diff --git a/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/config.yaml b/ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/config.yaml similarity index 100% rename from Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/config.yaml rename to ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/config.yaml diff --git a/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/logs/log.txt b/ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/logs/log.txt similarity index 100% rename from Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/logs/log.txt rename to ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/logs/log.txt diff --git a/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/models/actor_checkpoint.pt b/ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/models/actor_checkpoint.pt similarity index 100% rename from Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/models/actor_checkpoint.pt rename to ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/models/actor_checkpoint.pt diff --git a/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/learning_curve.png b/ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/learning_curve.png rename to ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/learning_curve.png diff --git a/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/res.csv b/ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/res.csv similarity index 100% rename from Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/res.csv rename to ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/results/res.csv diff --git a/Pendulum-v1/Test_gym_TD3_20230416-113300/config.yaml b/ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/config.yaml similarity index 100% rename from Pendulum-v1/Test_gym_TD3_20230416-113300/config.yaml rename to ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/config.yaml diff --git a/Pendulum-v1/Test_gym_TD3_20230416-113300/logs/log.txt b/ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/logs/log.txt similarity index 100% rename from Pendulum-v1/Test_gym_TD3_20230416-113300/logs/log.txt rename to ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/logs/log.txt diff --git a/Pendulum-v1/Test_gym_TD3_20230416-113300/models/actor.pth b/ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/models/actor.pth similarity index 100% rename from Pendulum-v1/Test_gym_TD3_20230416-113300/models/actor.pth rename to ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/models/actor.pth diff --git a/Pendulum-v1/Test_gym_TD3_20230416-113300/models/critic_1.pth b/ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/models/critic_1.pth similarity index 100% rename from Pendulum-v1/Test_gym_TD3_20230416-113300/models/critic_1.pth rename to ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/models/critic_1.pth diff --git a/Pendulum-v1/Test_gym_TD3_20230416-113300/models/critic_2.pth b/ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/models/critic_2.pth similarity index 100% rename from Pendulum-v1/Test_gym_TD3_20230416-113300/models/critic_2.pth rename to ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/models/critic_2.pth diff --git a/Pendulum-v1/Test_gym_TD3_20230416-113300/results/learning_curve.png b/ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Test_gym_TD3_20230416-113300/results/learning_curve.png rename to ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/results/learning_curve.png diff --git a/Pendulum-v1/Test_gym_TD3_20230416-113300/results/res.csv b/ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/results/res.csv similarity index 100% rename from Pendulum-v1/Test_gym_TD3_20230416-113300/results/res.csv rename to ClassControl/Pendulum-v1/Test_gym_TD3_20230416-113300/results/res.csv diff --git a/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/config.yaml b/ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/config.yaml similarity index 100% rename from Pendulum-v1/Test_gym_TD3_BC_20230416-113155/config.yaml rename to ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/config.yaml diff --git a/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/logs/log.txt b/ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/logs/log.txt similarity index 100% rename from Pendulum-v1/Test_gym_TD3_BC_20230416-113155/logs/log.txt rename to ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/logs/log.txt diff --git a/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/actor.pth b/ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/actor.pth similarity index 100% rename from Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/actor.pth rename to ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/actor.pth diff --git a/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/critic_1.pth b/ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/critic_1.pth similarity index 100% rename from Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/critic_1.pth rename to ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/critic_1.pth diff --git a/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/critic_2.pth b/ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/critic_2.pth similarity index 100% rename from Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/critic_2.pth rename to ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/models/critic_2.pth diff --git a/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/results/learning_curve.png b/ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Test_gym_TD3_BC_20230416-113155/results/learning_curve.png rename to ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/results/learning_curve.png diff --git a/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/results/res.csv b/ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/results/res.csv similarity index 100% rename from Pendulum-v1/Test_gym_TD3_BC_20230416-113155/results/res.csv rename to ClassControl/Pendulum-v1/Test_gym_TD3_BC_20230416-113155/results/res.csv diff --git a/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/config.yaml b/ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/config.yaml similarity index 100% rename from Pendulum-v1/Test_gym_mp_TD3_20230416-221428/config.yaml rename to ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/config.yaml diff --git a/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/logs/log.txt b/ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/logs/log.txt similarity index 100% rename from Pendulum-v1/Test_gym_mp_TD3_20230416-221428/logs/log.txt rename to ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/logs/log.txt diff --git a/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/actor.pth b/ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/actor.pth similarity index 100% rename from Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/actor.pth rename to ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/actor.pth diff --git a/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/critic_1.pth b/ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/critic_1.pth similarity index 100% rename from Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/critic_1.pth rename to ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/critic_1.pth diff --git a/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/critic_2.pth b/ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/critic_2.pth similarity index 100% rename from Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/critic_2.pth rename to ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/models/critic_2.pth diff --git a/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/results/learning_curve.png b/ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Test_gym_mp_TD3_20230416-221428/results/learning_curve.png rename to ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/results/learning_curve.png diff --git a/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/results/res.csv b/ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/results/res.csv similarity index 100% rename from Pendulum-v1/Test_gym_mp_TD3_20230416-221428/results/res.csv rename to ClassControl/Pendulum-v1/Test_gym_mp_TD3_20230416-221428/results/res.csv diff --git a/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/config.yaml b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ea5549b93dc00d07f4f31a45a50ed7a2cf970972 --- /dev/null +++ b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/config.yaml @@ -0,0 +1,56 @@ +general_cfg: + algo_name: DDPG + collect_traj: false + device: cuda + env_name: gym + load_checkpoint: true + load_model_step: best + load_path: Train_ray_Pendulum-v1_DDPG_20230527-001715 + max_episode: 10 + max_step: 200 + mode: test + model_save_fre: 2000 + mp_backend: single + n_learners: 1 + n_workers: 4 + online_eval: true + online_eval_episode: 20 + seed: 10 + share_buffer: true +algo_cfg: + action_type: dpg + actor_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear + actor_lr: 0.0001 + batch_size: 128 + buffer_size: 8000 + buffer_type: REPLAY_QUE + critic_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear + critic_lr: 0.001 + gamma: 0.99 + policy_loss_weight: 0.002 + tau: 0.001 + value_max: .inf + value_min: -.inf +env_cfg: + id: Pendulum-v1 + ignore_params: + - wrapper + - ignore_params + render_mode: rgb_array + wrapper: null diff --git a/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/logs/log.txt b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..e84378d408a27fcee7f0fc7babcb97b5b14bc0f4 --- /dev/null +++ b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/logs/log.txt @@ -0,0 +1,60 @@ +2023-05-27 12:07:39 - SimpleLog - INFO: - General Configs: +2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================ +2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type +2023-05-27 12:07:39 - SimpleLog - INFO: - env_name gym +2023-05-27 12:07:39 - SimpleLog - INFO: - algo_name DDPG +2023-05-27 12:07:39 - SimpleLog - INFO: - mode test +2023-05-27 12:07:39 - SimpleLog - INFO: - device cuda +2023-05-27 12:07:39 - SimpleLog - INFO: - seed 10 +2023-05-27 12:07:39 - SimpleLog - INFO: - max_episode 10 +2023-05-27 12:07:39 - SimpleLog - INFO: - max_step 200 +2023-05-27 12:07:39 - SimpleLog - INFO: - collect_traj 0 +2023-05-27 12:07:39 - SimpleLog - INFO: - mp_backend single +2023-05-27 12:07:39 - SimpleLog - INFO: - n_workers 4 +2023-05-27 12:07:39 - SimpleLog - INFO: - n_learners 1 +2023-05-27 12:07:39 - SimpleLog - INFO: - share_buffer 1 +2023-05-27 12:07:39 - SimpleLog - INFO: - online_eval 1 +2023-05-27 12:07:39 - SimpleLog - INFO: - online_eval_episode 20 +2023-05-27 12:07:39 - SimpleLog - INFO: - model_save_fre 2000 +2023-05-27 12:07:39 - SimpleLog - INFO: - load_checkpoint 1 +2023-05-27 12:07:39 - SimpleLog - INFO: - load_path Train_ray_Pendulum-v1_DDPG_20230527-001715 +2023-05-27 12:07:39 - SimpleLog - INFO: - load_model_step best +2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================ +2023-05-27 12:07:39 - SimpleLog - INFO: - Algo Configs: +2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================ +2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type +2023-05-27 12:07:39 - SimpleLog - INFO: - action_type dpg +2023-05-27 12:07:39 - SimpleLog - INFO: - buffer_type REPLAY_QUE +2023-05-27 12:07:39 - SimpleLog - INFO: - buffer_size 8000 +2023-05-27 12:07:39 - SimpleLog - INFO: - batch_size 128 +2023-05-27 12:07:39 - SimpleLog - INFO: - gamma 0.99 +2023-05-27 12:07:39 - SimpleLog - INFO: - policy_loss_weight 0.002 +2023-05-27 12:07:39 - SimpleLog - INFO: - critic_lr 0.001 +2023-05-27 12:07:39 - SimpleLog - INFO: - actor_lr 0.0001 +2023-05-27 12:07:39 - SimpleLog - INFO: - tau 0.001 +2023-05-27 12:07:39 - SimpleLog - INFO: - value_min -inf +2023-05-27 12:07:39 - SimpleLog - INFO: - value_max inf +2023-05-27 12:07:39 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-05-27 12:07:39 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================ +2023-05-27 12:07:39 - SimpleLog - INFO: - Env Configs: +2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================ +2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type +2023-05-27 12:07:39 - SimpleLog - INFO: - id Pendulum-v1 +2023-05-27 12:07:39 - SimpleLog - INFO: - render_mode rgb_array +2023-05-27 12:07:39 - SimpleLog - INFO: - wrapper None +2023-05-27 12:07:39 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================ +2023-05-27 12:07:39 - SimpleLog - INFO: - obs_space: Box([-1. -1. -8.], [1. 