diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/config.yaml b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b9e2a3f2f5345963ac79ca6f5eab53d2b525967b --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/config.yaml @@ -0,0 +1,81 @@ +general_cfg: + algo_name: SAC + collect_traj: false + device: cpu + env_name: gym + interact_summary_fre: 1 + load_checkpoint: true + load_model_step: best + load_path: Train_CartPole-v1_SAC_20230618-162702 + max_episode: 200 + max_step: 200 + mode: test + model_save_fre: 100 + model_summary_fre: 1 + mp_backend: single + n_learners: 1 + n_workers: 2 + online_eval: true + online_eval_episode: 10 + seed: 1 + share_buffer: true +algo_cfg: + action_type: discrete + actor_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear + actor_lr: 0.0003 + alpha: 0.1 + alpha_lr: 0.0001 + automatic_entropy_tuning: false + batch_size: 64 + buffer_size: 1000000 + buffer_type: REPLAY_QUE + critic1_lr: 0.001 + critic2_lr: 0.001 + critic_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear + epsilon_decay: 500 + epsilon_end: 0.01 + epsilon_start: 0.95 + gamma: 0.95 + hidden_dim: 64 + independ_actor: true + lr: 0.0001 + min_policy: 0 + n_epochs: 1 + n_steps_per_learn: 1 + share_optimizer: false + start_steps: 10000 + target_update: 1 + target_update_fre: 1 + tau: 0.005 + value_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear +env_cfg: + id: CartPole-v1 + ignore_params: + - wrapper + - ignore_params + render_mode: null + wrapper: null diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/logs/log.txt b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..b5985305ca46753d5626d47282881e8e5e261a43 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/logs/log.txt @@ -0,0 +1,639 @@ +2023-06-18 16:32:19 - SimpleLog - INFO: - General Configs: +2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:32:19 - SimpleLog - INFO: - Name Value Type +2023-06-18 16:32:19 - SimpleLog - INFO: - env_name gym +2023-06-18 16:32:19 - SimpleLog - INFO: - algo_name SAC +2023-06-18 16:32:19 - SimpleLog - INFO: - mode test +2023-06-18 16:32:19 - SimpleLog - INFO: - device cpu +2023-06-18 16:32:19 - SimpleLog - INFO: - seed 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - max_episode 200 +2023-06-18 16:32:19 - SimpleLog - INFO: - max_step 200 +2023-06-18 16:32:19 - SimpleLog - INFO: - collect_traj 0 +2023-06-18 16:32:19 - SimpleLog - INFO: - mp_backend single +2023-06-18 16:32:19 - SimpleLog - INFO: - n_workers 2 +2023-06-18 16:32:19 - SimpleLog - INFO: - n_learners 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - share_buffer 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - online_eval 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - online_eval_episode 10 +2023-06-18 16:32:19 - SimpleLog - INFO: - model_save_fre 100 +2023-06-18 16:32:19 - SimpleLog - INFO: - load_checkpoint 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - load_path Train_CartPole-v1_SAC_20230618-162702 +2023-06-18 16:32:19 - SimpleLog - INFO: - load_model_step best +2023-06-18 16:32:19 - SimpleLog - INFO: - interact_summary_fre 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - model_summary_fre 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:32:19 - SimpleLog - INFO: - Algo Configs: +2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:32:19 - SimpleLog - INFO: - Name Value Type +2023-06-18 16:32:19 - SimpleLog - INFO: - critic1_lr 0.001 +2023-06-18 16:32:19 - SimpleLog - INFO: - critic2_lr 0.001 +2023-06-18 16:32:19 - SimpleLog - INFO: - actor_lr 0.0003 +2023-06-18 16:32:19 - SimpleLog - INFO: - gamma 0.95 +2023-06-18 16:32:19 - SimpleLog - INFO: - tau 0.005 +2023-06-18 16:32:19 - SimpleLog - INFO: - alpha 0.1 +2023-06-18 16:32:19 - SimpleLog - INFO: - automatic_entropy_tuning 0 +2023-06-18 16:32:19 - SimpleLog - INFO: - batch_size 64 +2023-06-18 16:32:19 - SimpleLog - INFO: - hidden_dim 64 +2023-06-18 16:32:19 - SimpleLog - INFO: - n_epochs 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - start_steps 10000 +2023-06-18 16:32:19 - SimpleLog - INFO: - target_update_fre 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - buffer_size 1000000 +2023-06-18 16:32:19 - SimpleLog - INFO: - min_policy 0 +2023-06-18 16:32:19 - SimpleLog - INFO: - alpha_lr 0.0001 +2023-06-18 16:32:19 - SimpleLog - INFO: - n_steps_per_learn 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - action_type discrete +2023-06-18 16:32:19 - SimpleLog - INFO: - independ_actor 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - share_optimizer 0 +2023-06-18 16:32:19 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-06-18 16:32:19 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-06-18 16:32:19 - SimpleLog - INFO: - value_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-06-18 16:32:19 - SimpleLog - INFO: - buffer_type REPLAY_QUE +2023-06-18 16:32:19 - SimpleLog - INFO: - epsilon_decay 500 +2023-06-18 16:32:19 - SimpleLog - INFO: - epsilon_end 0.01 +2023-06-18 16:32:19 - SimpleLog - INFO: - epsilon_start 0.95 +2023-06-18 16:32:19 - SimpleLog - INFO: - lr 0.0001 +2023-06-18 16:32:19 - SimpleLog - INFO: - target_update 1 +2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:32:19 - SimpleLog - INFO: - Env Configs: +2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:32:19 - SimpleLog - INFO: - Name Value Type +2023-06-18 16:32:19 - SimpleLog - INFO: - id CartPole-v1 +2023-06-18 16:32:19 - SimpleLog - INFO: - render_mode None +2023-06-18 16:32:19 - SimpleLog - INFO: - wrapper None +2023-06-18 16:32:19 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:32:19 - SimpleLog - INFO: - Start testing! +2023-06-18 16:32:21 - SimpleLog - INFO: - update_step: 100, online_eval_reward: 200.000 +2023-06-18 16:32:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:21 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward 199.000 in 199 steps +2023-06-18 16:32:21 - SimpleLog - INFO: - Interactor 1 finished episode 2 with reward 200.000 in 200 steps +2023-06-18 16:32:22 - SimpleLog - INFO: - update_step: 200, online_eval_reward: 200.000 +2023-06-18 16:32:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:23 - SimpleLog - INFO: - update_step: 300, online_eval_reward: 200.000 +2023-06-18 16:32:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:23 - SimpleLog - INFO: - Interactor 1 finished episode 3 with reward 149.000 in 149 steps +2023-06-18 16:32:23 - SimpleLog - INFO: - Interactor 0 finished episode 4 with reward 167.000 in 167 steps +2023-06-18 16:32:24 - SimpleLog - INFO: - update_step: 400, online_eval_reward: 184.000 +2023-06-18 16:32:25 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 200.000 +2023-06-18 16:32:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:25 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 169.000 in 169 steps +2023-06-18 16:32:26 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward 200.000 in 200 steps +2023-06-18 16:32:27 - SimpleLog - INFO: - update_step: 600, online_eval_reward: 200.000 +2023-06-18 16:32:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:27 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward 111.000 in 111 steps +2023-06-18 16:32:28 - SimpleLog - INFO: - update_step: 700, online_eval_reward: 200.000 +2023-06-18 16:32:28 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:28 - SimpleLog - INFO: - Interactor 1 finished episode 8 with reward 200.000 in 200 steps +2023-06-18 16:32:28 - SimpleLog - INFO: - Interactor 0 finished episode 9 with reward 129.000 in 129 steps +2023-06-18 16:32:29 - SimpleLog - INFO: - update_step: 800, online_eval_reward: 200.000 +2023-06-18 16:32:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:30 - SimpleLog - INFO: - update_step: 900, online_eval_reward: 200.000 +2023-06-18 16:32:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:30 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward 200.000 in 200 steps +2023-06-18 16:32:30 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward 200.000 in 200 steps +2023-06-18 16:32:31 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 200.000 +2023-06-18 16:32:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:32 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward 137.000 in 137 steps +2023-06-18 16:32:33 - SimpleLog - INFO: - update_step: 1100, online_eval_reward: 200.000 +2023-06-18 16:32:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:33 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward 182.000 in 182 steps +2023-06-18 16:32:34 - SimpleLog - INFO: - update_step: 1200, online_eval_reward: 200.000 +2023-06-18 16:32:34 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:34 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward 163.000 in 163 steps +2023-06-18 16:32:34 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward 157.000 in 157 steps +2023-06-18 16:32:35 - SimpleLog - INFO: - update_step: 1300, online_eval_reward: 200.000 +2023-06-18 16:32:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:36 - SimpleLog - INFO: - update_step: 1400, online_eval_reward: 200.000 +2023-06-18 16:32:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:36 - SimpleLog - INFO: - Interactor 0 finished episode 16 with reward 131.000 in 131 steps +2023-06-18 16:32:36 - SimpleLog - INFO: - Interactor 1 finished episode 17 with reward 200.000 in 200 steps +2023-06-18 16:32:37 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 200.000 +2023-06-18 16:32:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:39 - SimpleLog - INFO: - update_step: 1600, online_eval_reward: 200.000 +2023-06-18 16:32:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:39 - SimpleLog - INFO: - Interactor 0 finished episode 18 with reward 200.000 in 200 steps +2023-06-18 16:32:39 - SimpleLog - INFO: - Interactor 1 finished episode 19 with reward 200.000 in 200 steps +2023-06-18 16:32:40 - SimpleLog - INFO: - update_step: 1700, online_eval_reward: 200.000 +2023-06-18 16:32:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:41 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward 173.000 in 173 steps +2023-06-18 16:32:41 - SimpleLog - INFO: - update_step: 1800, online_eval_reward: 200.000 +2023-06-18 16:32:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:41 - SimpleLog - INFO: - Interactor 0 finished episode 21 with reward 200.000 in 200 steps +2023-06-18 16:32:42 - SimpleLog - INFO: - update_step: 1900, online_eval_reward: 200.000 +2023-06-18 16:32:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:43 - SimpleLog - INFO: - Interactor 1 finished episode 22 with reward 170.000 in 170 steps +2023-06-18 16:32:43 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: 200.000 +2023-06-18 16:32:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:44 - SimpleLog - INFO: - Interactor 0 finished episode 23 with reward 196.000 in 196 steps +2023-06-18 16:32:45 - SimpleLog - INFO: - update_step: 2100, online_eval_reward: 200.000 +2023-06-18 16:32:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:45 - SimpleLog - INFO: - Interactor 1 finished episode 24 with reward 153.000 in 153 steps +2023-06-18 16:32:45 - SimpleLog - INFO: - Interactor 0 finished episode 25 with reward 186.000 in 186 steps +2023-06-18 16:32:46 - SimpleLog - INFO: - update_step: 2200, online_eval_reward: 200.000 +2023-06-18 16:32:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:47 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward 178.000 in 178 steps +2023-06-18 16:32:47 - SimpleLog - INFO: - update_step: 2300, online_eval_reward: 200.000 +2023-06-18 16:32:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:48 - SimpleLog - INFO: - Interactor 0 finished episode 27 with reward 182.000 in 182 steps +2023-06-18 16:32:48 - SimpleLog - INFO: - update_step: 2400, online_eval_reward: 200.000 +2023-06-18 16:32:48 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:49 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward 200.000 in 200 steps +2023-06-18 16:32:49 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 200.000 +2023-06-18 16:32:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:50 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward 162.000 in 162 steps +2023-06-18 16:32:51 - SimpleLog - INFO: - update_step: 2600, online_eval_reward: 200.000 +2023-06-18 16:32:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:51 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward 140.000 in 140 steps +2023-06-18 16:32:52 - SimpleLog - INFO: - update_step: 2700, online_eval_reward: 200.000 +2023-06-18 16:32:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:52 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward 200.000 in 200 steps +2023-06-18 16:32:53 - SimpleLog - INFO: - update_step: 2800, online_eval_reward: 200.000 +2023-06-18 16:32:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:53 - SimpleLog - INFO: - Interactor 1 finished episode 32 with reward 200.000 in 200 steps +2023-06-18 16:32:54 - SimpleLog - INFO: - update_step: 2900, online_eval_reward: 200.000 +2023-06-18 16:32:54 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:55 - SimpleLog - INFO: - Interactor 0 finished episode 33 with reward 200.000 in 200 steps +2023-06-18 16:32:55 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: 200.000 +2023-06-18 16:32:55 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:56 - SimpleLog - INFO: - Interactor 1 finished episode 34 with reward 200.000 in 200 steps +2023-06-18 16:32:57 - SimpleLog - INFO: - update_step: 3100, online_eval_reward: 200.000 +2023-06-18 16:32:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:57 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward 200.000 in 200 steps +2023-06-18 16:32:58 - SimpleLog - INFO: - Interactor 1 finished episode 36 with reward 166.000 in 166 steps +2023-06-18 16:32:58 - SimpleLog - INFO: - update_step: 3200, online_eval_reward: 200.000 +2023-06-18 16:32:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:59 - SimpleLog - INFO: - update_step: 3300, online_eval_reward: 200.000 +2023-06-18 16:32:59 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:32:59 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward 168.000 in 168 steps +2023-06-18 16:33:00 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward 160.000 in 160 steps +2023-06-18 16:33:00 - SimpleLog - INFO: - update_step: 3400, online_eval_reward: 200.000 +2023-06-18 16:33:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:02 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: 200.000 +2023-06-18 16:33:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:02 - SimpleLog - INFO: - Interactor 0 finished episode 39 with reward 200.000 in 200 steps +2023-06-18 16:33:02 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward 165.000 in 165 steps +2023-06-18 16:33:03 - SimpleLog - INFO: - update_step: 3600, online_eval_reward: 200.000 +2023-06-18 16:33:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:04 - SimpleLog - INFO: - update_step: 3700, online_eval_reward: 200.000 +2023-06-18 16:33:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:04 - SimpleLog - INFO: - Interactor 0 finished episode 41 with reward 200.000 in 200 steps +2023-06-18 16:33:04 - SimpleLog - INFO: - Interactor 1 finished episode 42 with reward 185.000 in 185 steps +2023-06-18 16:33:05 - SimpleLog - INFO: - update_step: 3800, online_eval_reward: 200.000 +2023-06-18 16:33:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:06 - SimpleLog - INFO: - Interactor 0 finished episode 43 with reward 131.000 in 131 steps +2023-06-18 16:33:07 - SimpleLog - INFO: - update_step: 3900, online_eval_reward: 200.000 +2023-06-18 16:33:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:07 - SimpleLog - INFO: - Interactor 1 finished episode 44 with reward 200.000 in 200 steps +2023-06-18 16:33:08 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: 200.000 +2023-06-18 16:33:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:08 - SimpleLog - INFO: - Interactor 0 finished episode 45 with reward 190.000 in 190 steps +2023-06-18 16:33:09 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward 183.000 in 183 steps +2023-06-18 16:33:09 - SimpleLog - INFO: - update_step: 4100, online_eval_reward: 200.000 +2023-06-18 16:33:09 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:10 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward 127.000 in 127 steps +2023-06-18 16:33:10 - SimpleLog - INFO: - update_step: 4200, online_eval_reward: 200.000 +2023-06-18 16:33:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:11 - SimpleLog - INFO: - Interactor 1 finished episode 48 with reward 200.000 in 200 steps +2023-06-18 16:33:12 - SimpleLog - INFO: - update_step: 4300, online_eval_reward: 200.000 +2023-06-18 16:33:12 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:12 - SimpleLog - INFO: - Interactor 0 finished episode 49 with reward 188.000 in 188 steps +2023-06-18 16:33:13 - SimpleLog - INFO: - update_step: 4400, online_eval_reward: 200.000 +2023-06-18 16:33:13 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:13 - SimpleLog - INFO: - Interactor 1 finished episode 50 with reward 159.000 in 159 steps +2023-06-18 16:33:14 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: 200.000 +2023-06-18 16:33:14 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:14 - SimpleLog - INFO: - Interactor 0 finished episode 51 with reward 200.000 in 200 steps +2023-06-18 16:33:15 - SimpleLog - INFO: - Interactor 1 finished episode 52 with reward 137.000 in 137 steps +2023-06-18 16:33:15 - SimpleLog - INFO: - update_step: 4600, online_eval_reward: 200.000 +2023-06-18 16:33:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:16 - SimpleLog - INFO: - update_step: 4700, online_eval_reward: 200.000 +2023-06-18 16:33:16 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:17 - SimpleLog - INFO: - Interactor 0 finished episode 53 with reward 200.000 in 200 steps +2023-06-18 16:33:17 - SimpleLog - INFO: - Interactor 1 finished episode 54 with reward 190.000 in 190 steps +2023-06-18 16:33:18 - SimpleLog - INFO: - update_step: 4800, online_eval_reward: 200.000 +2023-06-18 16:33:18 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:19 - SimpleLog - INFO: - update_step: 4900, online_eval_reward: 200.000 +2023-06-18 16:33:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:19 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward 200.000 in 200 steps +2023-06-18 16:33:19 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward 200.000 in 200 steps +2023-06-18 16:33:20 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: 200.000 +2023-06-18 16:33:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:21 - SimpleLog - INFO: - update_step: 5100, online_eval_reward: 200.000 +2023-06-18 16:33:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:22 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward 200.000 in 200 steps +2023-06-18 16:33:22 - SimpleLog - INFO: - Interactor 1 finished episode 58 with reward 200.000 in 200 steps +2023-06-18 16:33:23 - SimpleLog - INFO: - update_step: 5200, online_eval_reward: 200.000 +2023-06-18 16:33:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:24 - SimpleLog - INFO: - update_step: 5300, online_eval_reward: 200.000 +2023-06-18 16:33:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:24 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward 162.000 in 162 steps +2023-06-18 16:33:24 - SimpleLog - INFO: - Interactor 1 finished episode 60 with reward 200.000 in 200 steps +2023-06-18 16:33:25 - SimpleLog - INFO: - update_step: 5400, online_eval_reward: 200.000 +2023-06-18 16:33:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:25 - SimpleLog - INFO: - Interactor 0 finished episode 61 with reward 155.000 in 155 steps +2023-06-18 16:33:26 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: 200.000 +2023-06-18 16:33:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:27 - SimpleLog - INFO: - Interactor 0 finished episode 62 with reward 100.000 in 100 steps +2023-06-18 16:33:27 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward 200.000 in 200 steps +2023-06-18 16:33:27 - SimpleLog - INFO: - update_step: 5600, online_eval_reward: 200.000 +2023-06-18 16:33:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:29 - SimpleLog - INFO: - update_step: 5700, online_eval_reward: 200.000 +2023-06-18 16:33:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:29 - SimpleLog - INFO: - Interactor 1 finished episode 64 with reward 157.000 in 157 steps +2023-06-18 16:33:29 - SimpleLog - INFO: - Interactor 0 finished episode 65 with reward 200.000 in 200 steps +2023-06-18 16:33:30 - SimpleLog - INFO: - update_step: 5800, online_eval_reward: 200.000 +2023-06-18 16:33:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:31 - SimpleLog - INFO: - Interactor 1 finished episode 66 with reward 158.000 in 158 steps +2023-06-18 16:33:31 - SimpleLog - INFO: - update_step: 5900, online_eval_reward: 200.000 +2023-06-18 16:33:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:32 - SimpleLog - INFO: - Interactor 0 finished episode 67 with reward 189.000 in 189 steps +2023-06-18 16:33:32 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: 200.000 +2023-06-18 16:33:32 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:33 - SimpleLog - INFO: - Interactor 1 finished episode 68 with reward 185.000 in 185 steps +2023-06-18 16:33:34 - SimpleLog - INFO: - update_step: 6100, online_eval_reward: 200.000 +2023-06-18 16:33:34 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:34 - SimpleLog - INFO: - Interactor 0 finished episode 69 with reward 200.000 in 200 steps +2023-06-18 16:33:35 - SimpleLog - INFO: - update_step: 6200, online_eval_reward: 200.000 +2023-06-18 16:33:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:35 - SimpleLog - INFO: - Interactor 1 finished episode 70 with reward 161.000 in 161 steps +2023-06-18 16:33:36 - SimpleLog - INFO: - update_step: 6300, online_eval_reward: 200.000 +2023-06-18 16:33:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:36 - SimpleLog - INFO: - Interactor 0 finished episode 71 with reward 151.000 in 151 steps +2023-06-18 16:33:37 - SimpleLog - INFO: - update_step: 6400, online_eval_reward: 200.000 +2023-06-18 16:33:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:38 - SimpleLog - INFO: - Interactor 1 finished episode 72 with reward 200.000 in 200 steps +2023-06-18 16:33:39 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: 200.000 +2023-06-18 16:33:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:39 - SimpleLog - INFO: - Interactor 0 finished episode 73 with reward 200.000 in 200 steps +2023-06-18 16:33:40 - SimpleLog - INFO: - update_step: 6600, online_eval_reward: 200.000 +2023-06-18 16:33:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:40 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward 185.000 in 185 steps +2023-06-18 16:33:41 - SimpleLog - INFO: - update_step: 6700, online_eval_reward: 200.000 +2023-06-18 16:33:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:41 - SimpleLog - INFO: - Interactor 0 finished episode 75 with reward 200.000 in 200 steps +2023-06-18 16:33:42 - SimpleLog - INFO: - Interactor 1 finished episode 76 with reward 168.000 in 168 steps +2023-06-18 16:33:42 - SimpleLog - INFO: - Interactor 0 finished episode 77 with reward 95.000 in 95 steps +2023-06-18 16:33:42 - SimpleLog - INFO: - update_step: 6800, online_eval_reward: 200.000 +2023-06-18 16:33:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:43 - SimpleLog - INFO: - update_step: 6900, online_eval_reward: 200.000 +2023-06-18 16:33:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:44 - SimpleLog - INFO: - Interactor 1 finished episode 78 with reward 200.000 in 200 steps +2023-06-18 16:33:44 - SimpleLog - INFO: - Interactor 0 finished episode 79 with reward 200.000 in 200 steps +2023-06-18 16:33:45 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: 200.000 +2023-06-18 16:33:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:46 - SimpleLog - INFO: - update_step: 7100, online_eval_reward: 200.000 +2023-06-18 16:33:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:47 - SimpleLog - INFO: - Interactor 1 finished episode 80 with reward 200.000 in 200 steps +2023-06-18 16:33:47 - SimpleLog - INFO: - Interactor 0 finished episode 81 with reward 199.000 in 199 steps +2023-06-18 16:33:47 - SimpleLog - INFO: - update_step: 7200, online_eval_reward: 200.000 +2023-06-18 16:33:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:48 - SimpleLog - INFO: - update_step: 7300, online_eval_reward: 200.000 +2023-06-18 16:33:48 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:49 - SimpleLog - INFO: - Interactor 1 finished episode 82 with reward 200.000 in 200 steps +2023-06-18 16:33:49 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward 200.000 in 200 steps +2023-06-18 16:33:50 - SimpleLog - INFO: - update_step: 7400, online_eval_reward: 200.000 +2023-06-18 16:33:50 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:51 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: 200.000 +2023-06-18 16:33:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:51 - SimpleLog - INFO: - Interactor 0 finished episode 84 with reward 195.000 in 195 steps +2023-06-18 16:33:51 - SimpleLog - INFO: - Interactor 1 finished episode 85 with reward 200.000 in 200 steps +2023-06-18 16:33:52 - SimpleLog - INFO: - update_step: 7600, online_eval_reward: 200.000 +2023-06-18 16:33:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:53 - SimpleLog - INFO: - update_step: 7700, online_eval_reward: 200.000 +2023-06-18 16:33:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:54 - SimpleLog - INFO: - Interactor 0 finished episode 86 with reward 182.000 in 182 steps +2023-06-18 16:33:54 - SimpleLog - INFO: - Interactor 1 finished episode 87 with reward 200.000 in 200 steps +2023-06-18 16:33:54 - SimpleLog - INFO: - update_step: 7800, online_eval_reward: 200.000 +2023-06-18 16:33:54 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:56 - SimpleLog - INFO: - update_step: 7900, online_eval_reward: 200.000 +2023-06-18 16:33:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:56 - SimpleLog - INFO: - Interactor 0 finished episode 88 with reward 194.000 in 194 steps +2023-06-18 16:33:56 - SimpleLog - INFO: - Interactor 1 finished episode 89 with reward 200.000 in 200 steps +2023-06-18 16:33:57 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: 200.000 +2023-06-18 16:33:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:58 - SimpleLog - INFO: - update_step: 8100, online_eval_reward: 200.000 +2023-06-18 16:33:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:33:58 - SimpleLog - INFO: - Interactor 0 finished episode 90 with