diff --git a/Train_Pendulum-v1_SAC_20230618-163911/config.yaml b/Train_Pendulum-v1_SAC_20230618-163911/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..71c215064c325dd142f8cc4a4b27d1367a647490 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/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: false + load_model_step: best + load_path: Train_CartPole-v1_SAC_20230618-162702 + max_episode: 200 + max_step: 200 + mode: train + 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: continuous + 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: Pendulum-v1 + ignore_params: + - wrapper + - ignore_params + render_mode: null + wrapper: null diff --git a/Train_Pendulum-v1_SAC_20230618-163911/logs/log.txt b/Train_Pendulum-v1_SAC_20230618-163911/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..73694f200f231aecae309d4607a25e0702b86d36 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/logs/log.txt @@ -0,0 +1,487 @@ +2023-06-18 16:39:11 - SimpleLog - INFO: - General Configs: +2023-06-18 16:39:11 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:39:11 - SimpleLog - INFO: - Name Value Type +2023-06-18 16:39:11 - SimpleLog - INFO: - env_name gym +2023-06-18 16:39:11 - SimpleLog - INFO: - algo_name SAC +2023-06-18 16:39:11 - SimpleLog - INFO: - mode train +2023-06-18 16:39:11 - SimpleLog - INFO: - device cpu +2023-06-18 16:39:11 - SimpleLog - INFO: - seed 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - max_episode 200 +2023-06-18 16:39:11 - SimpleLog - INFO: - max_step 200 +2023-06-18 16:39:11 - SimpleLog - INFO: - collect_traj 0 +2023-06-18 16:39:11 - SimpleLog - INFO: - mp_backend single +2023-06-18 16:39:11 - SimpleLog - INFO: - n_workers 2 +2023-06-18 16:39:11 - SimpleLog - INFO: - n_learners 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - share_buffer 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - online_eval 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - online_eval_episode 10 +2023-06-18 16:39:11 - SimpleLog - INFO: - model_save_fre 100 +2023-06-18 16:39:11 - SimpleLog - INFO: - load_checkpoint 0 +2023-06-18 16:39:11 - SimpleLog - INFO: - load_path Train_CartPole-v1_SAC_20230618-162702 +2023-06-18 16:39:11 - SimpleLog - INFO: - load_model_step best +2023-06-18 16:39:11 - SimpleLog - INFO: - interact_summary_fre 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - model_summary_fre 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:39:11 - SimpleLog - INFO: - Algo Configs: +2023-06-18 16:39:11 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:39:11 - SimpleLog - INFO: - Name Value Type +2023-06-18 16:39:11 - SimpleLog - INFO: - critic1_lr 0.001 +2023-06-18 16:39:11 - SimpleLog - INFO: - critic2_lr 0.001 +2023-06-18 16:39:11 - SimpleLog - INFO: - actor_lr 0.0003 +2023-06-18 16:39:11 - SimpleLog - INFO: - gamma 0.95 +2023-06-18 16:39:11 - SimpleLog - INFO: - tau 0.005 +2023-06-18 16:39:11 - SimpleLog - INFO: - alpha 0.1 +2023-06-18 16:39:11 - SimpleLog - INFO: - automatic_entropy_tuning 0 +2023-06-18 16:39:11 - SimpleLog - INFO: - batch_size 64 +2023-06-18 16:39:11 - SimpleLog - INFO: - hidden_dim 64 +2023-06-18 16:39:11 - SimpleLog - INFO: - n_epochs 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - start_steps 10000 +2023-06-18 16:39:11 - SimpleLog - INFO: - target_update_fre 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - buffer_size 1000000 +2023-06-18 16:39:11 - SimpleLog - INFO: - min_policy 0 +2023-06-18 16:39:11 - SimpleLog - INFO: - alpha_lr 0.0001 +2023-06-18 16:39:11 - SimpleLog - INFO: - n_steps_per_learn 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - action_type continuous +2023-06-18 16:39:11 - SimpleLog - INFO: - independ_actor 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - share_optimizer 0 +2023-06-18 16:39:11 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-06-18 16:39:11 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-06-18 16:39:11 - SimpleLog - INFO: - value_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-06-18 16:39:11 - SimpleLog - INFO: - buffer_type REPLAY_QUE +2023-06-18 16:39:11 - SimpleLog - INFO: - epsilon_decay 500 +2023-06-18 16:39:11 - SimpleLog - INFO: - epsilon_end 0.01 +2023-06-18 16:39:11 - SimpleLog - INFO: - epsilon_start 0.95 +2023-06-18 16:39:11 - SimpleLog - INFO: - lr 0.0001 +2023-06-18 16:39:11 - SimpleLog - INFO: - target_update 1 +2023-06-18 16:39:11 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:39:11 - SimpleLog - INFO: - Env Configs: +2023-06-18 16:39:11 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:39:11 - SimpleLog - INFO: - Name Value Type +2023-06-18 16:39:11 - SimpleLog - INFO: - id Pendulum-v1 +2023-06-18 16:39:11 - SimpleLog - INFO: - render_mode None +2023-06-18 16:39:11 - SimpleLog - INFO: - wrapper None +2023-06-18 16:39:11 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-06-18 16:39:11 - SimpleLog - INFO: - ================================================================================ +2023-06-18 16:39:11 - SimpleLog - INFO: - Start training! +2023-06-18 16:39:13 - SimpleLog - INFO: - update_step: 100, online_eval_reward: -1380.018 +2023-06-18 16:39:13 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1380.018, save the best model! +2023-06-18 16:39:13 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward -1247.240 in 200 steps +2023-06-18 16:39:13 - SimpleLog - INFO: - Interactor 1 finished episode 2 with reward -1239.670 in 200 steps +2023-06-18 16:39:14 - SimpleLog - INFO: - update_step: 200, online_eval_reward: -1594.462 +2023-06-18 16:39:15 - SimpleLog - INFO: - update_step: 300, online_eval_reward: -1575.933 +2023-06-18 16:39:15 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward -1465.696 in 200 steps +2023-06-18 16:39:15 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward -1538.397 in 200 steps +2023-06-18 16:39:16 - SimpleLog - INFO: - update_step: 400, online_eval_reward: -1550.200 +2023-06-18 16:39:17 - SimpleLog - INFO: - update_step: 500, online_eval_reward: -1517.290 +2023-06-18 16:39:18 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward -1516.613 in 200 steps +2023-06-18 16:39:18 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward -1697.405 in 200 steps +2023-06-18 16:39:18 - SimpleLog - INFO: - update_step: 600, online_eval_reward: -1474.664 +2023-06-18 16:39:19 - SimpleLog - INFO: - update_step: 700, online_eval_reward: -1480.853 +2023-06-18 16:39:20 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward -1479.039 in 200 steps +2023-06-18 16:39:20 - SimpleLog - INFO: - Interactor 1 finished episode 8 with reward -1621.124 in 200 steps +2023-06-18 16:39:21 - SimpleLog - INFO: - update_step: 800, online_eval_reward: -1444.541 +2023-06-18 16:39:22 - SimpleLog - INFO: - update_step: 900, online_eval_reward: -1432.778 +2023-06-18 16:39:22 - SimpleLog - INFO: - Interactor 0 finished episode 9 with reward -1375.822 in 200 steps +2023-06-18 16:39:22 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward -1548.226 in 200 steps +2023-06-18 16:39:23 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: -1379.687 +2023-06-18 16:39:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1379.687, save the best model! +2023-06-18 16:39:24 - SimpleLog - INFO: - update_step: 1100, online_eval_reward: -1365.993 +2023-06-18 16:39:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1365.993, save the best model! +2023-06-18 16:39:25 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward -1417.818 in 200 steps +2023-06-18 16:39:25 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward -1484.637 in 200 steps +2023-06-18 16:39:26 - SimpleLog - INFO: - update_step: 1200, online_eval_reward: -1289.023 +2023-06-18 16:39:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1289.023, save the best model! +2023-06-18 16:39:27 - SimpleLog - INFO: - update_step: 1300, online_eval_reward: -1274.835 +2023-06-18 16:39:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1274.835, save the best model! +2023-06-18 16:39:27 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward -1299.286 in 200 steps +2023-06-18 16:39:27 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward -1410.494 in 200 steps +2023-06-18 16:39:28 - SimpleLog - INFO: - update_step: 1400, online_eval_reward: -1234.458 +2023-06-18 16:39:28 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1234.458, save the best model! +2023-06-18 16:39:29 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: -1167.915 +2023-06-18 16:39:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1167.915, save the best model! +2023-06-18 16:39:30 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward -1114.071 in 200 steps +2023-06-18 16:39:30 - SimpleLog - INFO: - Interactor 1 finished episode 16 with reward -1412.817 in 200 steps +2023-06-18 16:39:30 - SimpleLog - INFO: - update_step: 1600, online_eval_reward: -1164.202 +2023-06-18 16:39:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1164.202, save the best model! +2023-06-18 16:39:32 - SimpleLog - INFO: - update_step: 1700, online_eval_reward: -1135.373 +2023-06-18 16:39:32 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1135.373, save the best model! +2023-06-18 16:39:32 - SimpleLog - INFO: - Interactor 0 finished episode 17 with reward -1036.607 in 200 steps +2023-06-18 16:39:32 - SimpleLog - INFO: - Interactor 1 finished episode 18 with reward -1192.079 in 200 steps +2023-06-18 16:39:33 - SimpleLog - INFO: - update_step: 1800, online_eval_reward: -1136.757 +2023-06-18 16:39:34 - SimpleLog - INFO: - update_step: 1900, online_eval_reward: -1096.014 +2023-06-18 16:39:34 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1096.014, save the best model! +2023-06-18 16:39:35 - SimpleLog - INFO: - Interactor 0 finished episode 19 with reward -1018.449 in 200 steps +2023-06-18 16:39:35 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward -1162.681 in 200 steps +2023-06-18 16:39:35 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: -1065.251 +2023-06-18 16:39:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1065.251, save the best model! +2023-06-18 16:39:37 - SimpleLog - INFO: - update_step: 2100, online_eval_reward: -1124.240 +2023-06-18 16:39:37 - SimpleLog - INFO: - Interactor 0 finished episode 21 with reward -971.930 in 200 steps +2023-06-18 16:39:37 - SimpleLog - INFO: - Interactor 1 finished episode 22 with reward -1129.776 in 200 steps +2023-06-18 16:39:38 - SimpleLog - INFO: - update_step: 