1. 8.], (3,), float32), n_actions: Box(-2.0, 2.0, (1,), float32) +2023-05-27 12:07:40 - SimpleLog - INFO: - Start testing! +2023-05-27 12:07:42 - SimpleLog - INFO: - episode: 0, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:46 - SimpleLog - INFO: - episode: 1, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:46 - SimpleLog - INFO: - episode: 2, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:47 - SimpleLog - INFO: - episode: 3, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:48 - SimpleLog - INFO: - episode: 4, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:48 - SimpleLog - INFO: - episode: 5, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:49 - SimpleLog - INFO: - episode: 6, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:50 - SimpleLog - INFO: - episode: 7, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:51 - SimpleLog - INFO: - episode: 8, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:52 - SimpleLog - INFO: - episode: 9, ep_reward: -253.906, ep_step: 200 +2023-05-27 12:07:52 - SimpleLog - INFO: - Finish testing! total time consumed: 12.58s diff --git a/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/interact/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.0 b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/interact/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.0 new file mode 100644 index 0000000000000000000000000000000000000000..ad1d7ca409991de27294fe22492229f50cf0f5ba --- /dev/null +++ b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/interact/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64dbf4bf19be7aa1d79cd97ab84a6578e48107568cc32c3df036dc193e407562 +size 996 diff --git a/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/model/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.1 b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/model/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.1 new file mode 100644 index 0000000000000000000000000000000000000000..68ba9a14809ff7afc0171ffa5c9d8db901b6f90e --- /dev/null +++ b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/tb_logs/model/events.out.tfevents.1685160459.DESKTOP-H34HQIQ.22404.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e123931f1d5c5205cb1aa98cd172ba11f6bc0e4fb66cad15996d12535eb6d0b7 +size 40 diff --git a/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/videos/video.gif b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/videos/video.gif new file mode 100644 index 0000000000000000000000000000000000000000..2dbee30f6319e805284bb3945990a88a8df9713e --- /dev/null +++ b/ClassControl/Pendulum-v1/Test_single_Pendulum-v1_DDPG_20230527-120739/videos/video.gif @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b26fbb9e9e9d7827a4cde0e62ad7cca19c3186a30cfd7aaa61e8365854b5019 +size 80577 diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/config.yaml b/ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/config.yaml similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/config.yaml rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/config.yaml diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/logs/log.txt b/ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/logs/log.txt similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/logs/log.txt rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/logs/log.txt diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/models/actor_checkpoint.pt b/ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/models/actor_checkpoint.pt similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/models/actor_checkpoint.pt rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/models/actor_checkpoint.pt diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/learning_curve.png b/ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/learning_curve.png rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/learning_curve.png diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/res.csv b/ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/res.csv similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/res.csv rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_DDPG_HER_20230414-150220/results/res.csv diff --git a/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/config.yaml b/ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/config.yaml similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/config.yaml rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/config.yaml diff --git a/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/logs/log.txt b/ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/logs/log.txt similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/logs/log.txt rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/logs/log.txt diff --git a/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/models/checkpoint.pt b/ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/models/checkpoint.pt similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/models/checkpoint.pt rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/models/checkpoint.pt diff --git a/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/results/learning_curve.png b/ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/results/learning_curve.png rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/results/learning_curve.png diff --git a/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/results/res.csv b/ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/results/res.csv similarity index 100% rename from Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/results/res.csv rename to ClassControl/Pendulum-v1/Train_Pendulum-v1_SAC_20230305-114217/results/res.csv diff --git a/Pendulum-v1/Train_gym_TD3_20230416-110359/config.yaml b/ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/config.yaml similarity index 100% rename from Pendulum-v1/Train_gym_TD3_20230416-110359/config.yaml rename to ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/config.yaml diff --git a/Pendulum-v1/Train_gym_TD3_20230416-110359/logs/log.txt b/ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/logs/log.txt similarity index 100% rename from Pendulum-v1/Train_gym_TD3_20230416-110359/logs/log.txt rename to ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/logs/log.txt diff --git a/Pendulum-v1/Train_gym_TD3_20230416-110359/models/actor.pth b/ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/models/actor.pth similarity index 100% rename from Pendulum-v1/Train_gym_TD3_20230416-110359/models/actor.pth rename to ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/models/actor.pth diff --git a/Pendulum-v1/Train_gym_TD3_20230416-110359/models/critic_1.pth b/ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/models/critic_1.pth similarity index 100% rename from Pendulum-v1/Train_gym_TD3_20230416-110359/models/critic_1.pth rename to ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/models/critic_1.pth diff --git a/Pendulum-v1/Train_gym_TD3_20230416-110359/models/critic_2.pth b/ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/models/critic_2.pth similarity index 100% rename from Pendulum-v1/Train_gym_TD3_20230416-110359/models/critic_2.pth rename to ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/models/critic_2.pth diff --git a/Pendulum-v1/Train_gym_TD3_20230416-110359/results/learning_curve.png b/ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Train_gym_TD3_20230416-110359/results/learning_curve.png rename to ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/results/learning_curve.png diff --git a/Pendulum-v1/Train_gym_TD3_20230416-110359/results/res.csv b/ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/results/res.csv similarity index 100% rename from Pendulum-v1/Train_gym_TD3_20230416-110359/results/res.csv rename to ClassControl/Pendulum-v1/Train_gym_TD3_20230416-110359/results/res.csv diff --git a/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/config.yaml b/ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/config.yaml similarity index 100% rename from Pendulum-v1/Train_gym_TD3_BC_20230416-111154/config.yaml rename to ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/config.yaml diff --git a/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/logs/log.txt b/ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/logs/log.txt similarity index 100% rename from Pendulum-v1/Train_gym_TD3_BC_20230416-111154/logs/log.txt rename to ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/logs/log.txt diff --git a/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/actor.pth b/ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/actor.pth similarity index 100% rename from Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/actor.pth rename to ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/actor.pth diff --git a/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/critic_1.pth b/ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/critic_1.pth similarity index 100% rename from Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/critic_1.pth rename to ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/critic_1.pth diff --git a/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/critic_2.pth b/ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/critic_2.pth similarity index 100% rename from Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/critic_2.pth rename to ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/models/critic_2.pth diff --git a/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/results/learning_curve.png b/ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Train_gym_TD3_BC_20230416-111154/results/learning_curve.png rename to ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/results/learning_curve.png diff --git a/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/results/res.csv b/ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/results/res.csv similarity index 100% rename from Pendulum-v1/Train_gym_TD3_BC_20230416-111154/results/res.csv rename to ClassControl/Pendulum-v1/Train_gym_TD3_BC_20230416-111154/results/res.csv diff --git a/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/config.yaml b/ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/config.yaml similarity index 100% rename from Pendulum-v1/Train_gym_mp_TD3_20230416-214019/config.yaml rename to ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/config.yaml diff --git a/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/logs/log.txt b/ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/logs/log.txt similarity index 100% rename from Pendulum-v1/Train_gym_mp_TD3_20230416-214019/logs/log.txt rename to ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/logs/log.txt diff --git a/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/actor.pth b/ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/actor.pth similarity index 100% rename from Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/actor.pth rename to ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/actor.pth diff --git a/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/critic_1.pth