reward 189.000 in 189 steps +2023-06-18 16:33:59 - SimpleLog - INFO: - Interactor 1 finished episode 91 with reward 200.000 in 200 steps +2023-06-18 16:33:59 - SimpleLog - INFO: - update_step: 8200, online_eval_reward: 200.000 +2023-06-18 16:33:59 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:00 - SimpleLog - INFO: - update_step: 8300, online_eval_reward: 200.000 +2023-06-18 16:34:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:01 - SimpleLog - INFO: - Interactor 0 finished episode 92 with reward 200.000 in 200 steps +2023-06-18 16:34:01 - SimpleLog - INFO: - Interactor 1 finished episode 93 with reward 175.000 in 175 steps +2023-06-18 16:34:02 - SimpleLog - INFO: - update_step: 8400, online_eval_reward: 200.000 +2023-06-18 16:34:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:03 - SimpleLog - INFO: - update_step: 8500, online_eval_reward: 200.000 +2023-06-18 16:34:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:03 - SimpleLog - INFO: - Interactor 0 finished episode 94 with reward 200.000 in 200 steps +2023-06-18 16:34:03 - SimpleLog - INFO: - Interactor 1 finished episode 95 with reward 200.000 in 200 steps +2023-06-18 16:34:04 - SimpleLog - INFO: - update_step: 8600, online_eval_reward: 200.000 +2023-06-18 16:34:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:05 - SimpleLog - INFO: - update_step: 8700, online_eval_reward: 200.000 +2023-06-18 16:34:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:06 - SimpleLog - INFO: - Interactor 0 finished episode 96 with reward 200.000 in 200 steps +2023-06-18 16:34:06 - SimpleLog - INFO: - Interactor 1 finished episode 97 with reward 200.000 in 200 steps +2023-06-18 16:34:06 - SimpleLog - INFO: - update_step: 8800, online_eval_reward: 200.000 +2023-06-18 16:34:06 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:08 - SimpleLog - INFO: - update_step: 8900, online_eval_reward: 200.000 +2023-06-18 16:34:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:08 - SimpleLog - INFO: - Interactor 0 finished episode 98 with reward 175.000 in 175 steps +2023-06-18 16:34:08 - SimpleLog - INFO: - Interactor 1 finished episode 99 with reward 200.000 in 200 steps +2023-06-18 16:34:09 - SimpleLog - INFO: - update_step: 9000, online_eval_reward: 200.000 +2023-06-18 16:34:09 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:10 - SimpleLog - INFO: - update_step: 9100, online_eval_reward: 200.000 +2023-06-18 16:34:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:10 - SimpleLog - INFO: - Interactor 0 finished episode 100 with reward 180.000 in 180 steps +2023-06-18 16:34:11 - SimpleLog - INFO: - Interactor 1 finished episode 101 with reward 200.000 in 200 steps +2023-06-18 16:34:11 - SimpleLog - INFO: - update_step: 9200, online_eval_reward: 200.000 +2023-06-18 16:34:11 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:13 - SimpleLog - INFO: - update_step: 9300, online_eval_reward: 200.000 +2023-06-18 16:34:13 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:13 - SimpleLog - INFO: - Interactor 0 finished episode 102 with reward 200.000 in 200 steps +2023-06-18 16:34:13 - SimpleLog - INFO: - Interactor 1 finished episode 103 with reward 200.000 in 200 steps +2023-06-18 16:34:14 - SimpleLog - INFO: - update_step: 9400, online_eval_reward: 200.000 +2023-06-18 16:34:14 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:14 - SimpleLog - INFO: - Interactor 0 finished episode 104 with reward 179.000 in 179 steps +2023-06-18 16:34:15 - SimpleLog - INFO: - update_step: 9500, online_eval_reward: 200.000 +2023-06-18 16:34:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:15 - SimpleLog - INFO: - Interactor 1 finished episode 105 with reward 191.000 in 191 steps +2023-06-18 16:34:16 - SimpleLog - INFO: - update_step: 9600, online_eval_reward: 200.000 +2023-06-18 16:34:16 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:17 - SimpleLog - INFO: - Interactor 0 finished episode 106 with reward 186.000 in 186 steps +2023-06-18 16:34:17 - SimpleLog - INFO: - update_step: 9700, online_eval_reward: 200.000 +2023-06-18 16:34:17 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:18 - SimpleLog - INFO: - Interactor 1 finished episode 107 with reward 186.000 in 186 steps +2023-06-18 16:34:19 - SimpleLog - INFO: - update_step: 9800, online_eval_reward: 200.000 +2023-06-18 16:34:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:19 - SimpleLog - INFO: - Interactor 0 finished episode 108 with reward 200.000 in 200 steps +2023-06-18 16:34:20 - SimpleLog - INFO: - update_step: 9900, online_eval_reward: 200.000 +2023-06-18 16:34:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:20 - SimpleLog - INFO: - Interactor 1 finished episode 109 with reward 200.000 in 200 steps +2023-06-18 16:34:21 - SimpleLog - INFO: - update_step: 10000, online_eval_reward: 200.000 +2023-06-18 16:34:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:22 - SimpleLog - INFO: - Interactor 0 finished episode 110 with reward 200.000 in 200 steps +2023-06-18 16:34:22 - SimpleLog - INFO: - update_step: 10100, online_eval_reward: 200.000 +2023-06-18 16:34:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:23 - SimpleLog - INFO: - Interactor 1 finished episode 111 with reward 200.000 in 200 steps +2023-06-18 16:34:24 - SimpleLog - INFO: - update_step: 10200, online_eval_reward: 200.000 +2023-06-18 16:34:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:24 - SimpleLog - INFO: - Interactor 0 finished episode 112 with reward 192.000 in 192 steps +2023-06-18 16:34:25 - SimpleLog - INFO: - update_step: 10300, online_eval_reward: 200.000 +2023-06-18 16:34:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:25 - SimpleLog - INFO: - Interactor 1 finished episode 113 with reward 200.000 in 200 steps +2023-06-18 16:34:26 - SimpleLog - INFO: - update_step: 10400, online_eval_reward: 200.000 +2023-06-18 16:34:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:26 - SimpleLog - INFO: - Interactor 0 finished episode 114 with reward 163.000 in 163 steps +2023-06-18 16:34:27 - SimpleLog - INFO: - update_step: 10500, online_eval_reward: 200.000 +2023-06-18 16:34:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:28 - SimpleLog - INFO: - Interactor 1 finished episode 115 with reward 200.000 in 200 steps +2023-06-18 16:34:29 - SimpleLog - INFO: - update_step: 10600, online_eval_reward: 200.000 +2023-06-18 16:34:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:29 - SimpleLog - INFO: - Interactor 0 finished episode 116 with reward 200.000 in 200 steps +2023-06-18 16:34:30 - SimpleLog - INFO: - update_step: 10700, online_eval_reward: 200.000 +2023-06-18 16:34:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:30 - SimpleLog - INFO: - Interactor 1 finished episode 117 with reward 160.000 in 160 steps +2023-06-18 16:34:31 - SimpleLog - INFO: - update_step: 10800, online_eval_reward: 200.000 +2023-06-18 16:34:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:31 - SimpleLog - INFO: - Interactor 0 finished episode 118 with reward 200.000 in 200 steps +2023-06-18 16:34:32 - SimpleLog - INFO: - update_step: 10900, online_eval_reward: 200.000 +2023-06-18 16:34:32 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:32 - SimpleLog - INFO: - Interactor 1 finished episode 119 with reward 200.000 in 200 steps +2023-06-18 16:34:33 - SimpleLog - INFO: - update_step: 11000, online_eval_reward: 200.000 +2023-06-18 16:34:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:34 - SimpleLog - INFO: - Interactor 0 finished episode 120 with reward 200.000 in 200 steps +2023-06-18 16:34:34 - SimpleLog - INFO: - Interactor 1 finished episode 121 with reward 182.000 in 182 steps +2023-06-18 16:34:35 - SimpleLog - INFO: - update_step: 11100, online_eval_reward: 200.000 +2023-06-18 16:34:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:36 - SimpleLog - INFO: - update_step: 11200, online_eval_reward: 200.000 +2023-06-18 16:34:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:36 - SimpleLog - INFO: - Interactor 0 finished episode 122 with reward 200.000 in 200 steps +2023-06-18 16:34:37 - SimpleLog - INFO: - Interactor 1 finished episode 123 with reward 200.000 in 200 steps +2023-06-18 16:34:37 - SimpleLog - INFO: - update_step: 11300, online_eval_reward: 200.000 +2023-06-18 16:34:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:39 - SimpleLog - INFO: - update_step: 11400, online_eval_reward: 200.000 +2023-06-18 16:34:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:39 - SimpleLog - INFO: - Interactor 0 finished episode 124 with reward 200.000 in 200 steps +2023-06-18 16:34:39 - SimpleLog - INFO: - Interactor 1 finished episode 125 with reward 200.000 in 200 steps +2023-06-18 16:34:40 - SimpleLog - INFO: - update_step: 11500, online_eval_reward: 200.000 +2023-06-18 16:34:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:41 - SimpleLog - INFO: - update_step: 11600, online_eval_reward: 200.000 +2023-06-18 16:34:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:41 - SimpleLog - INFO: - Interactor 0 finished episode 126 with reward 200.000 in 200 steps +2023-06-18 16:34:41 - SimpleLog - INFO: - Interactor 1 finished episode 127 with reward 146.000 in 146 steps +2023-06-18 16:34:42 - SimpleLog - INFO: - update_step: 11700, online_eval_reward: 200.000 +2023-06-18 16:34:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:43 - SimpleLog - INFO: - update_step: 11800, online_eval_reward: 200.000 +2023-06-18 16:34:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:44 - SimpleLog - INFO: - Interactor 0 finished episode 128 with reward 176.000 in 176 steps +2023-06-18 16:34:44 - SimpleLog - INFO: - Interactor 1 finished episode 129 with reward 178.000 in 178 steps +2023-06-18 16:34:45 - SimpleLog - INFO: - update_step: 11900, online_eval_reward: 200.000 +2023-06-18 16:34:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:45 - SimpleLog - INFO: - Interactor 1 finished episode 130 with reward 172.000 in 172 steps +2023-06-18 16:34:46 - SimpleLog - INFO: - update_step: 12000, online_eval_reward: 200.000 +2023-06-18 16:34:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:46 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward 200.000 in 200 steps +2023-06-18 16:34:47 - SimpleLog - INFO: - update_step: 12100, online_eval_reward: 200.000 +2023-06-18 16:34:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:48 - SimpleLog - INFO: - Interactor 1 finished episode 132 with reward 200.000 in 200 steps +2023-06-18 16:34:48 - SimpleLog - INFO: - update_step: 12200, online_eval_reward: 200.000 +2023-06-18 16:34:48 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:48 - SimpleLog - INFO: - Interactor 0 finished episode 133 with reward 200.000 in 200 steps +2023-06-18 16:34:50 - SimpleLog - INFO: - update_step: 12300, online_eval_reward: 200.000 +2023-06-18 16:34:50 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:50 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward 200.000 in 200 steps +2023-06-18 16:34:51 - SimpleLog - INFO: - update_step: 12400, online_eval_reward: 200.000 +2023-06-18 16:34:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:51 - SimpleLog - INFO: - Interactor 0 finished episode 135 with reward 200.000 in 200 steps +2023-06-18 16:34:52 - SimpleLog - INFO: - update_step: 12500, online_eval_reward: 200.000 +2023-06-18 16:34:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:53 - SimpleLog - INFO: - Interactor 1 finished episode 136 with reward 200.000 in 200 steps +2023-06-18 16:34:53 - SimpleLog - INFO: - update_step: 12600, online_eval_reward: 200.000 +2023-06-18 16:34:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:53 - SimpleLog - INFO: - Interactor 0 finished episode 137 with reward 200.000 in 200 steps +2023-06-18 16:34:55 - SimpleLog - INFO: - update_step: 12700, online_eval_reward: 200.000 +2023-06-18 16:34:55 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:55 - SimpleLog - INFO: - Interactor 1 finished episode 138 with reward 200.000 in 200 steps +2023-06-18 16:34:56 - SimpleLog - INFO: - update_step: 12800, online_eval_reward: 200.000 +2023-06-18 16:34:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:56 - SimpleLog - INFO: - Interactor 0 finished episode 139 with reward 200.000 in 200 steps +2023-06-18 16:34:57 - SimpleLog - INFO: - update_step: 12900, online_eval_reward: 200.000 +2023-06-18 16:34:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:58 - SimpleLog - INFO: - Interactor 1 finished episode 140 with reward 200.000 in 200 steps +2023-06-18 16:34:58 - SimpleLog - INFO: - update_step: 13000, online_eval_reward: 200.000 +2023-06-18 16:34:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:34:59 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward 200.000 in 200 steps +2023-06-18 16:35:00 - SimpleLog - INFO: - update_step: 13100, online_eval_reward: 200.000 +2023-06-18 16:35:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:00 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward 200.000 in 200 steps +2023-06-18 16:35:01 - SimpleLog - INFO: - update_step: 13200, online_eval_reward: 200.000 +2023-06-18 16:35:01 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:01 - SimpleLog - INFO: - Interactor 0 finished episode 143 with reward 200.000 in 200 steps +2023-06-18 16:35:02 - SimpleLog - INFO: - update_step: 13300, online_eval_reward: 200.000 +2023-06-18 16:35:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:03 - SimpleLog - INFO: - Interactor 1 finished episode 144 with reward 200.000 in 200 steps +2023-06-18 16:35:03 - SimpleLog - INFO: - update_step: 13400, online_eval_reward: 200.000 +2023-06-18 16:35:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:03 - SimpleLog - INFO: - Interactor 0 finished episode 145 with reward 200.000 in 200 steps +2023-06-18 16:35:05 - SimpleLog - INFO: - update_step: 13500, online_eval_reward: 200.000 +2023-06-18 16:35:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:05 - SimpleLog - INFO: - Interactor 1 finished episode 146 with reward 200.000 in 200 steps +2023-06-18 16:35:06 - SimpleLog - INFO: - update_step: 13600, online_eval_reward: 200.000 +2023-06-18 16:35:06 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:06 - SimpleLog - INFO: - Interactor 0 finished episode 147 with reward 200.000 in 200 steps +2023-06-18 16:35:07 - SimpleLog - INFO: - update_step: 13700, online_eval_reward: 200.000 +2023-06-18 16:35:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:08 - SimpleLog - INFO: - Interactor 1 finished episode 148 with reward 200.000 in 200 steps +2023-06-18 16:35:08 - SimpleLog - INFO: - update_step: 13800, online_eval_reward: 200.000 +2023-06-18 16:35:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:08 - SimpleLog - INFO: - Interactor 0 finished episode 149 with reward 200.000 in 200 steps +2023-06-18 16:35:10 - SimpleLog - INFO: - update_step: 13900, online_eval_reward: 200.000 +2023-06-18 16:35:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:10 - SimpleLog - INFO: - Interactor 1 finished episode 150 with reward 200.000 in 200 steps +2023-06-18 16:35:10 - SimpleLog - INFO: - Interactor 0 finished episode 151 with reward 179.000 in 179 steps +2023-06-18 16:35:11 - SimpleLog - INFO: - update_step: 14000, online_eval_reward: 200.000 +2023-06-18 16:35:11 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:12 - SimpleLog - INFO: - update_step: 14100, online_eval_reward: 200.000 +2023-06-18 16:35:12 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:13 - SimpleLog - INFO: - Interactor 0 finished episode 152 with reward 187.000 in 187 steps +2023-06-18 16:35:13 - SimpleLog - INFO: - Interactor 1 finished episode 153 with reward 200.000 in 200 steps +2023-06-18 16:35:13 - SimpleLog - INFO: - update_step: 14200, online_eval_reward: 200.000 +2023-06-18 16:35:13 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:15 - SimpleLog - INFO: - update_step: 14300, online_eval_reward: 200.000 +2023-06-18 16:35:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 154 with reward 189.000 in 189 steps +2023-06-18 16:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 155 with reward 200.000 in 200 steps +2023-06-18 16:35:16 - SimpleLog - INFO: - update_step: 14400, online_eval_reward: 200.000 +2023-06-18 16:35:16 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:17 - SimpleLog - INFO: - update_step: 14500, online_eval_reward: 200.000 +2023-06-18 16:35:17 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 156 with reward 200.000 in 200 steps +2023-06-18 16:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 157 with reward 200.000 in 200 steps +2023-06-18 16:35:18 - SimpleLog - INFO: - update_step: 14600, online_eval_reward: 200.000 +2023-06-18 16:35:18 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:19 - SimpleLog - INFO: - update_step: 14700, online_eval_reward: 200.000 +2023-06-18 16:35:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:20 - SimpleLog - INFO: - Interactor 0 finished episode 158 with reward 191.000 in 191 steps +2023-06-18 16:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 159 with reward 200.000 in 200 steps +2023-06-18 16:35:21 - SimpleLog - INFO: - update_step: 14800, online_eval_reward: 200.000 +2023-06-18 16:35:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:22 - SimpleLog - INFO: - update_step: 14900, online_eval_reward: 200.000 +2023-06-18 16:35:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:22 - SimpleLog - INFO: - Interactor 0 finished episode 160 with reward 163.000 in 163 steps +2023-06-18 16:35:22 - SimpleLog - INFO: - Interactor 1 finished episode 161 with reward 200.000 in 200 steps +2023-06-18 16:35:23 - SimpleLog - INFO: - update_step: 15000, online_eval_reward: 200.000 +2023-06-18 16:35:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:24 - SimpleLog - INFO: - Interactor 0 finished episode 