2200, online_eval_reward: -880.723 +2023-06-18 16:39:38 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -880.723, save the best model! +2023-06-18 16:39:39 - SimpleLog - INFO: - update_step: 2300, online_eval_reward: -993.409 +2023-06-18 16:39:40 - SimpleLog - INFO: - Interactor 0 finished episode 23 with reward -940.286 in 200 steps +2023-06-18 16:39:40 - SimpleLog - INFO: - Interactor 1 finished episode 24 with reward -1006.670 in 200 steps +2023-06-18 16:39:40 - SimpleLog - INFO: - update_step: 2400, online_eval_reward: -874.374 +2023-06-18 16:39:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -874.374, save the best model! +2023-06-18 16:39:42 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: -1023.463 +2023-06-18 16:39:42 - SimpleLog - INFO: - Interactor 0 finished episode 25 with reward -854.571 in 200 steps +2023-06-18 16:39:42 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward -995.997 in 200 steps +2023-06-18 16:39:43 - SimpleLog - INFO: - update_step: 2600, online_eval_reward: -970.227 +2023-06-18 16:39:44 - SimpleLog - INFO: - update_step: 2700, online_eval_reward: -970.407 +2023-06-18 16:39:45 - SimpleLog - INFO: - Interactor 0 finished episode 27 with reward -891.371 in 200 steps +2023-06-18 16:39:45 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward -884.375 in 200 steps +2023-06-18 16:39:45 - SimpleLog - INFO: - update_step: 2800, online_eval_reward: -988.688 +2023-06-18 16:39:47 - SimpleLog - INFO: - update_step: 2900, online_eval_reward: -844.578 +2023-06-18 16:39:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -844.578, save the best model! +2023-06-18 16:39:47 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward -874.244 in 200 steps +2023-06-18 16:39:47 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward -950.054 in 200 steps +2023-06-18 16:39:48 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: -931.215 +2023-06-18 16:39:49 - SimpleLog - INFO: - update_step: 3100, online_eval_reward: -969.424 +2023-06-18 16:39:50 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward -761.690 in 200 steps +2023-06-18 16:39:50 - SimpleLog - INFO: - Interactor 1 finished episode 32 with reward -810.092 in 200 steps +2023-06-18 16:39:50 - SimpleLog - INFO: - update_step: 3200, online_eval_reward: -858.450 +2023-06-18 16:39:52 - SimpleLog - INFO: - update_step: 3300, online_eval_reward: -974.745 +2023-06-18 16:39:52 - SimpleLog - INFO: - Interactor 0 finished episode 33 with reward -720.616 in 200 steps +2023-06-18 16:39:52 - SimpleLog - INFO: - Interactor 1 finished episode 34 with reward -763.590 in 200 steps +2023-06-18 16:39:53 - SimpleLog - INFO: - update_step: 3400, online_eval_reward: -865.729 +2023-06-18 16:39:54 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: -703.698 +2023-06-18 16:39:54 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -703.698, save the best model! +2023-06-18 16:39:55 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward -697.547 in 200 steps +2023-06-18 16:39:55 - SimpleLog - INFO: - Interactor 1 finished episode 36 with reward -750.590 in 200 steps +2023-06-18 16:39:55 - SimpleLog - INFO: - update_step: 3600, online_eval_reward: -863.473 +2023-06-18 16:39:57 - SimpleLog - INFO: - update_step: 3700, online_eval_reward: -859.878 +2023-06-18 16:39:57 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward -731.446 in 200 steps +2023-06-18 16:39:57 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward -874.953 in 200 steps +2023-06-18 16:39:58 - SimpleLog - INFO: - update_step: 3800, online_eval_reward: -855.164 +2023-06-18 16:39:59 - SimpleLog - INFO: - update_step: 3900, online_eval_reward: -630.874 +2023-06-18 16:39:59 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -630.874, save the best model! +2023-06-18 16:40:00 - SimpleLog - INFO: - Interactor 0 finished episode 39 with reward -545.310 in 200 steps +2023-06-18 16:40:00 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward -751.373 in 200 steps +2023-06-18 16:40:00 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: -756.478 +2023-06-18 16:40:02 - SimpleLog - INFO: - update_step: 4100, online_eval_reward: -863.402 +2023-06-18 16:40:02 - SimpleLog - INFO: - Interactor 0 finished episode 41 with reward -646.219 in 200 steps +2023-06-18 16:40:02 - SimpleLog - INFO: - Interactor 1 finished episode 42 with reward -753.741 in 200 steps +2023-06-18 16:40:03 - SimpleLog - INFO: - update_step: 4200, online_eval_reward: -626.108 +2023-06-18 16:40:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -626.108, save the best model! +2023-06-18 16:40:04 - SimpleLog - INFO: - update_step: 4300, online_eval_reward: -748.564 +2023-06-18 16:40:05 - SimpleLog - INFO: - Interactor 0 finished episode 43 with reward -632.094 in 200 steps +2023-06-18 16:40:05 - SimpleLog - INFO: - Interactor 1 finished episode 44 with reward -751.567 in 200 steps +2023-06-18 16:40:05 - SimpleLog - INFO: - update_step: 4400, online_eval_reward: -649.743 +2023-06-18 16:40:06 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: -766.485 +2023-06-18 16:40:07 - SimpleLog - INFO: - Interactor 0 finished episode 45 with reward -627.878 in 200 steps +2023-06-18 16:40:07 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward -628.071 in 200 steps +2023-06-18 16:40:08 - SimpleLog - INFO: - update_step: 4600, online_eval_reward: -781.563 +2023-06-18 16:40:09 - SimpleLog - INFO: - update_step: 4700, online_eval_reward: -628.591 +2023-06-18 16:40:10 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward -509.268 in 200 steps +2023-06-18 16:40:10 - SimpleLog - INFO: - Interactor 1 finished episode 48 with reward -377.213 in 200 steps +2023-06-18 16:40:10 - SimpleLog - INFO: - update_step: 4800, online_eval_reward: -504.638 +2023-06-18 16:40:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -504.638, save the best model! +2023-06-18 16:40:11 - SimpleLog - INFO: - update_step: 4900, online_eval_reward: -530.351 +2023-06-18 16:40:12 - SimpleLog - INFO: - Interactor 0 finished episode 49 with reward -383.350 in 200 steps +2023-06-18 16:40:12 - SimpleLog - INFO: - Interactor 1 finished episode 50 with reward -501.978 in 200 steps +2023-06-18 16:40:13 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: -504.956 +2023-06-18 16:40:14 - SimpleLog - INFO: - update_step: 5100, online_eval_reward: -632.072 +2023-06-18 16:40:14 - SimpleLog - INFO: - Interactor 0 finished episode 51 with reward -255.278 in 200 steps +2023-06-18 16:40:14 - SimpleLog - INFO: - Interactor 1 finished episode 52 with reward -500.879 in 200 steps +2023-06-18 16:40:15 - SimpleLog - INFO: - update_step: 5200, online_eval_reward: -641.763 +2023-06-18 16:40:16 - SimpleLog - INFO: - update_step: 5300, online_eval_reward: -508.721 +2023-06-18 16:40:17 - SimpleLog - INFO: - Interactor 0 finished episode 53 with reward -257.886 in 200 steps +2023-06-18 16:40:17 - SimpleLog - INFO: - Interactor 1 finished episode 54 with reward -500.677 in 200 steps +2023-06-18 16:40:18 - SimpleLog - INFO: - update_step: 5400, online_eval_reward: -624.826 +2023-06-18 16:40:19 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: -504.471 +2023-06-18 16:40:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -504.471, save the best model! +2023-06-18 16:40:19 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward -259.141 in 200 steps +2023-06-18 16:40:19 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward -501.679 in 200 steps +2023-06-18 16:40:20 - SimpleLog - INFO: - update_step: 5600, online_eval_reward: -381.350 +2023-06-18 16:40:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -381.350, save the best model! +2023-06-18 16:40:21 - SimpleLog - INFO: - update_step: 5700, online_eval_reward: -627.468 +2023-06-18 16:40:22 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward -384.113 in 200 steps +2023-06-18 16:40:22 - SimpleLog - INFO: - Interactor 1 finished episode 58 with reward -401.693 in 200 steps +2023-06-18 16:40:23 - SimpleLog - INFO: - update_step: 5800, online_eval_reward: -627.865 +2023-06-18 16:40:24 - SimpleLog - INFO: - update_step: 5900, online_eval_reward: -524.992 +2023-06-18 16:40:24 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward -386.282 in 200 steps +2023-06-18 16:40:24 - SimpleLog - INFO: - Interactor 1 finished episode 60 with reward -377.906 in 200 steps +2023-06-18 16:40:25 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: -504.850 +2023-06-18 16:40:26 - SimpleLog - INFO: - update_step: 6100, online_eval_reward: -622.662 +2023-06-18 16:40:27 - SimpleLog - INFO: - Interactor 0 finished episode 61 with reward -264.980 in 200 steps +2023-06-18 16:40:27 - SimpleLog - INFO: - Interactor 1 finished episode 62 with reward -376.024 in 200 steps +2023-06-18 16:40:27 - SimpleLog - INFO: - update_step: 6200, online_eval_reward: -629.334 +2023-06-18 16:40:29 - SimpleLog - INFO: - update_step: 6300, online_eval_reward: -505.557 +2023-06-18 16:40:29 - SimpleLog - INFO: - Interactor 0 finished episode 63 with reward -258.428 in 200 steps +2023-06-18 16:40:29 - SimpleLog - INFO: - Interactor 1 finished episode 64 with reward -377.041 in 200 steps +2023-06-18 16:40:30 - SimpleLog - INFO: - update_step: 6400, online_eval_reward: -506.662 +2023-06-18 16:40:31 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: -504.294 +2023-06-18 16:40:32 - SimpleLog - INFO: - Interactor 0 finished episode 65 with reward -144.788 in 200 steps +2023-06-18 16:40:32 - SimpleLog - INFO: - Interactor 1 finished episode 66 with reward -250.861 in 200 steps +2023-06-18 16:40:32 - SimpleLog - INFO: - update_step: 6600, online_eval_reward: -506.432 +2023-06-18 16:40:34 - SimpleLog - INFO: - update_step: 6700, online_eval_reward: -503.358 +2023-06-18 16:40:34 - SimpleLog - INFO: - Interactor 0 finished episode 67 with reward -384.900 in 200 steps +2023-06-18 16:40:34 - SimpleLog - INFO: - Interactor 1 finished episode 68 with reward -503.686 in 200 steps +2023-06-18 16:40:35 - SimpleLog - INFO: - update_step: 6800, online_eval_reward: -610.874 +2023-06-18 16:40:36 - SimpleLog - INFO: - update_step: 6900, online_eval_reward: -507.600 +2023-06-18 16:40:37 - SimpleLog - INFO: - Interactor 0 finished episode 69 with reward -6.160 in 200 steps +2023-06-18 16:40:37 - SimpleLog - INFO: - Interactor 1 finished episode 70 with reward -249.738 in 200 steps +2023-06-18 16:40:37 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: -516.111 +2023-06-18 16:40:39 - SimpleLog - INFO: - update_step: 7100, online_eval_reward: -504.814 +2023-06-18 16:40:39 - SimpleLog - INFO: - Interactor 0 finished episode 71 with reward -130.383 in 200 steps +2023-06-18 16:40:39 - SimpleLog - INFO: - Interactor 1 finished episode 72 with reward -248.035 in 200 steps +2023-06-18 16:40:40 - SimpleLog - INFO: - update_step: 7200, online_eval_reward: -504.119 +2023-06-18 16:40:41 - SimpleLog - INFO: - update_step: 7300, online_eval_reward: -252.920 +2023-06-18 16:40:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -252.920, save the best model! +2023-06-18 16:40:42 - SimpleLog - INFO: - Interactor 0 finished episode 73 with reward -129.843 in 200 steps +2023-06-18 16:40:42 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward -123.091 in 200 steps +2023-06-18 16:40:42 - SimpleLog - INFO: - update_step: 7400, online_eval_reward: -504.046 +2023-06-18 16:40:44 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: -506.457 +2023-06-18 16:40:44 - SimpleLog - INFO: - Interactor 0 finished episode 75 with reward -9.244 in 200 steps +2023-06-18 16:40:44 - SimpleLog - INFO: - Interactor 1 finished episode 76 with reward -374.890 in 200 steps +2023-06-18 16:40:45 - SimpleLog - INFO: - update_step: 7600, online_eval_reward: -253.852 +2023-06-18 16:40:46 - SimpleLog - INFO: - update_step: 7700, online_eval_reward: -497.678 +2023-06-18 16:40:47 - SimpleLog - INFO: - Interactor 0 finished episode 77 with reward -257.436 in 200 steps +2023-06-18 16:40:47 - SimpleLog - INFO: - Interactor 1 finished episode 78 with reward -248.164 in 200 steps +2023-06-18 16:40:47 - SimpleLog - INFO: - update_step: 7800, online_eval_reward: -518.276 +2023-06-18 16:40:49 - SimpleLog - INFO: - update_step: 7900, online_eval_reward: -496.236 +2023-06-18 16:40:49 - SimpleLog - INFO: - Interactor 0 finished episode 79 with reward -129.262 in 200 steps +2023-06-18 16:40:49 - SimpleLog - INFO: - Interactor 1 finished episode 80 with reward -378.180 in 200 steps +2023-06-18 16:40:50 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: -505.930 +2023-06-18 16:40:51 - SimpleLog - INFO: - update_step: 8100, online_eval_reward: -505.368 +2023-06-18 16:40:52 - SimpleLog - INFO: - Interactor 0 finished episode 81 with reward -382.849 in 200 steps +2023-06-18 16:40:52 - SimpleLog - INFO: - Interactor 1 finished episode 82 with reward -501.592 in 200 steps +2023-06-18 16:40:52 - SimpleLog - INFO: - update_step: 8200, online_eval_reward: -512.991 +2023-06-18 16:40:54 - SimpleLog - INFO: - update_step: 8300, online_eval_reward: -504.157 +2023-06-18 16:40:54 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward -289.496 in 200 steps +2023-06-18 16:40:54 - SimpleLog - INFO: - Interactor 1 finished episode 84 with reward -379.101 in 200 steps +2023-06-18 16:40:55 - SimpleLog - INFO: - update_step: 8400, online_eval_reward: -471.989 +2023-06-18 16:40:56 - SimpleLog - INFO: - update_step: 8500, online_eval_reward: -378.024 +2023-06-18 16:40:57 - SimpleLog - INFO: - Interactor 0 finished episode 85 with reward -383.413 in 200 steps +2023-06-18 16:40:57 - SimpleLog - INFO: - Interactor 1 finished episode 86 with reward -377.348 in 200 steps +2023-06-18 16:40:57 - SimpleLog - INFO: - update_step: 8600, online_eval_reward: -504.045 +2023-06-18 16:40:59 - SimpleLog - INFO: - update_step: 8700, online_eval_reward: -622.723 +2023-06-18 16:40:59 - SimpleLog - INFO: - Interactor 0 finished episode 87 with reward -258.051 in 200 steps +2023-06-18 16:40:59 - SimpleLog - INFO: - Interactor 1 finished episode 88 with reward -378.418 in 200 steps +2023-06-18 16:41:00 - SimpleLog - INFO: - update_step: 8800, online_eval_reward: -504.854 +2023-06-18 16:41:01 - SimpleLog - INFO: - update_step: 8900, online_eval_reward: -501.113 +2023-06-18 16:41:02 - SimpleLog - INFO: - Interactor 0 finished episode 89 with reward -265.978 in 200 steps +2023-06-18 16:41:02 - SimpleLog - INFO: - Interactor 1 finished episode 90 with reward -377.551 in 200 steps +2023-06-18 16:41:02 - SimpleLog - INFO: - update_step: 9000, online_eval_reward: -627.357 +2023-06-18 16:41:04 - SimpleLog - INFO: - update_step: 9100, online_eval_reward: -378.242 +2023-06-18 16:41:04 - SimpleLog - INFO: - Interactor 0 finished episode 91 with reward -376.627 in 200 steps +2023-06-18 16:41:04 - SimpleLog - INFO: - Interactor 1 finished episode 92 with reward -379.475 in 200 steps +2023-06-18 16:41:05 - SimpleLog - INFO: - update_step: 9200, online_eval_reward: -523.777 +2023-06-18 16:41:06 - SimpleLog - INFO: - update_step: 9300, online_eval_reward: -392.154 +2023-06-18 16:41:07 - SimpleLog - INFO: - Interactor 0 finished episode 93 with reward -257.879 in 200 steps +2023-06-18 16:41:07 - SimpleLog - INFO: - Interactor 1 finished episode 94 with reward -364.066 in 200 steps +2023-06-18 16:41:07 - SimpleLog - INFO: - update_step: 9400, online_eval_reward: -505.073 +2023-06-18 16:41:09 - SimpleLog - INFO: - update_step: 9500, online_eval_reward: -392.630 +2023-06-18 16:41:09 - SimpleLog - INFO: - Interactor 0 finished episode 95 with reward -256.403 in 200 steps +2023-06-18 16:41:09 - SimpleLog - INFO: - Interactor 1 finished episode 96 with reward -378.919 in 200 steps +2023-06-18 16:41:10 - SimpleLog - INFO: - update_step: 9600, online_eval_reward: -611.083 +2023-06-18 16:41:11 - SimpleLog - INFO: - update_step: 9700, online_eval_reward: -575.006 +2023-06-18 16:41:12 - SimpleLog - INFO: - Interactor 0 finished episode 97 with reward -257.988 in 200 steps +2023-06-18 16:41:12 - SimpleLog - INFO: - Interactor 1 finished episode 98 with reward -375.953 in 200 steps +2023-06-18 16:41:12 - SimpleLog - INFO: - update_step: 9800, online_eval_reward: -504.909 +2023-06-18 16:41:14 - SimpleLog - INFO: - update_step: 9900, online_eval_reward: -521.546 +2023-06-18 16:41:14 - SimpleLog - INFO: - Interactor 0 finished episode 99 with reward -257.814 in 200 steps +2023-06-18 16:41:14 - SimpleLog - INFO: - Interactor 1 finished episode 100 with reward -376.679 in 200 steps +2023-06-18 16:41:15 - SimpleLog - INFO: - update_step: 10000, online_eval_reward: -498.104 +2023-06-18 16:41:16 - SimpleLog - INFO: - update_step: 10100, online_eval_reward: -505.148 +2023-06-18 16:41:17 - SimpleLog - INFO: - Interactor 0 finished episode 101 with reward -383.380 in 200 steps +2023-06-18 16:41:17 - SimpleLog - INFO: - Interactor 1 finished episode 102 with reward -376.594 in 200 steps +2023-06-18 16:41:17 - SimpleLog - INFO: - update_step: 10200, online_eval_reward: -502.743 +2023-06-18 16:41:18 - SimpleLog - INFO: - update_step: 10300, online_eval_reward: -495.894 +2023-06-18 16:41:19 - SimpleLog - INFO: - Interactor 0 finished episode 103 with reward -258.215 in 200 steps +2023-06-18 16:41:19 - SimpleLog - INFO: - Interactor 1 finished episode 104 with reward -252.459 in 200 steps +2023-06-18 16:41:20 - SimpleLog - INFO: - update_step: 10400, online_eval_reward: -428.521 +2023-06-18 16:41:21 - SimpleLog - INFO: - update_step: 10500, online_eval_reward: -509.165 +2023-06-18 16:41:21 - SimpleLog - INFO: - Interactor 0 finished episode 105 with reward -237.254 in 200 steps +2023-06-18 16:41:21 - SimpleLog - INFO: - Interactor 1 finished episode 106 with reward -249.686 in 200 steps +2023-06-18 16:41:22 - SimpleLog - INFO: - update_step: 10600, online_eval_reward: -378.710 +2023-06-18 16:41:23 - SimpleLog - INFO: - update_step: 10700, online_eval_reward: -467.916 +2023-06-18 16:41:24 - SimpleLog - INFO: - Interactor 0 finished episode 107 with reward -380.161 in 200 steps +2023-06-18 16:41:24 - SimpleLog - INFO: - Interactor 1 finished episode 108 with reward -377.340 in 200 steps +2023-06-18 16:41:25 - SimpleLog - INFO: - update_step: 10800, online_eval_reward: -504.152 +2023-06-18 16:41:26 - SimpleLog - INFO: - update_step: 10900, online_eval_reward: -616.149 +2023-06-18 16:41:26 - SimpleLog - INFO: - Interactor 0 finished episode 109 with reward -256.526 in 200 steps +2023-06-18 16:41:26 - SimpleLog - INFO: - Interactor 1 finished episode 110 with reward -250.052 in 200 steps +2023-06-18 16:41:27 - SimpleLog - INFO: - update_step: 11000, online_eval_reward: -624.551 +2023-06-18 16:41:28 - SimpleLog - INFO: - update_step: 11100, online_eval_reward: -626.679 +2023-06-18 16:41:29 - SimpleLog - INFO: - Interactor 0 finished episode 111 with reward -255.673 in 200 steps +2023-06-18 16:41:29 - SimpleLog - INFO: - Interactor 1 finished episode 112 with reward -249.592 in 200 steps +2023-06-18 16:41:30 - SimpleLog - INFO: - update_step: 11200, online_eval_reward: -504.051 +2023-06-18 16:41:31 - SimpleLog - INFO: - update_step: 11300, online_eval_reward: -627.940 +2023-06-18 16:41:31 - SimpleLog - INFO: - Interactor 0 finished episode 113 with reward -257.611 in 200 steps +2023-06-18 16:41:31 - SimpleLog - INFO: - Interactor 1 finished episode 114 with reward -375.881 in 200 steps +2023-06-18 16:41:32 - SimpleLog - INFO: - update_step: 11400, online_eval_reward: -603.049 +2023-06-18 16:41:33 - SimpleLog - INFO: - update_step: 11500, online_eval_reward: -471.987 +2023-06-18 16:41:34 - SimpleLog - INFO: - Interactor 0 finished episode 115 with reward -382.501 in 200 steps +2023-06-18 16:41:34 - SimpleLog - INFO: - Interactor 1 finished episode 116 with reward -252.038 in 200 steps +2023-06-18 16:41:35 - SimpleLog - INFO: - update_step: 11600, online_eval_reward: -503.790 +2023-06-18 16:41:36 - SimpleLog - INFO: - update_step: 11700, online_eval_reward: -503.284 +2023-06-18 16:41:36 - SimpleLog - INFO: - Interactor 0 finished episode 117 with reward -264.405 in 200 steps +2023-06-18 16:41:36 - SimpleLog - INFO: - Interactor 1 finished episode 118 with reward -502.513 in 200 steps +2023-06-18 16:41:37 - SimpleLog - INFO: - update_step: 11800, online_eval_reward: -627.830 +2023-06-18 16:41:38 - SimpleLog - INFO: - update_step: 11900, online_eval_reward: -622.682 +2023-06-18 16:41:39 - SimpleLog - INFO: - Interactor 0 finished episode 119 with reward -344.907 in 200 steps +2023-06-18 16:41:39 - SimpleLog - INFO: - Interactor 1 finished episode 120 with reward -405.190 in 200 steps +2023-06-18 16:41:40 - SimpleLog - INFO: - update_step: 12000, online_eval_reward: -503.674 +2023-06-18 16:41:41 - SimpleLog - INFO: - update_step: 12100, online_eval_reward: -628.032 +2023-06-18 16:41:42 - SimpleLog - INFO: - Interactor 0 finished episode 121 with reward -384.215 in 200 steps +2023-06-18 16:41:42 - SimpleLog - INFO: - Interactor 1 finished episode 122 with reward -432.613 in 200 steps +2023-06-18 16:41:42 - SimpleLog - INFO: - update_step: 12200, online_eval_reward: -503.886 +2023-06-18 16:41:44 - SimpleLog - INFO: - update_step: 12300, online_eval_reward: -503.432 +2023-06-18 16:41:44 - SimpleLog - INFO: - Interactor 0 finished episode 123 with reward -383.556 in 200 steps +2023-06-18 16:41:44 - SimpleLog - INFO: - Interactor 1 finished episode 124 with reward -415.292 in 200 steps +2023-06-18 16:41:45 - SimpleLog - INFO: - update_step: 12400, online_eval_reward: -549.750 +2023-06-18 16:41:46 - SimpleLog - INFO: - update_step: 12500, online_eval_reward: -500.803 +2023-06-18 16:41:47 - SimpleLog - INFO: - Interactor 0 finished episode 125 with reward -384.129 in 200 steps +2023-06-18 16:41:47 - SimpleLog - INFO: - Interactor 1 finished episode 126 with reward -378.644 in 200 steps +2023-06-18 16:41:47 - SimpleLog - INFO: - update_step: 12600, online_eval_reward: -614.173 +2023-06-18 16:41:49 - SimpleLog - INFO: - update_step: 12700, online_eval_reward: -504.940 +2023-06-18 16:41:49 - SimpleLog - INFO: - Interactor 0 finished episode 127 with reward -384.349 in 200 steps +2023-06-18 16:41:49 - SimpleLog - INFO: - Interactor 1 finished episode 128 with reward -378.360 in 200 steps +2023-06-18 16:41:50 - SimpleLog - INFO: - update_step: 12800, online_eval_reward: -627.797 +2023-06-18 16:41:51 - SimpleLog - INFO: - update_step: 12900, online_eval_reward: -597.391 +2023-06-18 16:41:52 - SimpleLog - INFO: - Interactor 0 finished episode 129 with reward -383.978 in 200 steps +2023-06-18 16:41:52 - SimpleLog - INFO: - Interactor 1 finished episode 130 with reward -380.662 in 200 steps +2023-06-18 16:41:52 - SimpleLog - INFO: - update_step: 13000, online_eval_reward: -504.481 +2023-06-18 16:41:54 - SimpleLog - INFO: - update_step: 13100, online_eval_reward: -502.841 +2023-06-18 16:41:54 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward -383.082 in 200 steps +2023-06-18 16:41:54 - SimpleLog - INFO: - Interactor 1 finished episode 132 with reward -377.854 in 200 steps +2023-06-18 16:41:55 - SimpleLog - INFO: - update_step: 13200, online_eval_reward: -606.172 +2023-06-18 16:41:56 - SimpleLog - INFO: - update_step: 13300, online_eval_reward: -627.079 +2023-06-18 16:41:57 - SimpleLog - INFO: - Interactor 0 finished episode 133 with reward -261.498 in 200 steps +2023-06-18 16:41:57 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward -378.427 in 200 steps +2023-06-18 16:41:57 - SimpleLog - INFO: - update_step: 13400, online_eval_reward: -621.482 +2023-06-18 16:41:59 - SimpleLog - INFO: - update_step: 13500, online_eval_reward: -627.802 +2023-06-18 16:41:59 - SimpleLog - INFO: - Interactor 0 finished episode 135 with reward -259.911 in 200 steps +2023-06-18 16:41:59 - SimpleLog - INFO: - Interactor 1 finished episode 136 with reward -254.313 in 200 steps +2023-06-18 16:42:00 - SimpleLog - INFO: - update_step: 13600, online_eval_reward: -554.930 +2023-06-18 16:42:01 - SimpleLog - INFO: - update_step: 13700, online_eval_reward: -568.048 +2023-06-18 16:42:02 - SimpleLog - INFO: - Interactor 0 finished episode 137 with reward -292.799 in 200 steps +2023-06-18 16:42:02 - SimpleLog - INFO: - Interactor 1 finished episode 138 with reward -378.388 in 200 steps +2023-06-18 16:42:02 - SimpleLog - INFO: - update_step: 13800, online_eval_reward: -536.149 +2023-06-18 16:42:03 - SimpleLog - INFO: - update_step: 13900, online_eval_reward: -506.025 +2023-06-18 16:42:04 - SimpleLog - INFO: - Interactor 0 finished episode 139 with reward -259.192 in 200 steps +2023-06-18 16:42:04 - SimpleLog - INFO: - Interactor 1 finished episode 140 with reward -378.459 in 200 steps +2023-06-18 16:42:05 - SimpleLog - INFO: - update_step: 14000, online_eval_reward: -521.703 +2023-06-18 16:42:06 - SimpleLog - INFO: - update_step: 14100, online_eval_reward: -510.447 +2023-06-18 16:42:07 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward -261.268 in 200 steps +2023-06-18 16:42:07 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward -378.171 in 200 steps +2023-06-18 16:42:07 - SimpleLog - INFO: - update_step: 14200, online_eval_reward: -522.750 +2023-06-18 16:42:09 - SimpleLog - INFO: - update_step: 14300, online_eval_reward: -499.859 +2023-06-18 16:42:09 - SimpleLog - INFO: - Interactor 0 finished episode 143 with reward -258.966 in 200 steps +2023-06-18 16:42:09 - SimpleLog - INFO: - Interactor 1 finished episode 144 with reward -377.578 in 200 steps +2023-06-18 16:42:10 - SimpleLog - INFO: - update_step: 14400, online_eval_reward: -503.152 +2023-06-18 16:42:11 - SimpleLog - INFO: - update_step: 14500, online_eval_reward: -504.464 +2023-06-18 16:42:12 - SimpleLog - INFO: - Interactor 0 finished episode 145 with reward -259.010 in 200 steps +2023-06-18 16:42:12 - SimpleLog - INFO: - Interactor 1 finished episode 146 with reward -378.754 in 200 steps +2023-06-18 16:42:12 - SimpleLog - INFO: - update_step: 14600, online_eval_reward: -407.771 +2023-06-18 16:42:13 - SimpleLog - INFO: - update_step: 14700, online_eval_reward: -504.594 +2023-06-18 16:42:14 - SimpleLog - INFO: - Interactor 0 finished episode 147 with reward -265.800 in 200 steps +2023-06-18 16:42:14 - SimpleLog - INFO: - Interactor 1 finished episode 148 with reward -379.020 in 200 steps +2023-06-18 16:42:15 - SimpleLog - INFO: - update_step: 14800, online_eval_reward: -521.266 +2023-06-18 16:42:16 - SimpleLog - INFO: - update_step: 14900, online_eval_reward: -504.800 +2023-06-18 16:42:17 - SimpleLog - INFO: - Interactor 0 finished episode 149 with reward -259.717 in 200 steps +2023-06-18 16:42:17 - SimpleLog - INFO: - Interactor 1 finished episode 150 with reward -371.442 in 200 steps +2023-06-18 16:42:17 - SimpleLog - INFO: - update_step: 15000, online_eval_reward: -557.607 +2023-06-18 16:42:18 - SimpleLog - INFO: - update_step: 15100, online_eval_reward: -503.430 +2023-06-18 16:42:19 - SimpleLog - INFO: - Interactor 0 finished episode 151 with reward -259.884 in 200 steps +2023-06-18 16:42:19 - SimpleLog - INFO: - Interactor 1 finished episode 152 with reward -378.490 in 200 steps +2023-06-18 16:42:20 - SimpleLog - INFO: - update_step: 15200, online_eval_reward: -503.907 +2023-06-18 16:42:21 - SimpleLog - INFO: - update_step: 15300, online_eval_reward: -504.686 +2023-06-18 16:42:22 - SimpleLog - INFO: - Interactor 0 finished episode 153 with reward -137.131 in 200 steps +2023-06-18 16:42:22 - SimpleLog - INFO: - Interactor 1 finished episode 154 with reward -256.148 in 200 steps +2023-06-18 16:42:22 - SimpleLog - INFO: - update_step: 15400, online_eval_reward: -503.950 +2023-06-18 16:42:23 - SimpleLog - INFO: - update_step: 15500, online_eval_reward: -377.807 +2023-06-18 16:42:24 - SimpleLog - INFO: - Interactor 0 finished episode 155 with reward -182.937 in 200 steps +2023-06-18 16:42:24 - SimpleLog - INFO: - Interactor 1 finished episode 156 with reward -228.954 in 200 steps +2023-06-18 16:42:25 - SimpleLog - INFO: - update_step: 15600, online_eval_reward: -633.895 +2023-06-18 16:42:26 - SimpleLog - INFO: - update_step: 15700, online_eval_reward: -504.156 +2023-06-18 16:42:27 - SimpleLog - INFO: - Interactor 0 finished episode 157 with reward -135.201 in 200 steps +2023-06-18 16:42:27 - SimpleLog - INFO: - Interactor 1 finished episode 158 with reward -127.702 in 200 steps +2023-06-18 16:42:27 - SimpleLog - INFO: - update_step: 15800, online_eval_reward: -504.442 +2023-06-18 16:42:28 - SimpleLog - INFO: - update_step: 15900, online_eval_reward: -378.320 +2023-06-18 16:42:29 - SimpleLog - INFO: - Interactor 0 finished episode 159 with reward -140.012 in 200 steps +2023-06-18 16:42:29 - SimpleLog - INFO: - Interactor 1 finished episode 160 with reward -254.871 in 200 steps +2023-06-18 16:42:30 - SimpleLog - INFO: - update_step: 16000, online_eval_reward: -758.459 +2023-06-18 16:42:31 - SimpleLog - INFO: - update_step: 16100, online_eval_reward: -528.790 +2023-06-18 16:42:32 - SimpleLog - INFO: - Interactor 0 finished episode 161 with reward -260.244 in 200 steps +2023-06-18 16:42:32 - SimpleLog - INFO: - Interactor 1 finished episode 162 with reward -378.559 in 200 steps +2023-06-18 16:42:32 - SimpleLog - INFO: - update_step: 16200, online_eval_reward: -512.799 +2023-06-18 16:42:33 - SimpleLog - INFO: - update_step: 16300, online_eval_reward: -500.630 +2023-06-18 16:42:34 - SimpleLog - INFO: - Interactor 0 finished episode 163 with reward -135.817 in 200 steps +2023-06-18 16:42:34 - SimpleLog - INFO: - Interactor 1 finished episode 164 with reward -260.366 in 200 steps +2023-06-18 16:42:35 - SimpleLog - INFO: - update_step: 16400, online_eval_reward: -514.297 +2023-06-18 16:42:36 - SimpleLog - INFO: - update_step: 16500, online_eval_reward: -504.048 +2023-06-18 16:42:37 - SimpleLog - INFO: - Interactor 0 finished episode 165 with reward -13.423 in 200 steps +2023-06-18 16:42:37 - SimpleLog - INFO: - Interactor 1 finished episode 166 with reward -132.449 in 200 steps +2023-06-18 16:42:37 - SimpleLog - INFO: - update_step: 16600, online_eval_reward: -504.361 +2023-06-18 16:42:39 - SimpleLog - INFO: - update_step: 16700, online_eval_reward: -503.206 +2023-06-18 16:42:39 - SimpleLog - INFO: - Interactor 0 finished episode 167 with reward -139.457 in 200 steps +2023-06-18 16:42:39 - SimpleLog - INFO: - Interactor 1 finished episode 168 with reward -374.078 in 200 steps +2023-06-18 16:42:40 - SimpleLog - INFO: - update_step: 16800, online_eval_reward: -453.025 +2023-06-18 16:42:41 - SimpleLog - INFO: - update_step: 16900, online_eval_reward: -377.225 +2023-06-18 16:42:42 - SimpleLog - INFO: - Interactor 0 finished episode 169 with reward -277.210 in 200 steps +2023-06-18 16:42:42 - SimpleLog - INFO: - Interactor 1 finished episode 170 with reward -252.749 in 200 steps +2023-06-18 16:42:42 - SimpleLog - INFO: - update_step: 17000, online_eval_reward: -494.961 +2023-06-18 16:42:44 - SimpleLog - INFO: - update_step: 17100, online_eval_reward: -628.388 +2023-06-18 16:42:44 - SimpleLog - INFO: - Interactor 0 finished episode 171 with reward -186.962 in 200 steps +2023-06-18 16:42:44 - SimpleLog - INFO: - Interactor 1 finished episode 172 with reward -279.426 in 200 steps +2023-06-18 16:42:45 - SimpleLog - INFO: - update_step: 17200, online_eval_reward: -403.423 +2023-06-18 16:42:46 - SimpleLog - INFO: - update_step: 17300, online_eval_reward: -377.556 +2023-06-18 16:42:47 - SimpleLog - INFO: - Interactor 0 finished episode 173 with reward -129.997 in 200 steps +2023-06-18 