b/ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/critic_1.pth similarity index 100% rename from Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/critic_1.pth rename to ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/critic_1.pth diff --git a/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/critic_2.pth b/ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/critic_2.pth similarity index 100% rename from Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/critic_2.pth rename to ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/models/critic_2.pth diff --git a/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/results/learning_curve.png b/ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/results/learning_curve.png similarity index 100% rename from Pendulum-v1/Train_gym_mp_TD3_20230416-214019/results/learning_curve.png rename to ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/results/learning_curve.png diff --git a/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/results/res.csv b/ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/results/res.csv similarity index 100% rename from Pendulum-v1/Train_gym_mp_TD3_20230416-214019/results/res.csv rename to ClassControl/Pendulum-v1/Train_gym_mp_TD3_20230416-214019/results/res.csv diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/config.yaml b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..87c0c8f58ffbaf4284a63755fbd94d8f4c527206 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/config.yaml @@ -0,0 +1,56 @@ +general_cfg: + algo_name: DDPG + collect_traj: false + device: cuda + env_name: gym + load_checkpoint: false + load_model_step: best + load_path: Train_single_CartPole-v1_DQN_20230515-211721 + max_episode: 200 + max_step: 200 + mode: train + model_save_fre: 2000 + mp_backend: ray + n_learners: 1 + n_workers: 4 + online_eval: true + online_eval_episode: 20 + seed: 10 + share_buffer: true +algo_cfg: + action_type: dpg + actor_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear + actor_lr: 0.0001 + batch_size: 128 + buffer_size: 8000 + buffer_type: REPLAY_QUE + critic_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear + critic_lr: 0.001 + gamma: 0.99 + policy_loss_weight: 0.002 + tau: 0.001 + value_max: .inf + value_min: -.inf +env_cfg: + id: Pendulum-v1 + ignore_params: + - wrapper + - ignore_params + render_mode: null + wrapper: null diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/logs/log.txt b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..34dcbbf44f19d91cf7a6111a4f027152f78c7461 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/logs/log.txt @@ -0,0 +1,283 @@ +2023-05-27 00:17:15 - SimpleLog - INFO: - General Configs: +2023-05-27 00:17:15 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:17:15 - SimpleLog - INFO: - Name Value Type +2023-05-27 00:17:15 - SimpleLog - INFO: - env_name gym +2023-05-27 00:17:15 - SimpleLog - INFO: - algo_name DDPG +2023-05-27 00:17:15 - SimpleLog - INFO: - mode train +2023-05-27 00:17:15 - SimpleLog - INFO: - device cuda +2023-05-27 00:17:15 - SimpleLog - INFO: - seed 10 +2023-05-27 00:17:15 - SimpleLog - INFO: - max_episode 200 +2023-05-27 00:17:15 - SimpleLog - INFO: - max_step 200 +2023-05-27 00:17:15 - SimpleLog - INFO: - collect_traj 0 +2023-05-27 00:17:15 - SimpleLog - INFO: - mp_backend ray +2023-05-27 00:17:15 - SimpleLog - INFO: - n_workers 4 +2023-05-27 00:17:15 - SimpleLog - INFO: - n_learners 1 +2023-05-27 00:17:15 - SimpleLog - INFO: - share_buffer 1 +2023-05-27 00:17:15 - SimpleLog - INFO: - online_eval 1 +2023-05-27 00:17:15 - SimpleLog - INFO: - online_eval_episode 20 +2023-05-27 00:17:15 - SimpleLog - INFO: - model_save_fre 2000 +2023-05-27 00:17:15 - SimpleLog - INFO: - load_checkpoint 0 +2023-05-27 00:17:15 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_DQN_20230515-211721 +2023-05-27 00:17:15 - SimpleLog - INFO: - load_model_step best +2023-05-27 00:17:15 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:17:15 - SimpleLog - INFO: - Algo Configs: +2023-05-27 00:17:15 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:17:15 - SimpleLog - INFO: - Name Value Type +2023-05-27 00:17:15 - SimpleLog - INFO: - action_type dpg +2023-05-27 00:17:15 - SimpleLog - INFO: - buffer_type REPLAY_QUE +2023-05-27 00:17:15 - SimpleLog - INFO: - buffer_size 8000 +2023-05-27 00:17:15 - SimpleLog - INFO: - batch_size 128 +2023-05-27 00:17:15 - SimpleLog - INFO: - gamma 0.99 +2023-05-27 00:17:15 - SimpleLog - INFO: - policy_loss_weight 0.002 +2023-05-27 00:17:15 - SimpleLog - INFO: - critic_lr 0.001 +2023-05-27 00:17:15 - SimpleLog - INFO: - actor_lr 0.0001 +2023-05-27 00:17:15 - SimpleLog - INFO: - tau 0.001 +2023-05-27 00:17:15 - SimpleLog - INFO: - value_min -inf +2023-05-27 00:17:15 - SimpleLog - INFO: - value_max inf +2023-05-27 00:17:15 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-05-27 00:17:15 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-05-27 00:17:15 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:17:15 - SimpleLog - INFO: - Env Configs: +2023-05-27 00:17:15 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:17:15 - SimpleLog - INFO: - Name Value Type +2023-05-27 00:17:15 - SimpleLog - INFO: - id Pendulum-v1 +2023-05-27 00:17:15 - SimpleLog - INFO: - render_mode None +2023-05-27 00:17:15 - SimpleLog - INFO: - wrapper None +2023-05-27 00:17:15 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-27 00:17:15 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:17:20 - SimpleLog - INFO: - obs_space: Box([-1. -1. -8.], [1. 1. 8.], (3,), float32), n_actions: Box(-2.0, 2.0, (1,), float32) +2023-05-27 00:17:36 - RayLog - INFO: - Worker 2 finished episode 0 with reward -1451.948 in 200 steps +2023-05-27 00:17:36 - RayLog - INFO: - Worker 1 finished episode 0 with reward -1426.784 in 200 steps +2023-05-27 00:17:36 - RayLog - INFO: - Worker 0 finished episode 0 with reward -1551.199 in 200 steps +2023-05-27 00:17:36 - RayLog - INFO: - Worker 3 finished episode 0 with reward -1445.478 in 200 steps +2023-05-27 00:17:47 - RayLog - INFO: - Worker 2 finished episode 1 with reward -1166.916 in 200 steps +2023-05-27 00:17:47 - RayLog - INFO: - Worker 1 finished episode 3 with reward -1593.319 in 200 steps +2023-05-27 00:17:47 - RayLog - INFO: - Worker 0 finished episode 3 with reward -1603.294 in 200 steps +2023-05-27 00:17:47 - RayLog - INFO: - Worker 3 finished episode 4 with reward -1605.817 in 200 steps +2023-05-27 00:17:58 - RayLog - INFO: - learner id: 0, update_step: 2000, online_eval_reward: -1548.226 +2023-05-27 00:17:58 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -1548.226, save the best model! +2023-05-27 00:18:02 - RayLog - INFO: - Worker 2 finished episode 5 with reward -1538.540 in 200 steps +2023-05-27 00:18:02 - RayLog - INFO: - Worker 1 finished episode 6 with reward -1569.025 in 200 steps +2023-05-27 00:18:02 - RayLog - INFO: - Worker 0 finished episode 7 with reward -1578.207 in 200 steps +2023-05-27 00:18:02 - RayLog - INFO: - Worker 3 finished episode 8 with reward -1565.720 in 200 steps +2023-05-27 00:18:13 - RayLog - INFO: - Worker 2 finished episode 9 with reward -1543.753 in 200 steps +2023-05-27 00:18:13 - RayLog - INFO: - Worker 1 finished episode 10 with reward -1593.543 in 200 steps +2023-05-27 00:18:13 - RayLog - INFO: - Worker 0 finished episode 11 with reward -1599.652 in 200 steps +2023-05-27 00:18:13 - RayLog - INFO: - Worker 3 finished episode 12 with reward -1576.990 in 200 steps +2023-05-27 00:18:24 - RayLog - INFO: - Worker 2 finished episode 13 with reward -1494.538 in 200 steps +2023-05-27 00:18:24 - RayLog - INFO: - Worker 1 finished episode 14 with reward -1561.907 in 200 steps +2023-05-27 00:18:24 - RayLog - INFO: - Worker 0 finished episode 15 with reward -1576.500 in 200 steps +2023-05-27 00:18:24 - RayLog - INFO: - Worker 3 finished episode 16 with reward -1562.714 in 200 steps +2023-05-27 00:18:28 - RayLog - INFO: - learner id: 0, update_step: 4000, online_eval_reward: -1492.934 +2023-05-27 00:18:28 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -1492.934, save the best model! +2023-05-27 00:18:38 - RayLog - INFO: - Worker 2 finished episode 17 with reward -1441.521 in 200 steps +2023-05-27 00:18:38 - RayLog - INFO: - Worker 1 finished episode 18 with reward -1524.784 in 200 steps +2023-05-27 00:18:38 - RayLog - INFO: - Worker 0 finished episode 19 with reward -1460.997 in 200 steps +2023-05-27 00:18:38 - RayLog - INFO: - Worker 3 finished episode 20 with reward -1504.649 in 200 steps +2023-05-27 00:18:49 - RayLog - INFO: - Worker 2 finished episode 21 with reward -1159.768 in 200 steps +2023-05-27 00:18:49 - RayLog - INFO: - Worker 0 finished episode 23 with reward -1547.452 in 200 steps +2023-05-27 00:18:49 - RayLog - INFO: - Worker 1 finished episode 22 with reward -1245.359 in 200 steps +2023-05-27 00:18:49 - RayLog - INFO: - Worker 3 finished episode 24 with reward -1316.269 in 200 steps +2023-05-27 00:18:58 - RayLog - INFO: - learner id: 0, update_step: 6000, online_eval_reward: -1493.150 +2023-05-27 00:19:02 - RayLog - INFO: - Worker 2 finished episode 25 with reward -1123.863 in 200 steps +2023-05-27 00:19:02 - RayLog - INFO: - Worker 0 finished episode 26 with reward -1249.138 in 200 steps +2023-05-27 00:19:02 - RayLog - INFO: - Worker 1 finished episode 27 with reward -1208.721 in 200 steps +2023-05-27 00:19:02 - RayLog - INFO: - Worker 3 finished episode 28 with reward -1142.612 in 200 steps +2023-05-27 00:19:15 - RayLog - INFO: - Worker 2 finished episode 29 with reward -997.769 in 200 steps +2023-05-27 00:19:15 - RayLog - INFO: - Worker 0 finished episode 31 with reward -1118.224 in 200 steps +2023-05-27 00:19:15 - RayLog - INFO: - Worker 1 finished episode 31 with reward -1066.523 in 200 steps +2023-05-27 00:19:15 - RayLog - INFO: - Worker 3 finished episode 32 with reward -1068.746 in 200 steps +2023-05-27 00:19:28 - RayLog - INFO: - Worker 2 finished episode 33 with reward -937.183 in 200 steps +2023-05-27 00:19:28 - RayLog - INFO: - Worker 0 finished episode 34 with reward -1376.815 in 200 steps +2023-05-27 00:19:28 - RayLog - INFO: - Worker 1 finished episode 35 with reward -966.611 in 200 steps +2023-05-27 00:19:28 - RayLog - INFO: - Worker 3 finished episode 36 with reward -1073.693 in 200 steps +2023-05-27 00:19:32 - RayLog - INFO: - learner id: 0, update_step: 8000, online_eval_reward: -1493.374 +2023-05-27 00:19:42 - RayLog - INFO: - Worker 2 finished episode 37 with reward -878.047 in 200 steps +2023-05-27 00:19:42 - RayLog - INFO: - Worker 0 finished episode 38 with reward -976.531 in 200 steps +2023-05-27 00:19:42 - RayLog - INFO: - Worker 1 finished episode 39 with reward -956.583 in 200 steps +2023-05-27 00:19:42 - RayLog - INFO: - Worker 3 finished episode 40 with reward -805.417 in 200 steps +2023-05-27 00:19:54 - RayLog - INFO: - Worker 2 finished episode 42 with reward -532.475 in 200 steps +2023-05-27 00:19:54 - RayLog - INFO: - Worker 0 finished episode 42 with reward -1061.521 in 200 steps +2023-05-27 00:19:54 - RayLog - INFO: - Worker 1 finished episode 43 with reward -553.406 in 200 steps +2023-05-27 00:19:54 - RayLog - INFO: - Worker 3 finished episode 44 with reward -668.325 in 200 steps +2023-05-27 00:20:04 - RayLog - INFO: - learner id: 0, update_step: 10000, online_eval_reward: -536.765 +2023-05-27 00:20:04 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -536.765, save the best model! +2023-05-27 00:20:08 - RayLog - INFO: - Worker 2 finished episode 45 with reward -410.737 in 200 steps +2023-05-27 00:20:08 - RayLog - INFO: - Worker 0 finished episode 46 with reward -1107.134 in 200 steps +2023-05-27 00:20:08 - RayLog - INFO: - Worker 1 finished episode 47 with reward -571.280 in 200 steps +2023-05-27 00:20:08 - RayLog - INFO: - Worker 3 finished episode 48 with reward -464.369 in 200 steps +2023-05-27 00:20:20 - RayLog - INFO: - Worker 2 finished episode 49 with reward -534.199 in 200 steps +2023-05-27 00:20:20 - RayLog - INFO: - Worker 0 finished episode 50 with reward -539.787 in 200 steps +2023-05-27 00:20:21 - RayLog - INFO: - Worker 1 finished episode 51 with reward -536.010 in 200 steps +2023-05-27 00:20:21 - RayLog - INFO: - Worker 3 finished episode 52 with reward -390.752 in 200 steps +2023-05-27 00:20:33 - RayLog - INFO: - Worker 2 finished episode 53 with reward -273.564 in 200 steps +2023-05-27 00:20:33 - RayLog - INFO: - Worker 0 finished episode 54 with reward -552.384 in 200 steps +2023-05-27 00:20:33 - RayLog - INFO: - Worker 1 finished episode 55 with reward -275.812 in 200 steps +2023-05-27 00:20:33 - RayLog - INFO: - Worker 3 finished episode 56 with reward -391.565 in 200 steps +2023-05-27 00:20:37 - RayLog - INFO: - learner id: 0, update_step: 12000, online_eval_reward: -374.204 +2023-05-27 00:20:37 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -374.204, save the best model! +2023-05-27 00:20:47 - RayLog - INFO: - Worker 2 finished episode 57 with reward -141.707 in 200 steps +2023-05-27 00:20:47 - RayLog - INFO: - Worker 0 finished episode 58 with reward -372.130 in 200 steps +2023-05-27 00:20:47 - RayLog - INFO: - Worker 1 finished episode 59 with reward -268.024 in 200 steps +2023-05-27 00:20:47 - RayLog - INFO: - Worker 3 finished episode 60 with reward -252.713 in 200 steps +2023-05-27 00:20:59 - RayLog - INFO: - Worker 2 finished episode 61 with reward -137.422 in 200 steps +2023-05-27 00:20:59 - RayLog - INFO: - Worker 0 finished episode 62 with reward -362.890 in 200 steps +2023-05-27 00:20:59 - RayLog - INFO: - Worker 1 finished episode 63 with reward -260.108 in 200 steps +2023-05-27 00:20:59 - RayLog - INFO: - Worker 3 finished episode 64 with reward -249.668 in 200 steps +2023-05-27 00:21:09 - RayLog - INFO: - learner id: 0, update_step: 14000, online_eval_reward: -351.751 +2023-05-27 00:21:09 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -351.751, save the best model! +2023-05-27 00:21:13 - RayLog - INFO: - Worker 2 finished episode 65 with reward -136.902 in 200 steps +2023-05-27 00:21:13 - RayLog - INFO: - Worker 0 finished episode 66 with reward -363.455 in 200 steps +2023-05-27 00:21:13 - RayLog - INFO: - Worker 1 finished episode 67 with reward -255.716 in 200 steps +2023-05-27 00:21:13 - RayLog - INFO: - Worker 3 finished episode 68 with reward -245.107 in 200 steps +2023-05-27 00:21:26 - RayLog - INFO: - Worker 2 finished episode 69 with reward -133.383 in 200 steps +2023-05-27 00:21:26 - RayLog - INFO: - Worker 0 finished episode 70 with reward -346.740 in 200 steps +2023-05-27 00:21:26 - RayLog - INFO: - Worker 1 finished episode 71 with reward -257.755 in 200 steps +2023-05-27 00:21:26 - RayLog - INFO: - Worker 3 finished episode 72 with reward -242.626 in 200 steps +2023-05-27 00:21:38 - RayLog - INFO: - Worker 2 finished episode 73 with reward -132.665 in 200 steps +2023-05-27 00:21:38 - RayLog - INFO: - Worker 0 finished episode 74 with reward -460.159 in 200 steps +2023-05-27 00:21:38 - RayLog - INFO: - Worker 1 finished episode 75 with reward -260.655 in 200 steps +2023-05-27 00:21:38 - RayLog - INFO: - Worker 3 finished episode 76 with reward -242.048 in 200 steps +2023-05-27 00:21:42 - RayLog - INFO: - learner id: 0, update_step: 16000, online_eval_reward: -261.486 +2023-05-27 00:21:42 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -261.486, save the best model! +2023-05-27 00:21:52 - RayLog - INFO: - Worker 2 finished episode 77 with reward -130.662 in 200 steps +2023-05-27 00:21:52 - RayLog - INFO: - Worker 0 finished episode 78 with reward -392.058 in 200 steps +2023-05-27 00:21:52 - RayLog - INFO: - Worker 1 finished episode 79 with reward -258.029 in 200 steps +2023-05-27 00:21:52 - RayLog - INFO: - Worker 3 finished episode 80 with reward -240.002 in 200 steps +2023-05-27 00:22:05 - RayLog - INFO: - Worker 2 finished episode 81 with reward -128.995 in 200 steps +2023-05-27 00:22:05 - RayLog - INFO: - Worker 0 finished episode 82 with reward -390.709 in 200 steps +2023-05-27 00:22:05 - RayLog - INFO: - Worker 1 finished episode 83 with reward -256.941 in 200 steps +2023-05-27 00:22:05 - RayLog - INFO: - Worker 3 finished episode 84 with reward -241.232 in 200 steps +2023-05-27 00:22:16 - RayLog - INFO: - learner id: 0, update_step: 18000, online_eval_reward: -261.173 +2023-05-27 00:22:16 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -261.173, save the best model! +2023-05-27 00:22:20 - RayLog - INFO: - Worker 2 finished episode 85 with reward -129.842 in 200 steps +2023-05-27 00:22:20 - RayLog - INFO: - Worker 0 finished episode 86 with reward -385.724 in 200 steps +2023-05-27 00:22:20 - RayLog - INFO: - Worker 1 finished episode 87 with reward -259.445 in 200 steps +2023-05-27 00:22:20 - RayLog - INFO: - Worker 3 finished episode 88 with reward -239.046 in 200 steps +2023-05-27 00:22:33 - RayLog - INFO: - Worker 2 finished episode 89 with reward -129.676 in 200 steps +2023-05-27 00:22:33 - RayLog - INFO: - Worker 0 finished episode 90 with reward -384.466 in 200 steps +2023-05-27 00:22:33 - RayLog - INFO: - Worker 1 finished episode 91 with reward -254.073 in 200 steps +2023-05-27 00:22:33 - RayLog - INFO: - Worker 3 finished episode 92 with reward -236.958 in 200 steps +2023-05-27 00:22:45 - RayLog - INFO: - Worker 2 finished episode 93 with reward -128.925 in 200 steps +2023-05-27 00:22:45 - RayLog - INFO: - Worker 0 finished episode 94 with reward -389.155 in 200 steps +2023-05-27 00:22:45 - RayLog - INFO: - Worker 1 finished episode 95 with reward -248.248 in 200 steps +2023-05-27 00:22:45 - RayLog - INFO: - Worker 3 finished episode 96 with reward -240.203 in 200 steps +2023-05-27 00:22:50 - RayLog - INFO: - learner id: 0, update_step: 20000, online_eval_reward: -260.301 +2023-05-27 00:22:50 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -260.301, save the best model! +2023-05-27 00:23:00 - RayLog - INFO: - Worker 2 finished episode 97 with reward -130.815 in 200 steps +2023-05-27 00:23:00 - RayLog - INFO: - Worker 0 finished episode 98 with reward -264.699 in 200 steps +2023-05-27 00:23:01 - RayLog - INFO: - Worker 1 finished episode 99 with reward -252.631 in 200 steps +2023-05-27 00:23:01 - RayLog - INFO: - Worker 3 finished episode 100 with reward -241.614 in 200 steps +2023-05-27 00:23:13 - RayLog - INFO: - Worker 2 finished episode 101 with reward -127.897 in 200 steps +2023-05-27 00:23:13 - RayLog - INFO: - Worker 0 finished episode 102 with reward -382.318 in 200 steps +2023-05-27 00:23:13 - RayLog - INFO: - Worker 1 finished episode 103 with reward -249.393 in 200 steps +2023-05-27 00:23:13 - RayLog - INFO: - Worker 3 finished episode 104 with reward -236.064 in 200 steps +2023-05-27 00:23:24 - RayLog - INFO: - learner id: 0, update_step: 22000, online_eval_reward: -257.503 +2023-05-27 00:23:24 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -257.503, save the best model! +2023-05-27 00:23:28 - RayLog - INFO: - Worker 2 finished episode 105 with reward -126.619 in 200 steps +2023-05-27 00:23:28 - RayLog - INFO: - Worker 0 finished episode 106 with reward -261.980 in 200 steps +2023-05-27 00:23:28 - RayLog - INFO: - Worker 1 finished episode 107 with reward -247.431 in 200 steps +2023-05-27 00:23:28 - RayLog - INFO: - Worker 3 finished episode 108 with reward -238.771 in 200 steps +2023-05-27 00:23:41 - RayLog - INFO: - Worker 2 finished episode 109 with reward -125.812 in 200 steps +2023-05-27 00:23:41 - RayLog - INFO: - Worker 0 finished episode 110 with reward -261.920 in 200 steps +2023-05-27 00:23:41 - RayLog - INFO: - Worker 1 finished episode 111 with reward -245.626 in 200 steps +2023-05-27 00:23:41 - RayLog - INFO: - Worker 3 finished episode 112 with reward -238.486 in 200 steps +2023-05-27 00:23:55 - RayLog - INFO: - Worker 2 finished episode 113 with reward -128.340 in 200 steps +2023-05-27 00:23:55 - RayLog - INFO: - Worker 0 finished episode 114 with reward -258.998 in 200 steps +2023-05-27 00:23:55 - RayLog - INFO: - Worker 1 finished episode 115 with reward -247.832 in 200 steps +2023-05-27 00:23:55 - RayLog - INFO: - Worker 3 finished episode 116 with reward -239.194 in 200 steps +2023-05-27 00:23:59 - RayLog - INFO: - learner id: 0, update_step: 24000, online_eval_reward: -257.609 +2023-05-27 00:24:10 - RayLog - INFO: - Worker 2 finished episode 117 with reward -125.382 in 200 steps +2023-05-27 00:24:10 - RayLog - INFO: - Worker 0 finished episode 118 with reward -382.680 in 200 steps +2023-05-27 00:24:10 - RayLog - INFO: - Worker 1 finished episode 120 with reward -249.722 in 200 steps +2023-05-27 00:24:10 - RayLog - INFO: - Worker 3 finished episode 120 with reward -232.887 in 200 steps +2023-05-27 00:24:22 - RayLog - INFO: - Worker 2 finished episode 121 with reward -126.514 in 200 steps +2023-05-27 00:24:22 - RayLog - INFO: - Worker 0 finished episode 122 with reward -264.696 in 200 steps +2023-05-27 00:24:22 - RayLog - INFO: - Worker 1 finished episode 123 with reward -247.312 in 200 steps +2023-05-27 00:24:22 - RayLog - INFO: - Worker 3 finished episode 124 with reward -237.931 in 200 steps +2023-05-27 00:24:33 - RayLog - INFO: - learner id: 0, update_step: 26000, online_eval_reward: -257.615 +2023-05-27 00:24:37 - RayLog - INFO: - Worker 2 finished episode 125 with reward -125.401 in 200 steps +2023-05-27 00:24:37 - RayLog - INFO: - Worker 0 finished episode 126 with reward -391.984 in 200 steps +2023-05-27 00:24:37 - RayLog - INFO: - Worker 1 finished episode 128 with reward -245.055 in 200 steps +2023-05-27 00:24:37 - RayLog - INFO: - Worker 3 finished episode 128 with reward -241.654 in 200 steps +2023-05-27 00:24:49 - RayLog - INFO: - Worker 2 finished episode 129 with reward -129.201 in 200 steps +2023-05-27 00:24:49 - RayLog - INFO: - Worker 0 finished episode 130 with reward -383.073 in 200 steps +2023-05-27 00:24:49 - RayLog - INFO: - Worker 1 finished episode 131 with reward -249.794 in 200 steps +2023-05-27 00:24:49 - RayLog - INFO: - Worker 3 finished episode 132 with reward -638.571 in 200 steps +2023-05-27 00:25:01 - RayLog - INFO: - Worker 2 finished episode 133 with reward -128.480 in 200 steps +2023-05-27 00:25:01 - RayLog - INFO: - Worker 0 finished episode 134 with reward -257.693 in 200 steps +2023-05-27 00:25:01 - RayLog - INFO: - Worker 1 finished episode 135 with reward -251.526 in 200 steps +2023-05-27 00:25:01 - RayLog - INFO: - Worker 3 finished episode 136 with reward -237.464 in 200 steps +2023-05-27 00:25:05 - RayLog - INFO: - learner id: 0, update_step: 28000, online_eval_reward: -258.711 +2023-05-27 00:25:16 - RayLog - INFO: - Worker 2 finished episode 137 with reward -125.328 in 200 steps +2023-05-27 00:25:16 - RayLog - INFO: - Worker 0 finished episode 138 with reward -396.933 in 200 steps +2023-05-27 00:25:16 - RayLog - INFO: - Worker 1 finished episode 139 with reward -243.056 in 200 steps +2023-05-27 00:25:16 - RayLog - INFO: - Worker 3 finished episode 140 with reward -236.837 in 200 steps +2023-05-27 00:25:29 - RayLog - INFO: - Worker 2 finished episode 141 with reward -125.565 in 200 steps +2023-05-27 00:25:29 - RayLog - INFO: - Worker 0 finished episode 142 with reward -385.128 in 200 steps +2023-05-27 00:25:29 - RayLog - INFO: - Worker 1 finished episode 143 with reward -247.311 in 200 steps +2023-05-27 00:25:29 - RayLog - INFO: - Worker 3 finished episode 144 with reward -237.032 in 200 steps +2023-05-27 00:25:40 - RayLog - INFO: - learner id: 0, update_step: 30000, online_eval_reward: -321.698 +2023-05-27 00:25:44 - RayLog - INFO: - Worker 2 finished episode 145 with reward -125.422 in 200 steps +2023-05-27 00:25:44 - RayLog - INFO: - Worker 0 finished episode 146 with reward -318.491 in 