:37:17 - SimpleLog - INFO: - Interactor 1 finished episode 964 with reward 200.000 in 200 steps +2023-06-23 22:37:17 - SimpleLog - INFO: - Interactor 1 finished episode 965 with reward 200.000 in 200 steps +2023-06-23 22:37:17 - SimpleLog - INFO: - Interactor 0 finished episode 966 with reward 200.000 in 200 steps +2023-06-23 22:37:17 - SimpleLog - INFO: - Interactor 1 finished episode 967 with reward 200.000 in 200 steps +2023-06-23 22:37:17 - SimpleLog - INFO: - Interactor 0 finished episode 968 with reward 200.000 in 200 steps +2023-06-23 22:37:18 - SimpleLog - INFO: - Interactor 0 finished episode 969 with reward 200.000 in 200 steps +2023-06-23 22:37:18 - SimpleLog - INFO: - Interactor 1 finished episode 970 with reward 200.000 in 200 steps +2023-06-23 22:37:18 - SimpleLog - INFO: - Interactor 0 finished episode 971 with reward 200.000 in 200 steps +2023-06-23 22:37:18 - SimpleLog - INFO: - Interactor 1 finished episode 972 with reward 200.000 in 200 steps +2023-06-23 22:37:18 - SimpleLog - INFO: - Interactor 1 finished episode 973 with reward 200.000 in 200 steps +2023-06-23 22:37:18 - SimpleLog - INFO: - Interactor 0 finished episode 974 with reward 200.000 in 200 steps +2023-06-23 22:37:18 - SimpleLog - INFO: - Interactor 1 finished episode 975 with reward 200.000 in 200 steps +2023-06-23 22:37:19 - SimpleLog - INFO: - update_step: 600, online_eval_reward: 200.000 +2023-06-23 22:37:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:19 - SimpleLog - INFO: - Interactor 0 finished episode 976 with reward 200.000 in 200 steps +2023-06-23 22:37:19 - SimpleLog - INFO: - Interactor 1 finished episode 977 with reward 200.000 in 200 steps +2023-06-23 22:37:19 - SimpleLog - INFO: - Interactor 0 finished episode 978 with reward 200.000 in 200 steps +2023-06-23 22:37:19 - SimpleLog - INFO: - Interactor 0 finished episode 979 with reward 23.000 in 23 steps +2023-06-23 22:37:19 - SimpleLog - INFO: - Interactor 0 finished episode 980 with reward 200.000 in 200 steps +2023-06-23 22:37:19 - SimpleLog - INFO: - Interactor 1 finished episode 981 with reward 200.000 in 200 steps +2023-06-23 22:37:20 - SimpleLog - INFO: - Interactor 0 finished episode 982 with reward 200.000 in 200 steps +2023-06-23 22:37:20 - SimpleLog - INFO: - Interactor 1 finished episode 983 with reward 200.000 in 200 steps +2023-06-23 22:37:20 - SimpleLog - INFO: - Interactor 1 finished episode 984 with reward 200.000 in 200 steps +2023-06-23 22:37:20 - SimpleLog - INFO: - Interactor 0 finished episode 985 with reward 200.000 in 200 steps +2023-06-23 22:37:20 - SimpleLog - INFO: - Interactor 1 finished episode 986 with reward 79.000 in 79 steps +2023-06-23 22:37:20 - SimpleLog - INFO: - Interactor 1 finished episode 987 with reward 200.000 in 200 steps +2023-06-23 22:37:20 - SimpleLog - INFO: - Interactor 0 finished episode 988 with reward 200.000 in 200 steps +2023-06-23 22:37:20 - SimpleLog - INFO: - Interactor 1 finished episode 989 with reward 200.000 in 200 steps +2023-06-23 22:37:21 - SimpleLog - INFO: - update_step: 610, online_eval_reward: 200.000 +2023-06-23 22:37:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-23 22:37:21 - SimpleLog - INFO: - Interactor 0 finished episode 990 with reward 200.000 in 200 steps +2023-06-23 22:37:21 - SimpleLog - INFO: - Interactor 0 finished episode 991 with reward 200.000 in 200 steps +2023-06-23 22:37:21 - SimpleLog - INFO: - Interactor 1 finished episode 992 with reward 200.000 in 200 steps +2023-06-23 22:37:21 - SimpleLog - INFO: - Interactor 0 finished episode 993 with reward 200.000 in 200 steps +2023-06-23 22:37:22 - SimpleLog - INFO: - Interactor 1 finished episode 994 with reward 200.000 in 200 steps +2023-06-23 22:37:22 - SimpleLog - INFO: - Interactor 0 finished episode 995 with reward 200.000 in 200 steps +2023-06-23 22:37:22 - SimpleLog - INFO: - Interactor 1 finished episode 996 with reward 200.000 in 200 steps +2023-06-23 22:37:22 - SimpleLog - INFO: - Interactor 1 finished episode 997 with reward 200.000 in 200 steps +2023-06-23 22:37:22 - SimpleLog - INFO: - Interactor 0 finished episode 998 with reward 200.000 in 200 steps +2023-06-23 22:37:22 - SimpleLog - INFO: - Interactor 0 finished episode 999 with reward 200.000 in 200 steps +2023-06-23 22:37:22 - SimpleLog - INFO: - Interactor 1 finished episode 1000 with reward 200.000 in 200 steps +2023-06-23 22:37:22 - SimpleLog - INFO: - Finish training! Time cost: 127.441 s