16:42:47 - SimpleLog - INFO: - Interactor 1 finished episode 174 with reward -249.593 in 200 steps +2023-06-18 16:42:47 - SimpleLog - INFO: - update_step: 17400, online_eval_reward: -125.928 +2023-06-18 16:42:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -125.928, save the best model! +2023-06-18 16:42:49 - SimpleLog - INFO: - update_step: 17500, online_eval_reward: -252.264 +2023-06-18 16:42:49 - SimpleLog - INFO: - Interactor 0 finished episode 175 with reward -333.461 in 200 steps +2023-06-18 16:42:49 - SimpleLog - INFO: - Interactor 1 finished episode 176 with reward -380.684 in 200 steps +2023-06-18 16:42:50 - SimpleLog - INFO: - update_step: 17600, online_eval_reward: -377.967 +2023-06-18 16:42:51 - SimpleLog - INFO: - update_step: 17700, online_eval_reward: -502.527 +2023-06-18 16:42:52 - SimpleLog - INFO: - Interactor 0 finished episode 177 with reward -382.695 in 200 steps +2023-06-18 16:42:52 - SimpleLog - INFO: - Interactor 1 finished episode 178 with reward -377.542 in 200 steps +2023-06-18 16:42:52 - SimpleLog - INFO: - update_step: 17800, online_eval_reward: -503.022 +2023-06-18 16:42:54 - SimpleLog - INFO: - update_step: 17900, online_eval_reward: -509.103 +2023-06-18 16:42:54 - SimpleLog - INFO: - Interactor 0 finished episode 179 with reward -382.172 in 200 steps +2023-06-18 16:42:54 - SimpleLog - INFO: - Interactor 1 finished episode 180 with reward -500.410 in 200 steps +2023-06-18 16:42:55 - SimpleLog - INFO: - update_step: 18000, online_eval_reward: -518.620 +2023-06-18 16:42:56 - SimpleLog - INFO: - update_step: 18100, online_eval_reward: -502.824 +2023-06-18 16:42:57 - SimpleLog - INFO: - Interactor 0 finished episode 181 with reward -381.368 in 200 steps +2023-06-18 16:42:57 - SimpleLog - INFO: - Interactor 1 finished episode 182 with reward -500.005 in 200 steps +2023-06-18 16:42:58 - SimpleLog - INFO: - update_step: 18200, online_eval_reward: -748.451 +2023-06-18 16:42:59 - SimpleLog - INFO: - update_step: 18300, online_eval_reward: -519.708 +2023-06-18 16:42:59 - SimpleLog - INFO: - Interactor 0 finished episode 183 with reward -382.336 in 200 steps +2023-06-18 16:42:59 - SimpleLog - INFO: - Interactor 1 finished episode 184 with reward -377.370 in 200 steps +2023-06-18 16:43:00 - SimpleLog - INFO: - update_step: 18400, online_eval_reward: -503.253 +2023-06-18 16:43:01 - SimpleLog - INFO: - update_step: 18500, online_eval_reward: -504.352 +2023-06-18 16:43:02 - SimpleLog - INFO: - Interactor 0 finished episode 185 with reward -381.589 in 200 steps +2023-06-18 16:43:02 - SimpleLog - INFO: - Interactor 1 finished episode 186 with reward -498.094 in 200 steps +2023-06-18 16:43:03 - SimpleLog - INFO: - update_step: 18600, online_eval_reward: -621.553 +2023-06-18 16:43:04 - SimpleLog - INFO: - update_step: 18700, online_eval_reward: -503.396 +2023-06-18 16:43:04 - SimpleLog - INFO: - Interactor 0 finished episode 187 with reward -381.901 in 200 steps +2023-06-18 16:43:04 - SimpleLog - INFO: - Interactor 1 finished episode 188 with reward -500.203 in 200 steps +2023-06-18 16:43:05 - SimpleLog - INFO: - update_step: 18800, online_eval_reward: -378.566 +2023-06-18 16:43:06 - SimpleLog - INFO: - update_step: 18900, online_eval_reward: -503.793 +2023-06-18 16:43:07 - SimpleLog - INFO: - Interactor 0 finished episode 189 with reward -381.694 in 200 steps +2023-06-18 16:43:07 - SimpleLog - INFO: - Interactor 1 finished episode 190 with reward -500.428 in 200 steps +2023-06-18 16:43:08 - SimpleLog - INFO: - update_step: 19000, online_eval_reward: -502.545 +2023-06-18 16:43:09 - SimpleLog - INFO: - update_step: 19100, online_eval_reward: -501.932 +2023-06-18 16:43:10 - SimpleLog - INFO: - Interactor 0 finished episode 191 with reward -268.149 in 200 steps +2023-06-18 16:43:10 - SimpleLog - INFO: - Interactor 1 finished episode 192 with reward -376.541 in 200 steps +2023-06-18 16:43:10 - SimpleLog - INFO: - update_step: 19200, online_eval_reward: -558.227 +2023-06-18 16:43:12 - SimpleLog - INFO: - update_step: 19300, online_eval_reward: -517.582 +2023-06-18 16:43:12 - SimpleLog - INFO: - Interactor 0 finished episode 193 with reward -259.277 in 200 steps +2023-06-18 16:43:12 - SimpleLog - INFO: - Interactor 1 finished episode 194 with reward -377.712 in 200 steps +2023-06-18 16:43:13 - SimpleLog - INFO: - update_step: 19400, online_eval_reward: -500.636 +2023-06-18 16:43:14 - SimpleLog - INFO: - update_step: 19500, online_eval_reward: -377.581 +2023-06-18 16:43:15 - SimpleLog - INFO: - Interactor 0 finished episode 195 with reward -258.805 in 200 steps +2023-06-18 16:43:15 - SimpleLog - INFO: - Interactor 1 finished episode 196 with reward -374.762 in 200 steps +2023-06-18 16:43:15 - SimpleLog - INFO: - update_step: 19600, online_eval_reward: -125.934 +2023-06-18 16:43:17 - SimpleLog - INFO: - update_step: 19700, online_eval_reward: -502.898 +2023-06-18 16:43:17 - SimpleLog - INFO: - Interactor 0 finished episode 197 with reward -134.881 in 200 steps +2023-06-18 16:43:17 - SimpleLog - INFO: - Interactor 1 finished episode 198 with reward -274.250 in 200 steps +2023-06-18 16:43:18 - SimpleLog - INFO: - update_step: 19800, online_eval_reward: -377.947 +2023-06-18 16:43:19 - SimpleLog - INFO: - update_step: 19900, online_eval_reward: -380.967 +2023-06-18 16:43:20 - SimpleLog - INFO: - Interactor 0 finished episode 199 with reward -131.490 in 200 steps +2023-06-18 16:43:20 - SimpleLog - INFO: - Interactor 1 finished episode 200 with reward -254.782 in 200 steps +2023-06-18 16:43:20 - SimpleLog - INFO: - Finish training! Time cost: 248.411 s diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/100 b/Train_Pendulum-v1_SAC_20230618-163911/models/100 new file mode 100644 index 0000000000000000000000000000000000000000..259d973bacae47b6001bb41a93f978d4cf1804e4 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6607973c1581ba4c3b8799d4376360708a60cd801b603549605dde4ac4d26aaa +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1000 b/Train_Pendulum-v1_SAC_20230618-163911/models/1000 new file mode 100644 index 0000000000000000000000000000000000000000..15d929a99d395d964f44bfc91b0ba02896d8cf97 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f343139d2775d5e39cc655b23e115f6180e6624cc12df75622fb1425a82a709 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10000 b/Train_Pendulum-v1_SAC_20230618-163911/models/10000 new file mode 100644 index 0000000000000000000000000000000000000000..a6ab7b9a69d6b5fe4d1ecc54828e87a6548b49d8 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7053581566e0070608f66e30f3b1a2806ff44a347e49bea615c53fb71fa80b7b +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10100 b/Train_Pendulum-v1_SAC_20230618-163911/models/10100 new file mode 100644 index 0000000000000000000000000000000000000000..44d86bc0e16e7d92f4f3453757bb5c92e07fa256 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744e25f444f803c9287d9e4a1778778f566112f62a8730f705f72525c72e1647 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10200 b/Train_Pendulum-v1_SAC_20230618-163911/models/10200 new file mode 100644 index 0000000000000000000000000000000000000000..dbb9c3d8efee1e22536e31d57858afd6674286e8 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64688b841083f83a8b2c3998d3e3402f2cf928babf50cb4b4c8be1be6ee7c644 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10300 b/Train_Pendulum-v1_SAC_20230618-163911/models/10300 new file mode 100644 index 0000000000000000000000000000000000000000..0fa962a9524c93da21b68a5ddeb57ef7c78ddca7 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc1df6de020679ff0466c501b4dcbd3c3522f6a25b75d0bb4dc2b1a19f41dd7 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10400 b/Train_Pendulum-v1_SAC_20230618-163911/models/10400 new file mode 100644 index 0000000000000000000000000000000000000000..dbe79a40bd498dd6bcc20124955fc128830da68c --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ee333a2d2a7bef53b0e173c46c9d6bcd3a6155be2f8d48b8550f89134ac51dc +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10500 b/Train_Pendulum-v1_SAC_20230618-163911/models/10500 new file mode 100644 index 0000000000000000000000000000000000000000..31aba396f65bfe8b13ca4120278d88cb1c9ec99f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fa2ffbb8716a53878c596d90e4dfbab4aca0ef15d2ab20cf8790ebe7d54780f +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10600 b/Train_Pendulum-v1_SAC_20230618-163911/models/10600 new file mode 100644 index 0000000000000000000000000000000000000000..cae8841310727a838fd6695075634f306abc50cb --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8962ffc0f02dccd583bdf950ed38722c629e27c6de3720462a8afd3e3e60570 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10700 b/Train_Pendulum-v1_SAC_20230618-163911/models/10700 new file mode 100644 index 0000000000000000000000000000000000000000..b88ea608f425d786a34f85cf91e8372cca73aa6f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83970e12670c63a206ddf467869b89aa8c3e0651a2e8e9ab8241e9589b1d3c84 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10800 b/Train_Pendulum-v1_SAC_20230618-163911/models/10800 new file mode 100644 index 0000000000000000000000000000000000000000..40705eebd4cc224a0802638961bdaa068aa580f9 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b938f5f4cb442cddc47aa55d7fceef27a593f8b7d3b60bea04cf9da6a3234a8d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/10900 b/Train_Pendulum-v1_SAC_20230618-163911/models/10900 new file mode 100644 index 0000000000000000000000000000000000000000..0f3ac3d2f78c308ef1a5e5461dd2d0e5e1145fc2 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/10900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c645b696b549ff06072a9dc08e1478faee681db9dc566d69ca2a83f62475750c +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1100 b/Train_Pendulum-v1_SAC_20230618-163911/models/1100 new file mode 100644 index 0000000000000000000000000000000000000000..c16ec5a3963930da63b8b798107d16991c1156de --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ced2e7040447f293adafcb38f7ea7903cc9ece300709f70f440c115842fa99 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11000 b/Train_Pendulum-v1_SAC_20230618-163911/models/11000 new file mode 100644 index 0000000000000000000000000000000000000000..dfa88f7c900f828774f5d7049fe823d7004650dd --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb1075600544d7b6feb3fdd4703c3ea6db3f69724260eda201ccad904cc6009 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11100 