162 with reward 141.000 in 141 steps +2023-06-18 16:35:24 - SimpleLog - INFO: - update_step: 15100, online_eval_reward: 200.000 +2023-06-18 16:35:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:25 - SimpleLog - INFO: - Interactor 1 finished episode 163 with reward 154.000 in 154 steps +2023-06-18 16:35:25 - SimpleLog - INFO: - update_step: 15200, online_eval_reward: 200.000 +2023-06-18 16:35:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:26 - SimpleLog - INFO: - Interactor 0 finished episode 164 with reward 200.000 in 200 steps +2023-06-18 16:35:27 - SimpleLog - INFO: - update_step: 15300, online_eval_reward: 200.000 +2023-06-18 16:35:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:27 - SimpleLog - INFO: - Interactor 1 finished episode 165 with reward 200.000 in 200 steps +2023-06-18 16:35:28 - SimpleLog - INFO: - update_step: 15400, online_eval_reward: 200.000 +2023-06-18 16:35:28 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:28 - SimpleLog - INFO: - Interactor 0 finished episode 166 with reward 200.000 in 200 steps +2023-06-18 16:35:29 - SimpleLog - INFO: - update_step: 15500, online_eval_reward: 200.000 +2023-06-18 16:35:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:29 - SimpleLog - INFO: - Interactor 1 finished episode 167 with reward 200.000 in 200 steps +2023-06-18 16:35:30 - SimpleLog - INFO: - update_step: 15600, online_eval_reward: 200.000 +2023-06-18 16:35:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 168 with reward 167.000 in 167 steps +2023-06-18 16:35:31 - SimpleLog - INFO: - Interactor 1 finished episode 169 with reward 148.000 in 148 steps +2023-06-18 16:35:31 - SimpleLog - INFO: - update_step: 15700, online_eval_reward: 200.000 +2023-06-18 16:35:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:32 - SimpleLog - INFO: - Interactor 0 finished episode 170 with reward 168.000 in 168 steps +2023-06-18 16:35:33 - SimpleLog - INFO: - update_step: 15800, online_eval_reward: 200.000 +2023-06-18 16:35:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:33 - SimpleLog - INFO: - Interactor 1 finished episode 171 with reward 200.000 in 200 steps +2023-06-18 16:35:34 - SimpleLog - INFO: - update_step: 15900, online_eval_reward: 200.000 +2023-06-18 16:35:34 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:34 - SimpleLog - INFO: - Interactor 0 finished episode 172 with reward 187.000 in 187 steps +2023-06-18 16:35:35 - SimpleLog - INFO: - update_step: 16000, online_eval_reward: 200.000 +2023-06-18 16:35:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:36 - SimpleLog - INFO: - Interactor 1 finished episode 173 with reward 200.000 in 200 steps +2023-06-18 16:35:36 - SimpleLog - INFO: - update_step: 16100, online_eval_reward: 200.000 +2023-06-18 16:35:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:37 - SimpleLog - INFO: - Interactor 0 finished episode 174 with reward 200.000 in 200 steps +2023-06-18 16:35:37 - SimpleLog - INFO: - update_step: 16200, online_eval_reward: 200.000 +2023-06-18 16:35:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:38 - SimpleLog - INFO: - Interactor 1 finished episode 175 with reward 149.000 in 149 steps +2023-06-18 16:35:39 - SimpleLog - INFO: - update_step: 16300, online_eval_reward: 200.000 +2023-06-18 16:35:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 176 with reward 200.000 in 200 steps +2023-06-18 16:35:40 - SimpleLog - INFO: - update_step: 16400, online_eval_reward: 200.000 +2023-06-18 16:35:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:40 - SimpleLog - INFO: - Interactor 1 finished episode 177 with reward 200.000 in 200 steps +2023-06-18 16:35:41 - SimpleLog - INFO: - update_step: 16500, online_eval_reward: 200.000 +2023-06-18 16:35:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:42 - SimpleLog - INFO: - Interactor 0 finished episode 178 with reward 182.000 in 182 steps +2023-06-18 16:35:42 - SimpleLog - INFO: - update_step: 16600, online_eval_reward: 200.000 +2023-06-18 16:35:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:42 - SimpleLog - INFO: - Interactor 1 finished episode 179 with reward 175.000 in 175 steps +2023-06-18 16:35:44 - SimpleLog - INFO: - update_step: 16700, online_eval_reward: 200.000 +2023-06-18 16:35:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:44 - SimpleLog - INFO: - Interactor 0 finished episode 180 with reward 200.000 in 200 steps +2023-06-18 16:35:45 - SimpleLog - INFO: - update_step: 16800, online_eval_reward: 200.000 +2023-06-18 16:35:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:45 - SimpleLog - INFO: - Interactor 1 finished episode 181 with reward 200.000 in 200 steps +2023-06-18 16:35:46 - SimpleLog - INFO: - update_step: 16900, online_eval_reward: 200.000 +2023-06-18 16:35:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:46 - SimpleLog - INFO: - Interactor 0 finished episode 182 with reward 200.000 in 200 steps +2023-06-18 16:35:47 - SimpleLog - INFO: - update_step: 17000, online_eval_reward: 200.000 +2023-06-18 16:35:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:47 - SimpleLog - INFO: - Interactor 1 finished episode 183 with reward 200.000 in 200 steps +2023-06-18 16:35:48 - SimpleLog - INFO: - update_step: 17100, online_eval_reward: 200.000 +2023-06-18 16:35:48 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:49 - SimpleLog - INFO: - Interactor 0 finished episode 184 with reward 200.000 in 200 steps +2023-06-18 16:35:50 - SimpleLog - INFO: - update_step: 17200, online_eval_reward: 200.000 +2023-06-18 16:35:50 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:50 - SimpleLog - INFO: - Interactor 1 finished episode 185 with reward 200.000 in 200 steps +2023-06-18 16:35:51 - SimpleLog - INFO: - update_step: 17300, online_eval_reward: 200.000 +2023-06-18 16:35:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:51 - SimpleLog - INFO: - Interactor 0 finished episode 186 with reward 200.000 in 200 steps +2023-06-18 16:35:52 - SimpleLog - INFO: - Interactor 1 finished episode 187 with reward 186.000 in 186 steps +2023-06-18 16:35:52 - SimpleLog - INFO: - update_step: 17400, online_eval_reward: 200.000 +2023-06-18 16:35:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:53 - SimpleLog - INFO: - update_step: 17500, online_eval_reward: 200.000 +2023-06-18 16:35:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:54 - SimpleLog - INFO: - Interactor 0 finished episode 188 with reward 200.000 in 200 steps +2023-06-18 16:35:54 - SimpleLog - INFO: - Interactor 1 finished episode 189 with reward 200.000 in 200 steps +2023-06-18 16:35:55 - SimpleLog - INFO: - update_step: 17600, online_eval_reward: 200.000 +2023-06-18 16:35:55 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:56 - SimpleLog - INFO: - update_step: 17700, online_eval_reward: 200.000 +2023-06-18 16:35:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:56 - SimpleLog - INFO: - Interactor 0 finished episode 190 with reward 200.000 in 200 steps +2023-06-18 16:35:57 - SimpleLog - INFO: - Interactor 1 finished episode 191 with reward 200.000 in 200 steps +2023-06-18 16:35:57 - SimpleLog - INFO: - update_step: 17800, online_eval_reward: 200.000 +2023-06-18 16:35:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:58 - SimpleLog - INFO: - update_step: 17900, online_eval_reward: 200.000 +2023-06-18 16:35:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:35:59 - SimpleLog - INFO: - Interactor 0 finished episode 192 with reward 200.000 in 200 steps +2023-06-18 16:35:59 - SimpleLog - INFO: - Interactor 1 finished episode 193 with reward 200.000 in 200 steps +2023-06-18 16:36:00 - SimpleLog - INFO: - update_step: 18000, online_eval_reward: 200.000 +2023-06-18 16:36:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:36:01 - SimpleLog - INFO: - update_step: 18100, online_eval_reward: 200.000 +2023-06-18 16:36:01 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:36:02 - SimpleLog - INFO: - Interactor 0 finished episode 194 with reward 200.000 in 200 steps +2023-06-18 16:36:02 - SimpleLog - INFO: - Interactor 1 finished episode 195 with reward 200.000 in 200 steps +2023-06-18 16:36:02 - SimpleLog - INFO: - update_step: 18200, online_eval_reward: 200.000 +2023-06-18 16:36:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:36:04 - SimpleLog - INFO: - update_step: 18300, online_eval_reward: 200.000 +2023-06-18 16:36:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:36:04 - SimpleLog - INFO: - Interactor 0 finished episode 196 with reward 190.000 in 190 steps +2023-06-18 16:36:04 - SimpleLog - INFO: - Interactor 1 finished episode 197 with reward 200.000 in 200 steps +2023-06-18 16:36:05 - SimpleLog - INFO: - update_step: 18400, online_eval_reward: 200.000 +2023-06-18 16:36:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:36:06 - SimpleLog - INFO: - update_step: 18500, online_eval_reward: 200.000 +2023-06-18 16:36:06 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:36:06 - SimpleLog - INFO: - Interactor 0 finished episode 198 with reward 200.000 in 200 steps +2023-06-18 16:36:07 - SimpleLog - INFO: - Interactor 1 finished episode 199 with reward 200.000 in 200 steps +2023-06-18 16:36:07 - SimpleLog - INFO: - update_step: 18600, online_eval_reward: 200.000 +2023-06-18 16:36:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:36:08 - SimpleLog - INFO: - update_step: 18700, online_eval_reward: 200.000 +2023-06-18 16:36:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-06-18 16:36:09 - SimpleLog - INFO: - Interactor 0 finished episode 200 with reward 200.000 in 200 steps +2023-06-18 16:36:09 - SimpleLog - INFO: - Finish testing! Time cost: 229.417 s diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/100 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/100 new file mode 100644 index 0000000000000000000000000000000000000000..dd014e20faaa06ef3878c57816c4e24c700ee94c --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add5d0d53b1d79e1812626cb409e21ae8d0b347ce2aebca398412974d3092798 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1000 new file mode 100644 index 0000000000000000000000000000000000000000..4d1a11e5924d83dcd7852bc4b226f6d9860a1618 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4684feeeab8f71a31684e238f2e5d8f678c4a3c7b58443082c47d1d28d9978 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10000 new file mode 100644 index 0000000000000000000000000000000000000000..722f627851adbee64862e157f213d1524e55cfb4 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ed2d8a8d547df67abec878af406875d89cdb4903b41e52ac3460b465f1be16d +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10300 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10300 new file mode 100644 index 0000000000000000000000000000000000000000..1ad6a482a722afd13bfda55361b5302f1bcb8aaf --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d0f56697bb3e9f108b3034580de19fb4e7cb705897295d47bf1a98e4c01fb4 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10900 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10900 new file mode 100644 index 0000000000000000000000000000000000000000..1e5438d618e8b00810a93eb9901103c2643e74db --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73a645d4bdb58eed9da819ef63310565f1bf45c755b2b1042a921343a1e8b38 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1100 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1100 new file mode 100644 index 0000000000000000000000000000000000000000..bee1ea329bb6e29a59447da414f967dbda729d40 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4994ca255864a58d79d968116ebf58498e29b3cd3edd332eee5b32e46e99a4cc +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11000 new file mode 100644 index 0000000000000000000000000000000000000000..3dec9c65905d37f5cc297c1f0b4bf3b4d8a619db --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0f2b11eb37b31349365b2d077435a072d4376b3209ed258e0f60ec9d9165223 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11600 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11600 new file mode 100644 index 0000000000000000000000000000000000000000..53bbd9f1684429098fb83b7e0f0bb5a7ec18f40b --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e85ffdd23098b67aa11bd1f2a834a5a246ea67ed6fbd7b1289302600ef4bd7a7 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11700 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11700 new file mode 100644 index 0000000000000000000000000000000000000000..d961924b1dca1da21bc5d200cdc4b329f32c7a75 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3589f5bf1f7109d172dbce9e33abc5dcc6c3d5ca58a9201b41a20d80c3606fa +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11800 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11800 new file mode 100644 index 0000000000000000000000000000000000000000..40f5335e2dc1093e9544a4c271bf34df5c5dab2b --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d11f38c72072b2a5f453d3f5e04de50942848c7b5c4ef63cb65abcbc0b25ce4 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11900 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11900 new file mode 100644 index 0000000000000000000000000000000000000000..832f7fd8d4c1789a2d2e703416d153b7f19b6cd0 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15446f327abe16f08a2fd4ae6075751e51dd1a4aacc9cac3bd7ec3757db189b +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1200 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1200 new file mode 100644 index 0000000000000000000000000000000000000000..0c2fc3bfd60b04807df2370922526ad417fb57f6 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f66d0dc3d25181c5fbb35abe0015eb08e52eb2580c3a103ce66172945569748 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/12100 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/12100 new file mode 100644 index 0000000000000000000000000000000000000000..1e84be9c746afff2ecf8bc711905467375baaece --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/12100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b53ab418585ce3e703020b7e606a0de2f45aa0e82efe281621de69b41d92745 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13000 new file mode 100644 index 0000000000000000000000000000000000000000..1924a0d07bed1144610b0d38b92b2b28cef5491c --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0715db6295848d80e6134a04f22d3a314067d3806e16361444a3e63ab7c35db +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13100 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13100 new file mode 100644 index 0000000000000000000000000000000000000000..c7ed55af35baec2075de7afb65760e151172ad2f --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b32798dd921c01efb9fc320c6e6ec83c7b1fe1c6de64f902e6b52ed7a6c03d +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13200 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13200 new file mode 100644 index 0000000000000000000000000000000000000000..bf64bf995e3f139b031d605248756347d72822a3 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f48101058e77c02328aa36ce6573e9dd654000ac27a022eae23267301c296a7 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13900 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13900 new file mode 100644 index 0000000000000000000000000000000000000000..99a22421f393807e49c47e694bb092d254c1339a --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:024e07ed4c94b765288cd4d048dc671f32f265c924dd1fda6a7b50eeae5528f1 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1400 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1400 new file mode 100644 index 0000000000000000000000000000000000000000..b47f127a34e33bd871ffb57888ef661fd31e927d --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe907ad613ee3dfe9582c381ed4568943ffb65683f36560af5e3508b7523bf3 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14000 new file mode 100644 index 0000000000000000000000000000000000000000..36b945d8d5b223c0810edb625c5f43d09850eac1 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d024a2338eb3e6723c71e1a4a3b48962c940702cd0deb4fefb574281730194fb +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14100 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14100 new file mode 100644 index 0000000000000000000000000000000000000000..85002a0b9cda74ce13871b0e23e839065a38d3e2 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1429b0352df27acc14c4d1aa722354f1313f9eb76e2ebbec5f8cc571b71475a6 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14200 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14200 new file mode 100644 index 0000000000000000000000000000000000000000..8a91105ad97d0ca8a81690cffd56cf98932312c2 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42fa39c58e4bd8831410e102d4a30516eca012ab25ca28d9af73f03f2a66d6d6 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14300 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14300 new file mode 100644 index 0000000000000000000000000000000000000000..4296cefbb1167295ffd5ca8d9bd001311ba41bdd --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e662091f888025b5c6254d45abdd6dee1670d6e4a43cc0f6557627dc919899d9 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14900 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14900 new file mode 100644 index 0000000000000000000000000000000000000000..7ea13cfe35542e7295dd0331a051867ebbb26d91 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdeab0564c1a1f118c6e221479b77cec2c5b90dbf68899dd259880a5a24ff761 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1500 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1500 new file mode 100644 index 0000000000000000000000000000000000000000..7a3339e368315c4e558425b7ebdffd2d4e3d45dc --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804f2b482196318d71884b4e5d731d576c95130e4003b049048b1356a899a587 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15000 new file mode 100644 index 