b/Train_Pendulum-v1_SAC_20230618-163911/models/11100 new file mode 100644 index 0000000000000000000000000000000000000000..39431be5fe1524ea18122b6b70475e12e0d85a21 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bed910238b9f159851d3bbc21a3fc9ddc23af43406ea918fd64c2907d2e265 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11200 b/Train_Pendulum-v1_SAC_20230618-163911/models/11200 new file mode 100644 index 0000000000000000000000000000000000000000..dcbcb36a7f8f4a2874974f02f066690173915c97 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c51d2b7943f39214d82a4338e37e8a0199f275f6e6c38cfd00e2e3d9bc9f5c +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11300 b/Train_Pendulum-v1_SAC_20230618-163911/models/11300 new file mode 100644 index 0000000000000000000000000000000000000000..d900d705b38c0122ebf8bb502ac24f6a0efe9225 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e018ac4f4cc1ff85daf745f47d40471cebfb1ab2502a2d4fe102895287158c +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11400 b/Train_Pendulum-v1_SAC_20230618-163911/models/11400 new file mode 100644 index 0000000000000000000000000000000000000000..39e978d9448597d63e805f0389370b094aece6a5 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440a8d8d4a060bc410c7ba2280a8ff76593ae91320ab2f77201781def0bba9cb +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11500 b/Train_Pendulum-v1_SAC_20230618-163911/models/11500 new file mode 100644 index 0000000000000000000000000000000000000000..54cf17f46d258448364581d37140d107152ccf6c --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f228aaa642334dc7791c0074fe99794363e560491b878a8d642c5ac9611ce45 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11600 b/Train_Pendulum-v1_SAC_20230618-163911/models/11600 new file mode 100644 index 0000000000000000000000000000000000000000..126e8a2385276074995904e56a0ab418b2e03ea4 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1fc2c17b4e53e835f593468cb07978963f21cfea09f176320a837818c10f12c +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11700 b/Train_Pendulum-v1_SAC_20230618-163911/models/11700 new file mode 100644 index 0000000000000000000000000000000000000000..65dda150dd37c5df8a93d9992fd3716364b76047 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdad3c8cb8964855d9013803d0d09e2d596dcd7ee5af4dec8e40e862d2ad45e4 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11800 b/Train_Pendulum-v1_SAC_20230618-163911/models/11800 new file mode 100644 index 0000000000000000000000000000000000000000..be6df9430a0d975e81ee63a27cd75a26746030ef --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3587e2bb5853e0e150139a358d071f79dfa2b636630fd5a93fa9974f06bd1539 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/11900 b/Train_Pendulum-v1_SAC_20230618-163911/models/11900 new file mode 100644 index 0000000000000000000000000000000000000000..1a74f423d4192c10611d444992ec5ce094d9bae9 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/11900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20252803de7591bea432335559dc71a1b7ada510e680176edb733bc6dbbd582d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1200 b/Train_Pendulum-v1_SAC_20230618-163911/models/1200 new file mode 100644 index 0000000000000000000000000000000000000000..83620dcc8e3b14e515e7ae5e0f22150b3bba317c --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c889b18b770bd8a886aa129a1628ed420ea454dfc2704787276cc937d4098d66 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12000 b/Train_Pendulum-v1_SAC_20230618-163911/models/12000 new file mode 100644 index 0000000000000000000000000000000000000000..b47250cd464625a8820b1c1057f0f3ac29c7cf8e --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d568eebdf95b816da1a22471bd69c32602bb445d65b2ba88d93b080b3ada7c +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12100 b/Train_Pendulum-v1_SAC_20230618-163911/models/12100 new file mode 100644 index 0000000000000000000000000000000000000000..37177fab0e72a94ee6165a1af4e7b645735a3365 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be61aa2f1019e8ed023ab92d71141d5e7b64783784d092082393560d14584e9 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12200 b/Train_Pendulum-v1_SAC_20230618-163911/models/12200 new file mode 100644 index 0000000000000000000000000000000000000000..91dba3b37795dba37073fa55100fc33de7be55eb --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8a74a7bd508330342497b0e814beb5d763ee1e5bf6d1bb07686ee2f93a205a3 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12300 b/Train_Pendulum-v1_SAC_20230618-163911/models/12300 new file mode 100644 index 0000000000000000000000000000000000000000..f4767f93d77e694621da38a681168cd2a95d35dd --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b39147fe5f4a44b977ebf7c43346ce1cf85b8cb6e216cad7a9c43b1163559be +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12400 b/Train_Pendulum-v1_SAC_20230618-163911/models/12400 new file mode 100644 index 0000000000000000000000000000000000000000..7293ef5a646ea017912e90bc3a70b02a3e027f46 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc1b9ac35084e37fbe320e07b3b87e2a1139f9913aacbd351405bf16f5a00ba +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12500 b/Train_Pendulum-v1_SAC_20230618-163911/models/12500 new file mode 100644 index 0000000000000000000000000000000000000000..5c10637733ce98b83eef85f3fab07356312c89ca --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68aa800bba3c2802c5637067f57c9cca77e04058b5da96d25a7331ba49682b1b +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12600 b/Train_Pendulum-v1_SAC_20230618-163911/models/12600 new file mode 100644 index 0000000000000000000000000000000000000000..56a4a234df960d0eeb9a3b5fe9115420bbcf1817 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914c2407f42d89f012930f7599c7005c46cdbc123e4325d65acc2d4441ae007d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12700 b/Train_Pendulum-v1_SAC_20230618-163911/models/12700 new file mode 100644 index 0000000000000000000000000000000000000000..7184de664137581c4c11654b40ce984fb21475e2 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:424478d6a4b86e391c98ac9b137586649aa95cabf0fac752ec1ee8685a3a3819 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12800 b/Train_Pendulum-v1_SAC_20230618-163911/models/12800 new file mode 100644 index 0000000000000000000000000000000000000000..581203c55c05b74d3f52b01447467655d6e1d9f4 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371ed90e0af2ee87bbfa8fee59da5efcea081f075249dfab81ae409724eeded2 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/12900 b/Train_Pendulum-v1_SAC_20230618-163911/models/12900 new file mode 100644 index 0000000000000000000000000000000000000000..8e9eba5f57d0858a9a0003ebcfc850fee1096159 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/12900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83814996fb5bfe8bda1a2297e0884812a95039486f293838b24ee211fc350816 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1300 b/Train_Pendulum-v1_SAC_20230618-163911/models/1300 new file mode 100644 index 0000000000000000000000000000000000000000..792dccf0211e54597180be2168500561e1e24a77 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd3d70aa912612a5d055e6502f9cf009599074ac0b841ba71a3455c6d1f127d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13000 b/Train_Pendulum-v1_SAC_20230618-163911/models/13000 new file mode 100644 index 0000000000000000000000000000000000000000..3b7a8c368e0a318e2c474849fcd2095ee554fb3a --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0f609feb4677dfbe68264cbb61c49a87b8386b030969a6e4af1289e662a60c +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13100 b/Train_Pendulum-v1_SAC_20230618-163911/models/13100 new file mode 100644 index 0000000000000000000000000000000000000000..3fdd3d8163ac1633dfd1822cc870157761486f7a --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe98a3e7dd1d5c126ae369a66d117af833b8bbc67aa360395ddcbe4e05b31762 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13200 b/Train_Pendulum-v1_SAC_20230618-163911/models/13200 new file mode 100644 index 0000000000000000000000000000000000000000..e6e85c8c1e8dd4d4f1048ec857d6b9ef85783e7b --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f702e97836f33c9220a1a3ace1481ca92b0a8b983b04eb328990ef60cbe81f0 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13300 b/Train_Pendulum-v1_SAC_20230618-163911/models/13300 new file mode 100644 index 0000000000000000000000000000000000000000..6b7b612fca90995475f97cb9e1f4095451a5ae1f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cef70af2793ae938858c5e2207eeb1b6106294450b99308e3061117759c961d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13400 b/Train_Pendulum-v1_SAC_20230618-163911/models/13400 new file mode 100644 index 0000000000000000000000000000000000000000..6f549056826bdf4c636dd2f498e3bf66ddf38ab1 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af889889ec3123ce09cec93b0647b14570f01e9f5b34837463abc37f830ef46b +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13500 b/Train_Pendulum-v1_SAC_20230618-163911/models/13500 new file mode 100644 index 0000000000000000000000000000000000000000..da4aa23fdcd95ace71fa16e0c7c05a32868f6691 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e56888377e5b42fe4f406b26b3b1f6375faea01f09225cd791c374d17a3b0125 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13600 b/Train_Pendulum-v1_SAC_20230618-163911/models/13600 new file mode 100644 index 0000000000000000000000000000000000000000..2ad1241fd2573280df593292ff73f2c5966994ea --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:213282199bb24892800f2bb4c618c228f7764a70e00e9ba24d80cc2bf91261e5 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13700 b/Train_Pendulum-v1_SAC_20230618-163911/models/13700 new file mode 100644 index 0000000000000000000000000000000000000000..320189cba8059ceb409a6a4173dc11943970923f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73b6ffe2c18e95d6453538b0488e90d6148bf86b2d8b9bab75fe90f11af4b7b6 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13800 b/Train_Pendulum-v1_SAC_20230618-163911/models/13800 new file mode 100644 index 0000000000000000000000000000000000000000..dea61698dba883ecc2db5e5a9000b900c8d1fa30 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ddd9fd9d8a6bf55e63cc0cfb012aaaccc5848146d72c1f2c1c3ab8552823e9 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/13900 b/Train_Pendulum-v1_SAC_20230618-163911/models/13900 new file mode 100644 index 0000000000000000000000000000000000000000..8c8508a83a88f152db62606126e7e716ad1986eb --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/13900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c499fcd51c0f094d6a0e3b2887bcaa98ce0cac2e923a83a28af23340d84b9d2d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1400 b/Train_Pendulum-v1_SAC_20230618-163911/models/1400 new file mode 100644 index 0000000000000000000000000000000000000000..1fb026845b3a37b315509ec1ffeb73a5a0001022 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e4c9dc95391267a927149672e1728991bd99e985939a2435138f7cc6c166d00 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14000 b/Train_Pendulum-v1_SAC_20230618-163911/models/14000 new file mode 100644 index 0000000000000000000000000000000000000000..d443db9be8426c17029571a788902da02c0fe580 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f180ddc8d15f5412da6ee16d3de69f74befb87170ad2ceac2fcee4dcc5596276 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14100 b/Train_Pendulum-v1_SAC_20230618-163911/models/14100 new file mode 100644 index 0000000000000000000000000000000000000000..0a90dbb109278b8004bc7ce3a348e8a1df9cc573 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425d1576d5d226813913dfed59db805cbb5a8ba3b84a9e35bba6fc9c07748769 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14200 b/Train_Pendulum-v1_SAC_20230618-163911/models/14200 new file mode 100644 index 0000000000000000000000000000000000000000..3dff83100c8879c25c58c3c2017088be1be1cf11 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810d44859176a13fc96c7f90f7b1516dadda3a6a9285e803d216046b3c7b1c0d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14300 b/Train_Pendulum-v1_SAC_20230618-163911/models/14300 new file mode 100644 index 0000000000000000000000000000000000000000..66c7d214a81d4123ea97e58cfe12b7bb7a0b2292 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f4701e1ab001a321928472c8ea4cc2f9a26b14dca471d0303149a063ee33d9f +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14400 b/Train_Pendulum-v1_SAC_20230618-163911/models/14400 new file mode 100644 index 0000000000000000000000000000000000000000..e56d2dcadfb10e212d7608e6d7ebc1baeea68857 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fb419f63457e8f28b328e0bffc75fb8114889d51c649f51221067e1ed2e8ea0 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14500 b/Train_Pendulum-v1_SAC_20230618-163911/models/14500 new file mode 100644 index 0000000000000000000000000000000000000000..9602a71a325338feeb56590c49f7b44172fdc72c --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d014a171bdce31d8e44baf235d218285a7b638bbf54c97d66177fe53d644b92 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14600 b/Train_Pendulum-v1_SAC_20230618-163911/models/14600 new file mode 100644 index 0000000000000000000000000000000000000000..f2036a84355537906828c321c22fd17caf7b06b6 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adcfbbfab49c79f4e0c224797b1547d60bf98b888e06078252f056367a2f81f8 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14700 b/Train_Pendulum-v1_SAC_20230618-163911/models/14700 new file mode 100644 index 0000000000000000000000000000000000000000..b33560382c62ba5637e3aa4308cddc0576bf5d0b --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27592c65eed3351e4ad5348e23e0a235330dfb4ce561b6ce4d0dcf6919ea8515 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14800 b/Train_Pendulum-v1_SAC_20230618-163911/models/14800 new file mode 100644 index 0000000000000000000000000000000000000000..844864da5e1f55fd3452035db6ec82d916bca0f4 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bf267dcc6b56b77e5c7642201e0ee9231a7b471e12cfdbc63dee66df4775781 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/14900 b/Train_Pendulum-v1_SAC_20230618-163911/models/14900 new file mode 100644 index 0000000000000000000000000000000000000000..dcef6f6e486da0e25353dcbeaff4198ea1662631 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/14900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c08c221756645d0de274659d2435f31946a4b7a24a0b355e2354b9022f7c09c +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1500 b/Train_Pendulum-v1_SAC_20230618-163911/models/1500 new file mode 100644 index 0000000000000000000000000000000000000000..c88e18f3eb8c497bc655097b8373dabb23992d17 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a943247b25e7fbc314d3fd8e0ae37fcbcfb87c4696f32a6d66f8eebdab073756 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15000 b/Train_Pendulum-v1_SAC_20230618-163911/models/15000 new file mode 100644 index 0000000000000000000000000000000000000000..45fc3606ebe31bb43c4b080b2d2e4b6a9d0ac88a --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:408f74f6096fea01d95ae21f6c6c21dd785dded9e3bbaa8d4d0734a0ba3b5225 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15100 b/Train_Pendulum-v1_SAC_20230618-163911/models/15100 new file mode 100644 index 0000000000000000000000000000000000000000..2dd2b8f7145defd9f7adde279dcabc592bbda81a --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e564e570ad528876416f234d6b2d17306c5c3611aaf5eece3ec6732bcb57a434 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15200 b/Train_Pendulum-v1_SAC_20230618-163911/models/15200 new file mode 100644 index 0000000000000000000000000000000000000000..3004cd0a3876d136da99483b504f48fbb0c069e0 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ddd8b879c3a0d566fe2b33facb6953031efb1b6048443f3f13b1180ba1b382 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15300 b/Train_Pendulum-v1_SAC_20230618-163911/models/15300 new file mode 100644 index 0000000000000000000000000000000000000000..c0df81f0a954b41cdb044d2316d6f300d3435633 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c522a2cc82c12f1c56e1f0ca408b25fb80a13a864ba695024a9dc80146077f +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15400 b/Train_Pendulum-v1_SAC_20230618-163911/models/15400 new file mode 100644 index 0000000000000000000000000000000000000000..961cd5c49c405ac3731afb7c35be1e14f5249ded --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643eeb7ea575767caba18eb710d6bb15d5dbd09effa4eba57a22c024292e11e1 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15500 b/Train_Pendulum-v1_SAC_20230618-163911/models/15500 new file mode 100644 index 0000000000000000000000000000000000000000..47e1da1e53a41addad65c312286626f165e802e9 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:263742946b21fcd16e07dfd0e0a0355c834477ceab1ebfc224d118e69bb07a3c +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15600 b/Train_Pendulum-v1_SAC_20230618-163911/models/15600 new file mode 100644 index 0000000000000000000000000000000000000000..ede61e5e4afc446b6156b28b8007ca81d88eb380 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93a6f28282e81ea992c30581e3f1637d96bcd11958f39362ea84f1ab25293150 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15700 b/Train_Pendulum-v1_SAC_20230618-163911/models/15700 new file mode 100644 index 0000000000000000000000000000000000000000..81779d66e67a3cd55855394b3494d94f8cdaf0b8 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a150f0adb217b7c40b1641a71b706340c2ba57d7cda1c1c9a21318613dd57b9 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15800 b/Train_Pendulum-v1_SAC_20230618-163911/models/15800 new file mode 100644 index 0000000000000000000000000000000000000000..2525dfe53bad94edd5e56a431a87367c7d7f3031 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf143b61f6bd8e9cc524c663543b0021b9f8ea9152867c3e61bb7ff746e2bc0 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/15900 b/Train_Pendulum-v1_SAC_20230618-163911/models/15900 new file mode 100644 index 0000000000000000000000000000000000000000..434e8fd7c268d93777c3edb550ad61fb98f70e6d --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/15900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75f63f5c2abcca6135f121b189e30ead7a57f61d5b3812693a3bb49c59c46eb2 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1600 b/Train_Pendulum-v1_SAC_20230618-163911/models/1600 new file mode 100644 index 0000000000000000000000000000000000000000..23b7e261410f92150522bc661066926d8ee710f2 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d88a0f2d2a8778ac14e22b53f2e0d89802ad96f184afddac590b35e42234816 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16000 b/Train_Pendulum-v1_SAC_20230618-163911/models/16000 new file mode 100644 index 0000000000000000000000000000000000000000..307b937f870f1705cfdb82dabf6d400d76677f5d --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a19455607f9eeb21f47874bc3f21010616e1b9c6b55d545f7e02ec889fc43830 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16100 b/Train_Pendulum-v1_SAC_20230618-163911/models/16100 new file mode 100644 index 0000000000000000000000000000000000000000..27d35d1e50b795a95808678d29ab2593b3a76691 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8515e6f4534f46da4805e24145212eb20d25bde33b6802b3ff9766255d0a8405 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16200 b/Train_Pendulum-v1_SAC_20230618-163911/models/16200 new file mode 100644 index 0000000000000000000000000000000000000000..fb2b8d4e00fe7923cb3f996becdc4038ff59bfc9 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d69a1eab65fac894a7aba5d9d429107447e691b7a8f04d9769d12538251c3005 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16300 b/Train_Pendulum-v1_SAC_20230618-163911/models/16300 new file mode 100644 index 0000000000000000000000000000000000000000..fcc52f80cd75d6d6b1c50e6bdd5aa632dcc9182f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:710a33965d816f5a39a7517526588f03f5e834db8c8896d577b6a1b25f75df06 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16400 b/Train_Pendulum-v1_SAC_20230618-163911/models/16400 new file mode 100644 index 0000000000000000000000000000000000000000..293b8276da7657977c2a875f6096e60216c49a77 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57183810eb3370890c4d023c9194614dfafdb0f4435b4fa3f5caa8e0e65d3ae2 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16500 b/Train_Pendulum-v1_SAC_20230618-163911/models/16500 new file mode 100644 index 0000000000000000000000000000000000000000..801cdc98cf8cee674cf657e12a8b2c5763f11135 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55be178a299de27bb570cfdb72ca870e36426219f2e3db8daaa670d241225638 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16600 b/Train_Pendulum-v1_SAC_20230618-163911/models/16600 new file mode 100644 index 0000000000000000000000000000000000000000..d82d10e16ff8ab2d1001532e2d4aa415e370c27e --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebac9495c6cc228c1308b0b5d41e41aa05dae7986c481ef057b5380a66aeef5e +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16700 b/Train_Pendulum-v1_SAC_20230618-163911/models/16700 new file mode 100644 index 0000000000000000000000000000000000000000..85214135df2be8acc417bdc53078f269ba2f996f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc08b72260f458bea0645814fe58029ea5c6bc8152a3bfcc6340660b9b0871d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16800 b/Train_Pendulum-v1_SAC_20230618-163911/models/16800 new file mode 100644 index 0000000000000000000000000000000000000000..39817a7854291535c3b877d259ae01e16e030061 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dc856453a837a5fa311dabdff93a581f1e9b90130990644250a467de7bcfaa1 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/16900 b/Train_Pendulum-v1_SAC_20230618-163911/models/16900 new file mode 100644 index 0000000000000000000000000000000000000000..75ca349556e3e7ab0d098a5a95967bb881252269 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/16900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9364e77bc4170b11751ee97460bcc66e13d496690792e17fc862ed78ee43540 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1700 b/Train_Pendulum-v1_SAC_20230618-163911/models/1700 new file mode 100644 index 0000000000000000000000000000000000000000..8ff0c3bca82f15723133b1d4437c49bd0d1e9ad1 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4ce31ef505b8fe1bc4901f88563a581cbbe7589646aade15f98ac611452a3d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17000 b/Train_Pendulum-v1_SAC_20230618-163911/models/17000 new file mode 100644 index 0000000000000000000000000000000000000000..f6ceafc40f4fc29b86c37ba6ff156fc0ab0d31d3 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3c01b0b87bcf3ef87a2d3004ba9ce4c435f92260c7497311a710fbc5fa9c8d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17100 b/Train_Pendulum-v1_SAC_20230618-163911/models/17100 new file mode 100644 index 0000000000000000000000000000000000000000..4da491644ba01f5d01ea7809e9783a48d14473ec --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f67fcd6b89ba73e3e5f125a46a903f77c4771b6ebdb1c3d99349decb86a698dc +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17200 b/Train_Pendulum-v1_SAC_20230618-163911/models/17200 new file mode 100644 index 0000000000000000000000000000000000000000..5328fb41db9975868e38b7c552525db4bbebca21 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b18556db31563c078e5fa6689c7c1ecb9e8ec5b55946ee8fa7086a2d2fd049 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17300 b/Train_Pendulum-v1_SAC_20230618-163911/models/17300 new file mode 100644 index 0000000000000000000000000000000000000000..96ef07f77413b615f26aa00c435998a47cac926c --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67e49bf9b016fe7fb773afe02cbcf66346e23f69ff0a26ab8ec4b328dcd5f086 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17400 b/Train_Pendulum-v1_SAC_20230618-163911/models/17400 new file mode 100644 index 0000000000000000000000000000000000000000..1e0203d445b0853eaa8eb56b4b9a5c5a7b85857d --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71a0579bded0716bf3f1b31f55690ef34f71f807c2401a30e55df14e98df9c9 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17500 b/Train_Pendulum-v1_SAC_20230618-163911/models/17500 new file mode 100644 index 0000000000000000000000000000000000000000..5147d0fa3926a6c6f76473edb550cfdcd2d6083c --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c9ae6a6caaed2b4d89ca7692c4e00abf7f8c8e5f3acc4cb800d1a18f2f2907 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17600 b/Train_Pendulum-v1_SAC_20230618-163911/models/17600 new file mode 100644 index 0000000000000000000000000000000000000000..6503a1a05eead622bd0673d43a32874e0cf9589f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99de348d9c72d2cc0a6790b1f2ed039e34b2e920eae7f88139d831537e653bc +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17700 b/Train_Pendulum-v1_SAC_20230618-163911/models/17700 new file mode 100644 index 0000000000000000000000000000000000000000..60e05439cf365916855f5a7821e8eeff05eed326 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc39ce92520938d0e67d856b9b912396b74f4c343bd8231ba2daacb0a07b560 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17800 b/Train_Pendulum-v1_SAC_20230618-163911/models/17800 new file mode 100644 index 0000000000000000000000000000000000000000..cbdb4fb019b4d51b7a29da7d6da6cdc990d675a0 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f2ecd3ded50b25cef3e7c116a0b27558145cfc38fa50cb762295fa8562ab695 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/17900 b/Train_Pendulum-v1_SAC_20230618-163911/models/17900 new file mode 100644 index 0000000000000000000000000000000000000000..294e91f37b6555ffae6f04fcd20415003d1e6aac --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/17900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ef7679e4048b9bd2fad9d46e5eec731287f7417f728a50e82de637df645800 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/1800 b/Train_Pendulum-v1_SAC_20230618-163911/models/1800 new file mode 100644 index 0000000000000000000000000000000000000000..4f20e2a752323821d777b311cddc7f848f97c49e --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/1800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d96b95eda647674a386e958056398a06d6e0914151fd5be14db66038e67eb42d +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18000 b/Train_Pendulum-v1_SAC_20230618-163911/models/18000 new file mode 100644 index 0000000000000000000000000000000000000000..90be875118b8786ef26629cda1e92d7215774ce5 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e839ddb751c2a839493ee371c245b401a6327bfbba3328e1178d063197d029 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18100 b/Train_Pendulum-v1_SAC_20230618-163911/models/18100 new file mode 100644 index 0000000000000000000000000000000000000000..38ae8795e2e3df09a4d6d5b3551b9e349f4b9b6c --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18100 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36a47f01d3a05b30461355f5db43c3624189efe969dd9bf3c0f3498921b879b0 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18200 b/Train_Pendulum-v1_SAC_20230618-163911/models/18200 new file mode 100644 index 0000000000000000000000000000000000000000..bb2a4b2242dc34e8ef80a51e4d77464a3024ef6f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18200 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f092356f1324aa3eb11683cd8361f85764bb79ed6d52faf5443ce5631517ab +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18300 b/Train_Pendulum-v1_SAC_20230618-163911/models/18300 new file mode 100644 index 0000000000000000000000000000000000000000..ba80e42b4a9353c99aa05b746217e653b04fc95c --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18300 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8b510427359fa9864ec513583bc4318a6a042d826aa7a5ba156e070dca40e17 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18400 b/Train_Pendulum-v1_SAC_20230618-163911/models/18400 new file mode 100644 index 0000000000000000000000000000000000000000..7b44152e1f9679d21cd13fe3deff0756c7cae67f --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18400 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16c5a09e7119bf7018a03c3ce02aa73f594d77f3c11c57231bd8ab793466a7c5 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18500 b/Train_Pendulum-v1_SAC_20230618-163911/models/18500 new file mode 100644 index 0000000000000000000000000000000000000000..149061990923f55299648ffaae0360fc5c708bb1 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6da6916254d2e8d57124e7eabf16ee51a7b6905a56c6e7bad2c2df94ad958929 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18600 b/Train_Pendulum-v1_SAC_20230618-163911/models/18600 new file mode 100644 index 0000000000000000000000000000000000000000..07f19cefd7671681a3a36a96b0f895123139c5e6 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18600 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79c8e563be666b672d8be4ea2bbd5bbacce052f304d5a596f594a6a4830cc412 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18700 b/Train_Pendulum-v1_SAC_20230618-163911/models/18700 new file mode 100644 index 0000000000000000000000000000000000000000..1faeb125055f7440fe7ff997720d0a0d864e5943 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18700 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6c639431e9ffab0dc399adcc3a0efeacc59fc1623884e6e785d0660c164787 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18800 b/Train_Pendulum-v1_SAC_20230618-163911/models/18800 new file mode 100644 index 0000000000000000000000000000000000000000..ceafddfd4ea6dfa6874bcc9be0c571fb527e95a8 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18800 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963ab3a1615a535fdce86220bf3dfb9a876e6b53fe8c0f66557a8f3dabc7d89f +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/models/18900 b/Train_Pendulum-v1_SAC_20230618-163911/models/18900 new file mode 100644 index 0000000000000000000000000000000000000000..f6cb50bb38f71f3a8fe4add2e9637bea5ab17867 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/models/18900 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d765380a45d7704c4945a56bee144bd25693374b6b715f17610fc45e14304547 +size 1356936 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/tb_logs/interact/events.out.tfevents.1687077551.ML3090.330549.0 b/Train_Pendulum-v1_SAC_20230618-163911/tb_logs/interact/events.out.tfevents.1687077551.ML3090.330549.0 new file mode 100644 index 0000000000000000000000000000000000000000..61d141fcaa52b46eefe1bc25749f2c97454d9e59 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/tb_logs/interact/events.out.tfevents.1687077551.ML3090.330549.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2fdc28d315e8a1ee8ff541b15b2faddec4cb3cc990850353dbc27d6aea5558d +size 19786 diff --git a/Train_Pendulum-v1_SAC_20230618-163911/tb_logs/policy/events.out.tfevents.1687077551.ML3090.330549.1 b/Train_Pendulum-v1_SAC_20230618-163911/tb_logs/policy/events.out.tfevents.1687077551.ML3090.330549.1 new file mode 100644 index 0000000000000000000000000000000000000000..ef9e01ef80694d77aabeb460a07d454a7ec61a35 --- /dev/null +++ b/Train_Pendulum-v1_SAC_20230618-163911/tb_logs/policy/events.out.tfevents.1687077551.ML3090.330549.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fdd019c428a762b1ca0b2a815d9daec2aa8b2682774e3c3236ef73182f1485b +size 5561148