0000000000000000000000000000000000000000..fac55506bb872cd3f31a2641915da047a874c9b2 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4eb970666b6c2372a82b262ac37ce383312e706f9c99bfaf22df74ece0514e +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15100 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15100 new file mode 100644 index 0000000000000000000000000000000000000000..9fbd1930f62b7344ce9173c4e71ff7a7759c4733 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc15a1f3ef265e973138d3a3bdeda0e83a2cc5a3bcfa4e0a54b444ab31a424df +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15800 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15800 new file mode 100644 index 0000000000000000000000000000000000000000..557125aea7b622c675e144d7191ed0fee3baeceb --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a19d4aa9763c0d1b0a91f5057cf545f8cb912cdcc01d57cd9c7d8b94b9be2b +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15900 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15900 new file mode 100644 index 0000000000000000000000000000000000000000..d5ffec927334d31ee1687b7a566babc729450c3f --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f37ad7932f82a86bad4c931339a900f82b9c491233d3fad484140c6b94d726cf +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1600 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1600 new file mode 100644 index 0000000000000000000000000000000000000000..fe159dda89d4476b8d9e5d4467b248c68582eaad --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46a07579ee4351757949a014da81246e48cfe1094ab337c0b609643b9d535f2 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16000 new file mode 100644 index 0000000000000000000000000000000000000000..12853cf0243d001c40bb77a569174862651c78c0 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:122e09fde5d3b301e18bbcae10c4cf547b84d12e182a79b03c24200407aa3170 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16100 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16100 new file mode 100644 index 0000000000000000000000000000000000000000..f4dc13688f1275d9f8cdd8032070e53960588f11 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb8e131dfd24d6617fb4e68fd4c9657373259d4998464ad2bd686169f9c27bae +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16800 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16800 new file mode 100644 index 0000000000000000000000000000000000000000..16c2ebf499119344652f9966013fce9a7b9880b3 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64e93d92d90d7abb1be17c254e0db2b6dc384c85424ac01a8e23295745e6c6d2 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1700 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1700 new file mode 100644 index 0000000000000000000000000000000000000000..c329c9c4d7be40a6696d24237b8d0b9a3bc2dcf2 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02957143fc0d38de232441d8c8cb8052a2070fa396417b21cc9b6e660f51d6a9 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17000 new file mode 100644 index 0000000000000000000000000000000000000000..51bdb3f0227fef27e327eaa9f7c14b3268e049b7 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8074d61bd0c6226e4c82b9a7baedd4c829d6419bb1c40a555de75d94ea41aa89 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17100 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17100 new file mode 100644 index 0000000000000000000000000000000000000000..93e582b66c904f1d2419e735bb4fc88d68fc871a --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50da37ff21b597cab80241be3a936a135c151124c8d178d23132db79a0800775 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17200 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17200 new file mode 100644 index 0000000000000000000000000000000000000000..4a189b487afd6592e9117385c939ead74d0ffdae --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a49e08a7e07d426e3ce27e17a8ed309b1b69f0d9375caf7deca26d4c036ce2e +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17300 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17300 new file mode 100644 index 0000000000000000000000000000000000000000..b18014acf40a5ffeeb39c4643511186a78008737 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbcb20cec809eaf1d85071cea502999f60dd6ff73c7d958f874effdf700d70e6 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17600 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17600 new file mode 100644 index 0000000000000000000000000000000000000000..e500528629faf46a7d572c92986d7d5b97629b54 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2d3fcf5e8c5825688529931097a3aeaacd5998dbec1251b97c1f91fcddd7840 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17700 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17700 new file mode 100644 index 0000000000000000000000000000000000000000..74219f42437520117f2e12eb866398374a850104 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f548a74453f08f9d26e64ae5c724cb318c5c04ae1f9bd79ca0a37f6805c596ca +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17900 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17900 new file mode 100644 index 0000000000000000000000000000000000000000..c6dc32eaf1bd5492fb4bd44af2a52559a762c1e8 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4541a4a60377a5204c0fce60e9b98db6221cf48f9a00c33233f15950bc612f90 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1800 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1800 new file mode 100644 index 0000000000000000000000000000000000000000..c7ce458367b61eeb1dc666bad9c8b4c9eb2ae6e8 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e79ae7dea899d12054b60c533fc92c84dd6ab36e4d7f0b1134f839853ea1b2f +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18000 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18000 new file mode 100644 index 0000000000000000000000000000000000000000..76ccc1ce96f4b9893c54159eb72338003f75d804 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d5fa99802f6f7970efca114e078580867f439cab33432320623aa8ce09112d +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18400 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18400 new file mode 100644 index 0000000000000000000000000000000000000000..2971b538cd0de5cf0cfbeb1aa0bfbeb8f5e2aebf --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a27f5c13fa961caab89e7ffb2b5b2b264f91965731c7c3b0433eda222eb001 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18600 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18600 new file mode 100644 index 0000000000000000000000000000000000000000..cc67d6d516e7fd21e380968bfddd05f93a62d113 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7f34347ce4056945f9308e58d225fcdef0e1ad3324596a3ba14553b8310385 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18700 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18700 new file mode 100644 index 0000000000000000000000000000000000000000..99ba475a6b106004294db174ba4f7e595b0e174c --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b89a9b6bb7ac83c5084c4cd144e5ed8e306180ccd2a572e35239d978956d347 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1900 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1900 new file mode 100644 index 0000000000000000000000000000000000000000..168506938a5d8c223af28093b47684245b6bef71 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d291d4960503277bcd3eba3c87cb18a5e55a3acb09b6077cc8330c8c5ffcf899 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/200 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/200 new file mode 100644 index 0000000000000000000000000000000000000000..fb4a4a2b1695b37ef21191e23d20d3d95adbd6c7 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5631d59644656d58fb8b51c6223769b5bc1c43e352e7745ce85195592a24a756 +size 1362571 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/tb_logs/interact/events.out.tfevents.1687077139.ML3090.328984.0 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/tb_logs/interact/events.out.tfevents.1687077139.ML3090.328984.0 new file mode 100644 index 0000000000000000000000000000000000000000..dd52ec59d84a94beb7113eb0d6ec54a74a975329 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/tb_logs/interact/events.out.tfevents.1687077139.ML3090.328984.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2afc33eb6c50d1d5e1161b1d6e9cf207ab36edcdff724b5495c1838d6eb2d97d +size 19386 diff --git a/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/tb_logs/policy/events.out.tfevents.1687077139.ML3090.328984.1 b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/tb_logs/policy/events.out.tfevents.1687077139.ML3090.328984.1 new file mode 100644 index 0000000000000000000000000000000000000000..c74afd46abecb4946143e1a7241e86403aecae1b --- /dev/null +++ b/ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/tb_logs/policy/events.out.tfevents.1687077139.ML3090.328984.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4ef6d5f29f919a66c9ce75eb2c3116d515eba632b70574103cdf832651881b +size 5122633