200 steps +2023-05-27 00:25:44 - RayLog - INFO: - Worker 1 finished episode 147 with reward -243.852 in 200 steps +2023-05-27 00:25:44 - RayLog - INFO: - Worker 3 finished episode 148 with reward -237.555 in 200 steps +2023-05-27 00:25:57 - RayLog - INFO: - Worker 2 finished episode 149 with reward -125.752 in 200 steps +2023-05-27 00:25:57 - RayLog - INFO: - Worker 0 finished episode 150 with reward -291.795 in 200 steps +2023-05-27 00:25:57 - RayLog - INFO: - Worker 1 finished episode 151 with reward -250.404 in 200 steps +2023-05-27 00:25:57 - RayLog - INFO: - Worker 3 finished episode 152 with reward -235.658 in 200 steps +2023-05-27 00:26:10 - RayLog - INFO: - Worker 2 finished episode 153 with reward -126.320 in 200 steps +2023-05-27 00:26:10 - RayLog - INFO: - Worker 0 finished episode 154 with reward -316.699 in 200 steps +2023-05-27 00:26:10 - RayLog - INFO: - Worker 1 finished episode 155 with reward -247.839 in 200 steps +2023-05-27 00:26:10 - RayLog - INFO: - Worker 3 finished episode 156 with reward -238.029 in 200 steps +2023-05-27 00:26:14 - RayLog - INFO: - learner id: 0, update_step: 32000, online_eval_reward: -336.660 +2023-05-27 00:26:24 - RayLog - INFO: - Worker 2 finished episode 157 with reward -123.561 in 200 steps +2023-05-27 00:26:24 - RayLog - INFO: - Worker 0 finished episode 158 with reward -336.021 in 200 steps +2023-05-27 00:26:24 - RayLog - INFO: - Worker 1 finished episode 159 with reward -243.522 in 200 steps +2023-05-27 00:26:24 - RayLog - INFO: - Worker 3 finished episode 160 with reward -235.183 in 200 steps +2023-05-27 00:26:37 - RayLog - INFO: - Worker 2 finished episode 161 with reward -127.010 in 200 steps +2023-05-27 00:26:37 - RayLog - INFO: - Worker 0 finished episode 162 with reward -314.601 in 200 steps +2023-05-27 00:26:37 - RayLog - INFO: - Worker 1 finished episode 164 with reward -249.200 in 200 steps +2023-05-27 00:26:38 - RayLog - INFO: - Worker 3 finished episode 164 with reward -236.858 in 200 steps +2023-05-27 00:26:48 - RayLog - INFO: - learner id: 0, update_step: 34000, online_eval_reward: -336.947 +2023-05-27 00:26:52 - RayLog - INFO: - Worker 2 finished episode 165 with reward -123.759 in 200 steps +2023-05-27 00:26:52 - RayLog - INFO: - Worker 0 finished episode 167 with reward -337.302 in 200 steps +2023-05-27 00:26:52 - RayLog - INFO: - Worker 1 finished episode 167 with reward -244.929 in 200 steps +2023-05-27 00:26:52 - RayLog - INFO: - Worker 3 finished episode 168 with reward -235.501 in 200 steps +2023-05-27 00:27:04 - RayLog - INFO: - Worker 2 finished episode 169 with reward -126.060 in 200 steps +2023-05-27 00:27:04 - RayLog - INFO: - Worker 0 finished episode 170 with reward -342.141 in 200 steps +2023-05-27 00:27:04 - RayLog - INFO: - Worker 1 finished episode 171 with reward -247.857 in 200 steps +2023-05-27 00:27:04 - RayLog - INFO: - Worker 3 finished episode 172 with reward -235.949 in 200 steps +2023-05-27 00:27:16 - RayLog - INFO: - Worker 2 finished episode 173 with reward -125.042 in 200 steps +2023-05-27 00:27:16 - RayLog - INFO: - Worker 0 finished episode 174 with reward -337.675 in 200 steps +2023-05-27 00:27:16 - RayLog - INFO: - Worker 1 finished episode 175 with reward -244.513 in 200 steps +2023-05-27 00:27:16 - RayLog - INFO: - Worker 3 finished episode 176 with reward -236.820 in 200 steps +2023-05-27 00:27:21 - RayLog - INFO: - learner id: 0, update_step: 36000, online_eval_reward: -334.958 +2023-05-27 00:27:30 - RayLog - INFO: - Worker 2 finished episode 177 with reward -125.483 in 200 steps +2023-05-27 00:27:31 - RayLog - INFO: - Worker 0 finished episode 178 with reward -331.356 in 200 steps +2023-05-27 00:27:31 - RayLog - INFO: - Worker 1 finished episode 179 with reward -245.782 in 200 steps +2023-05-27 00:27:31 - RayLog - INFO: - Worker 3 finished episode 180 with reward -236.418 in 200 steps +2023-05-27 00:27:43 - RayLog - INFO: - Worker 2 finished episode 181 with reward -123.913 in 200 steps +2023-05-27 00:27:43 - RayLog - INFO: - Worker 0 finished episode 183 with reward -330.790 in 200 steps +2023-05-27 00:27:43 - RayLog - INFO: - Worker 1 finished episode 183 with reward -244.373 in 200 steps +2023-05-27 00:27:43 - RayLog - INFO: - Worker 3 finished episode 184 with reward -237.850 in 200 steps +2023-05-27 00:27:56 - RayLog - INFO: - learner id: 0, update_step: 38000, online_eval_reward: -328.723 +2023-05-27 00:28:01 - RayLog - INFO: - Worker 2 finished episode 185 with reward -125.132 in 200 steps +2023-05-27 00:28:01 - RayLog - INFO: - Worker 0 finished episode 186 with reward -333.844 in 200 steps +2023-05-27 00:28:01 - RayLog - INFO: - Worker 1 finished episode 187 with reward -245.075 in 200 steps +2023-05-27 00:28:01 - RayLog - INFO: - Worker 3 finished episode 188 with reward -236.059 in 200 steps +2023-05-27 00:28:13 - RayLog - INFO: - Worker 2 finished episode 189 with reward -125.009 in 200 steps +2023-05-27 00:28:13 - RayLog - INFO: - Worker 0 finished episode 190 with reward -319.946 in 200 steps +2023-05-27 00:28:13 - RayLog - INFO: - Worker 1 finished episode 191 with reward -245.653 in 200 steps +2023-05-27 00:28:13 - RayLog - INFO: - Worker 3 finished episode 192 with reward -238.445 in 200 steps +2023-05-27 00:28:25 - RayLog - INFO: - Worker 2 finished episode 193 with reward -124.193 in 200 steps +2023-05-27 00:28:25 - RayLog - INFO: - Worker 0 finished episode 194 with reward -291.396 in 200 steps +2023-05-27 00:28:25 - RayLog - INFO: - Worker 1 finished episode 195 with reward -243.751 in 200 steps +2023-05-27 00:28:25 - RayLog - INFO: - Worker 3 finished episode 196 with reward -236.249 in 200 steps +2023-05-27 00:28:29 - RayLog - INFO: - learner id: 0, update_step: 40000, online_eval_reward: -253.906 +2023-05-27 00:28:29 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: -253.906, save the best model! +2023-05-27 00:28:38 - RayLog - INFO: - Worker 2 finished episode 197 with reward -123.794 in 200 steps +2023-05-27 00:28:38 - RayLog - INFO: - Worker 0 finished episode 198 with reward -256.651 in 200 steps +2023-05-27 00:28:38 - RayLog - INFO: - Worker 1 finished episode 199 with reward -244.366 in 200 steps +2023-05-27 00:28:38 - RayLog - INFO: - Worker 3 finished episode 200 with reward -236.650 in 200 steps +2023-05-27 00:28:41 - SimpleLog - INFO: - Finish training! total time consumed: 685.93s diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/10000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/10000 new file mode 100644 index 0000000000000000000000000000000000000000..b9675af7f2e3757b881d0f2332909e99480bf75a --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/10000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7b6683b0f219abd73ad56fe7dc2964c622a25c7ed8958a894a050d712526d9 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/12000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/12000 new file mode 100644 index 0000000000000000000000000000000000000000..b22fe1b3b535f85d509ced7f55d9bb1c0e22e33d --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/12000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b4513dcd2c7826a09135f7d86ff9f7be9abc0ce9e2f9052ecf5c26d72a179a +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/14000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/14000 new file mode 100644 index 0000000000000000000000000000000000000000..6820617ea00e018b7f1c15261fac3efc59adcccf --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/14000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ee267747edac4419bc27e9cf2b24e69e0c226587f5010813809c20763bcf052 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/16000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/16000 new file mode 100644 index 0000000000000000000000000000000000000000..1c89bf5e7166b6975883efdeea91cf5d24aa4628 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/16000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b57fbf8527def508c751a49363970209736e713e9b33b14542603607daef0d5 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/18000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/18000 new file mode 100644 index 0000000000000000000000000000000000000000..7fbec3355974f9ea8854a57cf99d8c9111438db4 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/18000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f43e1cc7eae2a91244d946c6a076269f66b863ce2b7e43fd17a3446305db26bc +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/2000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/2000 new file mode 100644 index 0000000000000000000000000000000000000000..09bbe098dcdfa7d062c22aae3cd149003c627099 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/2000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4699fcf3fd062ce604e542874defaf1e170562cd7f9f1e375028dc6582af3337 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/20000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/20000 new file mode 100644 index 0000000000000000000000000000000000000000..26d89de7834f9fe4177e7ff98bc721b1dae28b0a --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/20000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2c9b6aad94dc72e0194dc611323cafce35c24ce777e8ffa12fb7468da1f330 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/22000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/22000 new file mode 100644 index 0000000000000000000000000000000000000000..4c42e10789bf2023abdd8a9106be90af5d58e2b5 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/22000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd4c546b6ab42a1498565843e66cda7ca7d1e47b79214cf46c0a91548b534ca +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/24000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/24000 new file mode 100644 index 0000000000000000000000000000000000000000..9d0a086d9e7ad8b2493f1e3eb8d510973f27f421 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/24000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bde0239673a32492b505b25531b0675b071e2babd1aca707d87fb6e08f08986 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/26000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/26000 new file mode 100644 index 0000000000000000000000000000000000000000..2578589b2fb0be40361927e986ae75ff1f26eb08 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/26000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ade65c03cbc81247d8be10eedec2be90f9556d076e407b4ae17cd1725810ec9 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/28000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/28000 new file mode 100644 index 0000000000000000000000000000000000000000..4e93e8ba663445cf52960927583a9c933729bfe3 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/28000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1064c650f48dc7d620816db660a6fa941a2c7f7a88b28dddfab1b6d5acc7e089 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/30000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/30000 new file mode 100644 index 0000000000000000000000000000000000000000..5667d4e42e8f9c7d1184bbcbcef3619ce0c24c18 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/30000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:647a477c786b454316ef4fe2fc976c5bce3ed0463058f488ddd2cc0a2ac3cf45 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/32000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/32000 new file mode 100644 index 0000000000000000000000000000000000000000..141a271b44a7bde4cb70ee1493b6b4ff28a7a580 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/32000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06503025ba337afe72a19878162f382035fda4ba7f119f8eba60118718653e53 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/34000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/34000 new file mode 100644 index 0000000000000000000000000000000000000000..d8e56bb4a6a9a12d24d090563a82f3588b012c7e --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/34000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5900a7359610aec6ec0412427be901be83bdc22bd55380cd548fd3982c4eddf5 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/36000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/36000 new file mode 100644 index 0000000000000000000000000000000000000000..e0f03a93e1c608dbcdaa10eb54c080af63366fdf --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/36000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be1ba9d2cd0fe55345104a8bb9c9c526fab33e1c86fd5a8c581fbb3331771f1 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/38000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/38000 new file mode 100644 index 0000000000000000000000000000000000000000..a14734526f2344d0257c131fc7362ef4e859ef93 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/38000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d376ec7b29accb2c9813e78dbccc1d741c4b7d32c8b206d4a6b9b588f5dfac +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/4000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/4000 new file mode 100644 index 0000000000000000000000000000000000000000..251fed5a57a0c4f8d69e56a874123e8b6c2b2d2d --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/4000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a98e159d139b7227a22c5fd13c937824ccaeb9f0f4e844f4573b2e768fc251 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/40000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/40000 new file mode 100644 index 0000000000000000000000000000000000000000..7907f85a3b731f1a7c6d933381249e2f2ddfd387 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/40000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62cb1993dc59d47ccca474c0df801ab6db245f565a0cfcc6bcbea4f9d6134e06 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/6000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/6000 new file mode 100644 index 0000000000000000000000000000000000000000..4384c919480d9126c3a6070bcb1fc5e06715e7f0 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/6000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c5f3e52032bd3687114fe74108af0b3b1513ffea4f204b0a8f2caf97ae43b7 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/8000 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/8000 new file mode 100644 index 0000000000000000000000000000000000000000..13ab3f9c3971738d707994971c9ba8d5fa63dc3d --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/8000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c295d24cf5728b40c55e475d7cbe1b8a850d1ed3a7254dbe7d73a8abd8dd1141 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/best b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/best new file mode 100644 index 0000000000000000000000000000000000000000..7907f85a3b731f1a7c6d933381249e2f2ddfd387 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/models/best @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62cb1993dc59d47ccca474c0df801ab6db245f565a0cfcc6bcbea4f9d6134e06 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/tb_logs/interact/events.out.tfevents.1685117843.DESKTOP-H34HQIQ.41704.0 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/tb_logs/interact/events.out.tfevents.1685117843.DESKTOP-H34HQIQ.41704.0 new file mode 100644 index 0000000000000000000000000000000000000000..437753b83c8d48d1bedeca8ba5adff47264eaf09 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/tb_logs/interact/events.out.tfevents.1685117843.DESKTOP-H34HQIQ.41704.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3053f684df722072d1bcccedc9da22f28b1431d8d24929679bed85a2f87c033 +size 20164 diff --git a/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/tb_logs/model/events.out.tfevents.1685117843.DESKTOP-H34HQIQ.41704.1 b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/tb_logs/model/events.out.tfevents.1685117843.DESKTOP-H34HQIQ.41704.1 new file mode 100644 index 0000000000000000000000000000000000000000..747f747213deab2b29d69ea31e2d3a5c921d2471 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_ray_Pendulum-v1_DDPG_20230527-001715/tb_logs/model/events.out.tfevents.1685117843.DESKTOP-H34HQIQ.41704.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9d234f0776e22f4e6acbd6e58115ed4c4ced15bb13adb347a1810a3b2e255c +size 6743068 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/config.yaml b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5688f11b12629e8723f02875d776d1799fc8ae34 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/config.yaml @@ -0,0 +1,56 @@ +general_cfg: + algo_name: DDPG + collect_traj: false + device: cuda + env_name: gym + load_checkpoint: false + load_model_step: best + load_path: Train_single_CartPole-v1_DQN_20230515-211721 + max_episode: 200 + max_step: 200 + mode: train + model_save_fre: 2000 + mp_backend: single + n_learners: 1 + n_workers: 4 + online_eval: true + online_eval_episode: 20 + seed: 10 + share_buffer: true +algo_cfg: + action_type: dpg + actor_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear + actor_lr: 0.0001 + batch_size: 128 + buffer_size: 8000 + buffer_type: REPLAY_QUE + critic_layers: + - activation: relu + layer_size: + - 256 + layer_type: linear + - activation: relu + layer_size: + - 256 + layer_type: linear + critic_lr: 0.001 + gamma: 0.99 + policy_loss_weight: 0.002 + tau: 0.001 + value_max: .inf + value_min: -.inf +env_cfg: + id: Pendulum-v1 + ignore_params: + - wrapper + - ignore_params + render_mode: null + wrapper: null diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/logs/log.txt b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..f760a7bfa9203ef0a9816bd7bdb8ec6fa56e784c --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/logs/log.txt @@ -0,0 +1,276 @@ +2023-05-27 00:28:59 - SimpleLog - INFO: - General Configs: +2023-05-27 00:28:59 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:28:59 - SimpleLog - INFO: - Name Value Type +2023-05-27 00:28:59 - SimpleLog - INFO: - env_name gym +2023-05-27 00:28:59 - SimpleLog - INFO: - algo_name DDPG +2023-05-27 00:28:59 - SimpleLog - INFO: - mode train +2023-05-27 00:28:59 - SimpleLog - INFO: - device cuda +2023-05-27 00:28:59 - SimpleLog - INFO: - seed 10 +2023-05-27 00:28:59 - SimpleLog - INFO: - max_episode 200 +2023-05-27 00:28:59 - SimpleLog - INFO: - max_step 200 +2023-05-27 00:28:59 - SimpleLog - INFO: - collect_traj 0 +2023-05-27 00:28:59 - SimpleLog - INFO: - mp_backend single +2023-05-27 00:28:59 - SimpleLog - INFO: - n_workers 4 +2023-05-27 00:28:59 - SimpleLog - INFO: - n_learners 1 +2023-05-27 00:28:59 - SimpleLog - INFO: - share_buffer 1 +2023-05-27 00:28:59 - SimpleLog - INFO: - online_eval 1 +2023-05-27 00:28:59 - SimpleLog - INFO: - online_eval_episode 20 +2023-05-27 00:28:59 - SimpleLog - INFO: - model_save_fre 2000 +2023-05-27 00:28:59 - SimpleLog - INFO: - load_checkpoint 0 +2023-05-27 00:28:59 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_DQN_20230515-211721 +2023-05-27 00:28:59 - SimpleLog - INFO: - load_model_step best +2023-05-27 00:28:59 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:28:59 - SimpleLog - INFO: - Algo Configs: +2023-05-27 00:28:59 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:28:59 - SimpleLog - INFO: - Name Value Type +2023-05-27 00:28:59 - SimpleLog - INFO: - action_type dpg +2023-05-27 00:28:59 - SimpleLog - INFO: - buffer_type REPLAY_QUE +2023-05-27 00:28:59 - SimpleLog - INFO: - buffer_size 8000 +2023-05-27 00:28:59 - SimpleLog - INFO: - batch_size 128 +2023-05-27 00:28:59 - SimpleLog - INFO: - gamma 0.99 +2023-05-27 00:28:59 - SimpleLog - INFO: - policy_loss_weight 0.002 +2023-05-27 00:28:59 - SimpleLog - INFO: - critic_lr 0.001 +2023-05-27 00:28:59 - SimpleLog - INFO: - actor_lr 0.0001 +2023-05-27 00:28:59 - SimpleLog - INFO: - tau 0.001 +2023-05-27 00:28:59 - SimpleLog - INFO: - value_min -inf +2023-05-27 00:28:59 - SimpleLog - INFO: - value_max inf +2023-05-27 00:28:59 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-05-27 00:28:59 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] +2023-05-27 00:28:59 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:28:59 - SimpleLog - INFO: - Env Configs: +2023-05-27 00:28:59 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:28:59 - SimpleLog - INFO: - Name Value Type +2023-05-27 00:28:59 - SimpleLog - INFO: - id Pendulum-v1 +2023-05-27 00:28:59 - SimpleLog - INFO: - render_mode None +2023-05-27 00:28:59 - SimpleLog - INFO: - wrapper None +2023-05-27 00:28:59 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-27 00:28:59 - SimpleLog - INFO: - ================================================================================ +2023-05-27 00:28:59 - SimpleLog - INFO: - obs_space: Box([-1. -1. -8.], [1. 1. 8.], (3,), float32), n_actions: Box(-2.0, 2.0, (1,), float32) +2023-05-27 00:28:59 - SimpleLog - INFO: - Start training! +2023-05-27 00:29:02 - SimpleLog - INFO: - episode: 0, ep_reward: -1661.201, ep_step: 200 +2023-05-27 00:29:04 - SimpleLog - INFO: - episode: 1, ep_reward: -1466.432, ep_step: 200 +2023-05-27 00:29:05 - SimpleLog - INFO: - episode: 2, ep_reward: -1506.946, ep_step: 200 +2023-05-27 00:29:07 - SimpleLog - INFO: - episode: 3, ep_reward: -1431.371, ep_step: 200 +2023-05-27 00:29:08 - SimpleLog - INFO: - episode: 4, ep_reward: -1450.385, ep_step: 200 +2023-05-27 00:29:10 - SimpleLog - INFO: - episode: 5, ep_reward: -1512.022, ep_step: 200 +2023-05-27 00:29:11 - SimpleLog - INFO: - episode: 6, ep_reward: -1225.477, ep_step: 200 +2023-05-27 00:29:13 - SimpleLog - INFO: - episode: 7, ep_reward: -1240.132, ep_step: 200 +2023-05-27 00:29:14 - SimpleLog - INFO: - episode: 8, ep_reward: -1578.078, ep_step: 200 +2023-05-27 00:29:16 - SimpleLog - INFO: - episode: 9, ep_reward: -1573.127, ep_step: 200 +2023-05-27 00:29:19 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: -1512.958 +2023-05-27 00:29:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1512.958, save the best model! +2023-05-27 00:29:19 - SimpleLog - INFO: - episode: 10, ep_reward: -1694.954, ep_step: 200 +2023-05-27 00:29:21 - SimpleLog - INFO: - episode: 11, ep_reward: -1551.799, ep_step: 200 +2023-05-27 00:29:23 - SimpleLog - INFO: - episode: 12, ep_reward: -1573.322, ep_step: 200 +2023-05-27 00:29:24 - SimpleLog - INFO: - episode: 13, ep_reward: -1530.919, ep_step: 200 +2023-05-27 00:29:26 - SimpleLog - INFO: - episode: 14, ep_reward: -1577.197, ep_step: 200 +2023-05-27 00:29:28 - SimpleLog - INFO: - episode: 15, ep_reward: -1576.294, ep_step: 200 +2023-05-27 00:29:30 - SimpleLog - INFO: - episode: 16, ep_reward: -1519.319, ep_step: 200 +2023-05-27 00:29:31 - SimpleLog - INFO: - episode: 17, ep_reward: -1491.932, ep_step: 200 +2023-05-27 00:29:33 - SimpleLog - INFO: - episode: 18, ep_reward: -1440.715, ep_step: 200 +2023-05-27 00:29:34 - SimpleLog - INFO: - episode: 19, ep_reward: -1511.762, ep_step: 200 +2023-05-27 00:29:37 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: -1492.909 +2023-05-27 00:29:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -1492.909, save the best model! +2023-05-27 00:29:38 - SimpleLog - INFO: - episode: 20, ep_reward: -1555.738, ep_step: 200 +2023-05-27 00:29:39 - SimpleLog - INFO: - episode: 21, ep_reward: -1527.226, ep_step: 200 +2023-05-27 00:29:41 - SimpleLog - INFO: - episode: 22, ep_reward: -1264.275, ep_step: 200 +2023-05-27 00:29:43 - SimpleLog - INFO: - episode: 23, ep_reward: -1258.880, ep_step: 200 +2023-05-27 00:29:44 - SimpleLog - INFO: - episode: 24, ep_reward: -1512.860, ep_step: 200 +2023-05-27 00:29:46 - SimpleLog - INFO: - episode: 25, ep_reward: -1531.582, ep_step: 200 +2023-05-27 00:29:47 - SimpleLog - INFO: - episode: 26, ep_reward: -1530.531, ep_step: 200 +2023-05-27 00:29:49 - SimpleLog - INFO: - episode: 27, ep_reward: -1343.932, ep_step: 200 +2023-05-27 00:29:50 - SimpleLog - INFO: - episode: 28, ep_reward: -1537.344, ep_step: 200 +2023-05-27 00:29:52 - SimpleLog - INFO: - episode: 29, ep_reward: -1409.571, ep_step: 200 +2023-05-27 00:29:55 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: -1492.954 +2023-05-27 00:29:56 - SimpleLog - INFO: - episode: 30, ep_reward: -1519.580, ep_step: 200 +2023-05-27 00:29:57 - SimpleLog - INFO: - episode: 31, ep_reward: -1388.753, ep_step: 200 +2023-05-27 00:29:59 - SimpleLog - INFO: - episode: 32, ep_reward: -1063.628, ep_step: 200 +2023-05-27 00:30:01 - SimpleLog - INFO: - episode: 33, ep_reward: -1168.097, ep_step: 200 +2023-05-27 00:30:02 - SimpleLog - INFO: - episode: 34, ep_reward: -1331.366, ep_step: 200 +2023-05-27 00:30:04 - SimpleLog - INFO: - episode: 35, ep_reward: -1293.768, ep_step: 200 +2023-05-27 00:30:05 - SimpleLog - INFO: - episode: 36, ep_reward: -1034.570, ep_step: 200 +2023-05-27 00:30:07 - SimpleLog - INFO: - episode: 37, ep_reward: -1553.501, ep_step: 200 +2023-05-27 00:30:09 - SimpleLog - INFO: - episode: 38, ep_reward: -1328.453, ep_step: 200 +2023-05-27 00:30:10 - SimpleLog - INFO: - episode: 39, ep_reward: -1194.988, ep_step: 200 +2023-05-27 00:30:13 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: -1493.162 +2023-05-27 00:30:14 - SimpleLog - INFO: - episode: 40, ep_reward: -1460.393, ep_step: 200 +2023-05-27 00:30:15 - SimpleLog - INFO: - episode: 41, ep_reward: -914.100, ep_step: 200 +2023-05-27 00:30:17 - SimpleLog - INFO: - episode: 42, ep_reward: -808.302, ep_step: 200 +2023-05-27 00:30:18 - SimpleLog - INFO: - episode: 43, ep_reward: -955.122, ep_step: 200 +2023-05-27 00:30:20 - SimpleLog - INFO: - episode: 44, ep_reward: -565.088, ep_step: 200 +2023-05-27 00:30:21 - SimpleLog - INFO: - episode: 45, ep_reward: -656.654, ep_step: 200 +2023-05-27 00:30:23 - SimpleLog - INFO: - episode: 46, ep_reward: -948.915, ep_step: 200 +2023-05-27 00:30:25 - SimpleLog - INFO: - episode: 47, ep_reward: -1058.994, ep_step: 200 +2023-05-27 00:30:26 - SimpleLog - INFO: - episode: 48, ep_reward: -828.764, ep_step: 200 +2023-05-27 00:30:28 - SimpleLog - INFO: - episode: 49, ep_reward: -785.656, ep_step: 200 +2023-05-27 00:30:30 - SimpleLog - INFO: - update_step: 10000, online_eval_reward: -513.639 +2023-05-27 00:30:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -513.639, save the best model! +2023-05-27 00:30:31 - SimpleLog - INFO: - episode: 50, ep_reward: -509.437, ep_step: 200 +2023-05-27 00:30:33 - SimpleLog - INFO: - episode: 51, ep_reward: -617.535, ep_step: 200 +2023-05-27 00:30:34 - SimpleLog - INFO: - episode: 52, ep_reward: -511.001, ep_step: 200 +2023-05-27 00:30:36 - SimpleLog - INFO: - episode: 53, ep_reward: -726.522, ep_step: 200 +2023-05-27 00:30:38 - SimpleLog - INFO: - episode: 54, ep_reward: -638.109, ep_step: 200 +2023-05-27 00:30:39 - SimpleLog - INFO: - episode: 55, ep_reward: -765.023, ep_step: 200 +2023-05-27 00:30:41 - SimpleLog - INFO: - episode: 56, ep_reward: -515.006, ep_step: 200 +2023-05-27 00:30:42 - SimpleLog - INFO: - episode: 57, ep_reward: -518.109, ep_step: 200 +2023-05-27 00:30:44 - SimpleLog - INFO: - episode: 58, ep_reward: -498.920, ep_step: 200 +2023-05-27 00:30:46 - SimpleLog - INFO: - episode: 59, ep_reward: -742.844, ep_step: 200 +2023-05-27 00:30:49 - SimpleLog - INFO: - update_step: 12000, online_eval_reward: -361.109 +2023-05-27 00:30:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -361.109, save the best model! +2023-05-27 00:30:49 - SimpleLog - INFO: - episode: 60, ep_reward: -793.589, ep_step: 200 +2023-05-27 00:30:51 - SimpleLog - INFO: - episode: 61, ep_reward: -581.931, ep_step: 200 +2023-05-27 00:30:53 - SimpleLog - INFO: - episode: 62, ep_reward: -739.699, ep_step: 200 +2023-05-27 00:30:54 - SimpleLog - INFO: - episode: 63, ep_reward: -587.436, ep_step: 200 +2023-05-27 00:30:56 - SimpleLog - INFO: - episode: 64, ep_reward: -454.861, ep_step: 200 +2023-05-27 00:30:57 - SimpleLog - INFO: - episode: 65, ep_reward: -429.372, ep_step: 200 +2023-05-27 00:30:59 - SimpleLog - INFO: - episode: 66, ep_reward: -335.385, ep_step: 200 +2023-05-27 00:31:01 - SimpleLog - INFO: - episode: 67, ep_reward: -343.434, ep_step: 200 +2023-05-27 00:31:02 - SimpleLog - INFO: - episode: 68, ep_reward: -449.724, ep_step: 200 +2023-05-27 00:31:04 - SimpleLog - INFO: - episode: 69, ep_reward: -336.069, ep_step: 200 +2023-05-27 00:31:07 - SimpleLog - INFO: - update_step: 14000, online_eval_reward: -335.937 +2023-05-27 00:31:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -335.937, save the best model! +2023-05-27 00:31:08 - SimpleLog - INFO: - episode: 70, ep_reward: -334.573, ep_step: 200 +2023-05-27 00:31:10 - SimpleLog - INFO: - episode: 71, ep_reward: -455.101, ep_step: 200 +2023-05-27 00:31:11 - SimpleLog - INFO: - episode: 72, ep_reward: -450.986, ep_step: 200 +2023-05-27 00:31:13 - SimpleLog - INFO: - episode: 73, ep_reward: -325.188, ep_step: 200 +2023-05-27 00:31:14 - SimpleLog - INFO: - episode: 74, ep_reward: -335.417, ep_step: 200 +2023-05-27 00:31:16 - SimpleLog - INFO: - episode: 75, ep_reward: -448.173, ep_step: 200 +2023-05-27 00:31:18 - SimpleLog - INFO: - episode: 76, ep_reward: -317.437, ep_step: 200 +2023-05-27 00:31:20 - SimpleLog - INFO: - episode: 77, ep_reward: -303.536, ep_step: 200 +2023-05-27 00:31:21 - SimpleLog - INFO: - episode: 78, ep_reward: -325.795, ep_step: 200 +2023-05-27 00:31:23 - SimpleLog - INFO: - episode: 79, ep_reward: -315.077, ep_step: 200 +2023-05-27 00:31:26 - SimpleLog - INFO: - update_step: 16000, online_eval_reward: -323.018 +2023-05-27 00:31:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -323.018, save the best model! +2023-05-27 00:31:27 - SimpleLog - INFO: - episode: 80, ep_reward: -426.788, ep_step: 200 +2023-05-27 00:31:29 - SimpleLog - INFO: - episode: 81, ep_reward: -431.983, ep_step: 200 +2023-05-27 00:31:31 - SimpleLog - INFO: - episode: 82, ep_reward: -315.165, ep_step: 200 +2023-05-27 00:31:33 - SimpleLog - INFO: - episode: 83, ep_reward: -324.079, ep_step: 200 +2023-05-27 00:31:34 - SimpleLog - INFO: - episode: 84, ep_reward: -321.491, ep_step: 200 +2023-05-27 00:31:36 - SimpleLog - INFO: - episode: 85, ep_reward: -396.571, ep_step: 200 +2023-05-27 00:31:37 - SimpleLog - INFO: - episode: 86, ep_reward: -397.450, ep_step: 200 +2023-05-27 00:31:39 - SimpleLog - INFO: - episode: 87, ep_reward: -401.147, ep_step: 200 +2023-05-27 00:31:41 - SimpleLog - INFO: - episode: 88, ep_reward: -402.048, ep_step: 200 +2023-05-27 00:31:42 - SimpleLog - INFO: - episode: 89, ep_reward: -400.057, ep_step: 200 +2023-05-27 00:31:46 - SimpleLog - INFO: - update_step: 18000, online_eval_reward: -401.499 +2023-05-27 00:31:46 - SimpleLog - INFO: - episode: 90, ep_reward: -403.737, ep_step: 200 +2023-05-27 00:31:48 - SimpleLog - INFO: - episode: 91, ep_reward: -395.337, ep_step: 200 +2023-05-27 00:31:49 - SimpleLog - INFO: - episode: 92, ep_reward: -405.396, ep_step: 200 +2023-05-27 00:31:51 - SimpleLog - INFO: - episode: 93, ep_reward: -394.181, ep_step: 200 +2023-05-27 00:31:52 - SimpleLog - INFO: - episode: 94, ep_reward: -396.762, ep_step: 200 +2023-05-27 00:31:54 - SimpleLog - INFO: - episode: 95, ep_reward: -395.173, ep_step: 200 +2023-05-27 00:31:56 - SimpleLog - INFO: - episode: 96, ep_reward: -1220.214, ep_step: 200 +2023-05-27 00:31:57 - SimpleLog - INFO: - episode: 97, ep_reward: -391.593, ep_step: 200 +2023-05-27 00:31:59 - SimpleLog - INFO: - episode: 98, ep_reward: -408.688, ep_step: 200 +2023-05-27 00:32:01 - SimpleLog - INFO: - episode: 99, ep_reward: -392.954, ep_step: 200 +2023-05-27 00:32:04 - SimpleLog - INFO: - update_step: 20000, online_eval_reward: -265.208 +2023-05-27 00:32:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -265.208, save the best model! +2023-05-27 00:32:04 - SimpleLog - INFO: - episode: 100, ep_reward: -400.185, ep_step: 200 +2023-05-27 00:32:06 - SimpleLog - INFO: - episode: 101, ep_reward: -261.834, ep_step: 200 +2023-05-27 00:32:08 - SimpleLog - INFO: - episode: 102, ep_reward: -386.378, ep_step: 200 +2023-05-27 00:32:09 - SimpleLog - INFO: - episode: 103, ep_reward: -398.440, ep_step: 200 +2023-05-27 00:32:11 - SimpleLog - INFO: - episode: 104, ep_reward: -290.212, ep_step: 200 +2023-05-27 00:32:13 - SimpleLog - INFO: - episode: 105, ep_reward: -276.961, ep_step: 200 +2023-05-27 00:32:14 - SimpleLog - INFO: - episode: 106, ep_reward: -326.268, ep_step: 200 +2023-05-27 00:32:16 - SimpleLog - INFO: - episode: 107, ep_reward: -318.556, ep_step: 200 +2023-05-27 00:32:18 - SimpleLog - INFO: - episode: 108, ep_reward: -310.143, ep_step: 200 +2023-05-27 00:32:19 - SimpleLog - INFO: - episode: 109, ep_reward: -296.360, ep_step: 200 +2023-05-27 00:32:22 - SimpleLog - INFO: - update_step: 22000, online_eval_reward: -319.053 +2023-05-27 00:32:23 - SimpleLog - INFO: - episode: 110, ep_reward: -312.254, ep_step: 200 +2023-05-27 00:32:24 - SimpleLog - INFO: - episode: 111, ep_reward: -304.765, ep_step: 200 +2023-05-27 00:32:26 - SimpleLog - INFO: - episode: 112, ep_reward: -299.560, ep_step: 200 +2023-05-27 00:32:28 - SimpleLog - INFO: - episode: 113, ep_reward: -295.238, ep_step: 200 +2023-05-27 00:32:29 - SimpleLog - INFO: - episode: 114, ep_reward: -322.348, ep_step: 200 +2023-05-27 00:32:31 - SimpleLog - INFO: - episode: 115, ep_reward: -315.010, ep_step: 200 +2023-05-27 00:32:33 - SimpleLog - INFO: - episode: 116, ep_reward: -317.994, ep_step: 200 +2023-05-27 00:32:34 - SimpleLog - INFO: - episode: 117, ep_reward: -301.996, ep_step: 200 +2023-05-27 00:32:36 - SimpleLog - INFO: - episode: 118, ep_reward: -323.265, ep_step: 200 +2023-05-27 00:32:37 - SimpleLog - INFO: - episode: 119, ep_reward: -332.644, ep_step: 200 +2023-05-27 00:32:40 - SimpleLog - INFO: - update_step: 24000, online_eval_reward: -330.781 +2023-05-27 00:32:41 - SimpleLog - INFO: - episode: 120, ep_reward: -340.317, ep_step: 200 +2023-05-27 00:32:43 - SimpleLog - INFO: - episode: 121, ep_reward: -330.843, ep_step: 200 +2023-05-27 00:32:44 - SimpleLog - INFO: - episode: 122, ep_reward: -324.560, ep_step: 200 +2023-05-27 00:32:46 - SimpleLog - INFO: - episode: 123, ep_reward: -303.582, ep_step: 200 +2023-05-27 00:32:47 - SimpleLog - INFO: - episode: 124, ep_reward: -318.335, ep_step: 200 +2023-05-27 00:32:49 - SimpleLog - INFO: - episode: 125, ep_reward: -329.885, ep_step: 200 +2023-05-27 00:32:51 - SimpleLog - INFO: - episode: 126, ep_reward: -473.694, ep_step: 200 +2023-05-27 00:32:52 - SimpleLog - INFO: - episode: 127, ep_reward: -335.948, ep_step: 200 +2023-05-27 00:32:54 - SimpleLog - INFO: - episode: 128, ep_reward: -462.891, ep_step: 200 +2023-05-27 00:32:56 - SimpleLog - INFO: - episode: 129, ep_reward: -332.484, ep_step: 200 +2023-05-27 00:32:59 - SimpleLog - INFO: - update_step: 26000, online_eval_reward: -335.792 +2023-05-27 00:32:59 - SimpleLog - INFO: - episode: 130, ep_reward: -331.908, ep_step: 200 +2023-05-27 00:33:01 - SimpleLog - INFO: - episode: 131, ep_reward: -333.130, ep_step: 200 +2023-05-27 00:33:03 - SimpleLog - INFO: - episode: 132, ep_reward: -313.720, ep_step: 200 +2023-05-27 00:33:04 - SimpleLog - INFO: - episode: 133, ep_reward: -337.996, ep_step: 200 +2023-05-27 00:33:06 - SimpleLog - INFO: - episode: 134, ep_reward: -345.811, ep_step: 200 +2023-05-27 00:33:08 - SimpleLog - INFO: - episode: 135, ep_reward: -340.689, ep_step: 200 +2023-05-27 00:33:09 - SimpleLog - INFO: - episode: 136, ep_reward: -344.886, ep_step: 200 +2023-05-27 00:33:11 - SimpleLog - INFO: - episode: 137, ep_reward: -311.142, ep_step: 200 +2023-05-27 00:33:13 - SimpleLog - INFO: - episode: 138, ep_reward: -348.848, ep_step: 200 +2023-05-27 00:33:14 - SimpleLog - INFO: - episode: 139, ep_reward: -339.404, ep_step: 200 +2023-05-27 00:33:17 - SimpleLog - INFO: - update_step: 28000, online_eval_reward: -338.074 +2023-05-27 00:33:18 - SimpleLog - INFO: - episode: 140, ep_reward: -326.129, ep_step: 200 +2023-05-27 00:33:19 - SimpleLog - INFO: - episode: 141, ep_reward: -347.216, ep_step: 200 +2023-05-27 00:33:21 - SimpleLog - INFO: - episode: 142, ep_reward: -330.485, ep_step: 200 +2023-05-27 00:33:23 - SimpleLog - INFO: - episode: 143, ep_reward: -333.542, ep_step: 200 +2023-05-27 00:33:24 - SimpleLog - INFO: - episode: 144, ep_reward: -331.096, ep_step: 200 +2023-05-27 00:33:26 - SimpleLog - INFO: - episode: 145, ep_reward: -338.880, ep_step: 200 +2023-05-27 00:33:27 - SimpleLog - INFO: - episode: 146, ep_reward: -337.393, ep_step: 200 +2023-05-27 00:33:29 - SimpleLog - INFO: - episode: 147, ep_reward: -318.588, ep_step: 200 +2023-05-27 00:33:31 - SimpleLog - INFO: - episode: 148, ep_reward: -336.684, ep_step: 200 +2023-05-27 00:33:32 - SimpleLog - INFO: - episode: 149, ep_reward: -336.559, ep_step: 200 +2023-05-27 00:33:36 - SimpleLog - INFO: - update_step: 30000, online_eval_reward: -336.016 +2023-05-27 00:33:36 - SimpleLog - INFO: - episode: 150, ep_reward: -313.757, ep_step: 200 +2023-05-27 00:33:38 - SimpleLog - INFO: - episode: 151, ep_reward: -344.355, ep_step: 200 +2023-05-27 00:33:39 - SimpleLog - INFO: - episode: 152, ep_reward: -323.297, ep_step: 200 +2023-05-27 00:33:41 - SimpleLog - INFO: - episode: 153, ep_reward: -327.646, ep_step: 200 +2023-05-27 00:33:42 - SimpleLog - INFO: - episode: 154, ep_reward: -335.975, ep_step: 200 +2023-05-27 00:33:44 - SimpleLog - INFO: - episode: 155, ep_reward: -318.358, ep_step: 200 +2023-05-27 00:33:45 - SimpleLog - INFO: - episode: 156, ep_reward: -324.404, ep_step: 200 +2023-05-27 00:33:47 - SimpleLog - INFO: - episode: 157, ep_reward: -325.595, ep_step: 200 +2023-05-27 00:33:48 - SimpleLog - INFO: - episode: 158, ep_reward: -336.706, ep_step: 200 +2023-05-27 00:33:50 - SimpleLog - INFO: - episode: 159, ep_reward: -324.430, ep_step: 200 +2023-05-27 00:33:53 - SimpleLog - INFO: - update_step: 32000, online_eval_reward: -330.636 +2023-05-27 00:33:54 - SimpleLog - INFO: - episode: 160, ep_reward: -322.437, ep_step: 200 +2023-05-27 00:33:55 - SimpleLog - INFO: - episode: 161, ep_reward: -336.050, ep_step: 200 +2023-05-27 00:33:57 - SimpleLog - INFO: - episode: 162, ep_reward: -331.872, ep_step: 200 +2023-05-27 00:33:59 - SimpleLog - INFO: - episode: 163, ep_reward: -321.575, ep_step: 200 +2023-05-27 00:34:00 - SimpleLog - INFO: - episode: 164, ep_reward: -296.710, ep_step: 200 +2023-05-27 00:34:02 - SimpleLog - INFO: - episode: 165, ep_reward: -326.305, ep_step: 200 +2023-05-27 00:34:03 - SimpleLog - INFO: - episode: 166, ep_reward: -315.655, ep_step: 200 +2023-05-27 00:34:05 - SimpleLog - INFO: - episode: 167, ep_reward: -327.117, ep_step: 200 +2023-05-27 00:34:07 - SimpleLog - INFO: - episode: 168, ep_reward: -315.649, ep_step: 200 +2023-05-27 00:34:08 - SimpleLog - INFO: - episode: 169, ep_reward: -325.160, ep_step: 200 +2023-05-27 00:34:11 - SimpleLog - INFO: - update_step: 34000, online_eval_reward: -325.015 +2023-05-27 00:34:12 - SimpleLog - INFO: - episode: 170, ep_reward: -328.977, ep_step: 200 +2023-05-27 00:34:13 - SimpleLog - INFO: - episode: 171, ep_reward: -322.324, ep_step: 200 +2023-05-27 00:34:15 - SimpleLog - INFO: - episode: 172, ep_reward: -294.012, ep_step: 200 +2023-05-27 00:34:16 - SimpleLog - INFO: - episode: 173, ep_reward: -319.424, ep_step: 200 +2023-05-27 00:34:18 - SimpleLog - INFO: - episode: 174, ep_reward: -304.872, ep_step: 200 +2023-05-27 00:34:19 - SimpleLog - INFO: - episode: 175, ep_reward: -330.653, ep_step: 200 +2023-05-27 00:34:21 - SimpleLog - INFO: - episode: 176, ep_reward: -330.855, ep_step: 200 +2023-05-27 00:34:23 - SimpleLog - INFO: - episode: 177, ep_reward: -320.936, ep_step: 200 +2023-05-27 00:34:24 - SimpleLog - INFO: - episode: 178, ep_reward: -293.672, ep_step: 200 +2023-05-27 00:34:26 - SimpleLog - INFO: - episode: 179, ep_reward: -305.842, ep_step: 200 +2023-05-27 00:34:29 - SimpleLog - INFO: - update_step: 36000, online_eval_reward: -316.303 +2023-05-27 00:34:29 - SimpleLog - INFO: - episode: 180, ep_reward: -304.273, ep_step: 200 +2023-05-27 00:34:31 - SimpleLog - INFO: - episode: 181, ep_reward: -319.363, ep_step: 200 +2023-05-27 00:34:33 - SimpleLog - INFO: - episode: 182, ep_reward: -309.749, ep_step: 200 +2023-05-27 00:34:34 - SimpleLog - INFO: - episode: 183, ep_reward: -295.360, ep_step: 200 +2023-05-27 00:34:36 - SimpleLog - INFO: - episode: 184, ep_reward: -260.432, ep_step: 200 +2023-05-27 00:34:38 - SimpleLog - INFO: - episode: 185, ep_reward: -299.548, ep_step: 200 +2023-05-27 00:34:39 - SimpleLog - INFO: - episode: 186, ep_reward: -306.128, ep_step: 200 +2023-05-27 00:34:41 - SimpleLog - INFO: - episode: 187, ep_reward: -1411.605, ep_step: 200 +2023-05-27 00:34:42 - SimpleLog - INFO: - episode: 188, ep_reward: -1556.318, ep_step: 200 +2023-05-27 00:34:44 - SimpleLog - INFO: - episode: 189, ep_reward: -1544.945, ep_step: 200 +2023-05-27 00:34:47 - SimpleLog - INFO: - update_step: 38000, online_eval_reward: -304.749 +2023-05-27 00:34:47 - SimpleLog - INFO: - episode: 190, ep_reward: -383.180, ep_step: 200 +2023-05-27 00:34:49 - SimpleLog - INFO: - episode: 191, ep_reward: -1478.870, ep_step: 200 +2023-05-27 00:34:51 - SimpleLog - INFO: - episode: 192, ep_reward: -278.173, ep_step: 200 +2023-05-27 00:34:52 - SimpleLog - INFO: - episode: 193, ep_reward: -274.785, ep_step: 200 +2023-05-27 00:34:54 - SimpleLog - INFO: - episode: 194, ep_reward: -258.812, ep_step: 200 +2023-05-27 00:34:56 - SimpleLog - INFO: - episode: 195, ep_reward: -302.596, ep_step: 200 +2023-05-27 00:34:57 - SimpleLog - INFO: - episode: 196, ep_reward: -300.993, ep_step: 200 +2023-05-27 00:34:59 - SimpleLog - INFO: - episode: 197, ep_reward: -298.122, ep_step: 200 +2023-05-27 00:35:00 - SimpleLog - INFO: - episode: 198, ep_reward: -292.155, ep_step: 200 +2023-05-27 00:35:02 - SimpleLog - INFO: - episode: 199, ep_reward: -278.364, ep_step: 200 +2023-05-27 00:35:02 - SimpleLog - INFO: - Finish training! total time consumed: 362.67s diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/10000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/10000 new file mode 100644 index 0000000000000000000000000000000000000000..d390d2b7e3a7761479aa97aa7142347d6f169be8 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/10000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5a0f4913f71236ce6c07a7628d2b8cdb7ace2b3f1c95572213663d4fb5ab3d6 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/12000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/12000 new file mode 100644 index 0000000000000000000000000000000000000000..177602263071cc026c05224fbd1707b9a4b857c1 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/12000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e81a939426933ae5ef75709f719aba22d462889f18f73e32c1a0f293d5a667 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/14000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/14000 new file mode 100644 index 0000000000000000000000000000000000000000..a4dda526af7ed3b4b16effb34095964fe57d08c3 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/14000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abbb8e3b1f2cf5a24b1c592bfd7f2ffa987f1e47bff7cc446f0cbd4e4ff4c96c +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/16000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/16000 new file mode 100644 index 0000000000000000000000000000000000000000..0ba1d3df9e8827d548f923063c8788b5f5f66bf5 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/16000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c71f548a6f3e22e82dc6530e1d8cb1a67df9807a56665b9ad9c48d64c9de85f3 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/18000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/18000 new file mode 100644 index 0000000000000000000000000000000000000000..0f0f85a932ce37d18dc41d2170c4b47e44d3f376 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/18000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d156355068a3421b1533cc15fe7a976d28b1de4806b0ab315d27a3b1d882f8 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/2000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/2000 new file mode 100644 index 0000000000000000000000000000000000000000..efc8119f7092abe3c876513a3a691503accb1a11 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/2000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e03aa07e52d527010865ee3ae41ea3be55f6ca39c5d7471dea4ed990b91ce4e2 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/20000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/20000 new file mode 100644 index 0000000000000000000000000000000000000000..e7f87e8cf816bb13de588be54d738d8f6335463b --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/20000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02aaf9e92804edca69782db608b29e80329c013ccd696461f4f0d36ae7ee41ca +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/22000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/22000 new file mode 100644 index 0000000000000000000000000000000000000000..62ad0c8312be00b44d5b1cb9e58163bce6977371 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/22000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87d0fb2505e5988110b0eddf1041ec5384b010197bd549f0ff5d402d035e9d3 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/24000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/24000 new file mode 100644 index 0000000000000000000000000000000000000000..27fc2f51b8ca936d91187150380198e5336fba91 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/24000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:588ca5f18e5b067954bc6847e615b2ea14362ba14325c0575a6cbff9c74ea44c +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/26000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/26000 new file mode 100644 index 0000000000000000000000000000000000000000..b5592e1addc7b9d8e4858820aa718479347b3c50 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/26000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e49d9071ede06cacd07110de39179dbe8828b1ea21048fde34cae1b6ddc38ad +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/28000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/28000 new file mode 100644 index 0000000000000000000000000000000000000000..24e0b34b9ebb12a4098639f1ab19df071dabea16 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/28000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111b05394f08730189c33348ba0d8f9d56ba278002bce99d5ac5bc404f564110 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/30000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/30000 new file mode 100644 index 0000000000000000000000000000000000000000..d27424c3738d716cc2a3c2744365104121dc75d3 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/30000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a740a98678c7dcf163f59403821281dbcefc2be1a69cb8c30bcadb0f1cde0672 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/32000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/32000 new file mode 100644 index 0000000000000000000000000000000000000000..66d9e2475146b8a2826138e4463a64c50a354376 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/32000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e63c6ffd4618afe9e62d62d86ce5573c93246844fc086d133cde7bf6a6bb94b +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/34000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/34000 new file mode 100644 index 0000000000000000000000000000000000000000..7b9e0819ded605ab034f17c450047d5234398702 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/34000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcf4e0d03945eb77b4dde01248645546475f7c5cfc6acf75723ddbc2d647b568 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/36000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/36000 new file mode 100644 index 0000000000000000000000000000000000000000..452a34d0a689b1f7d67992bba0d9687a4844701e --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/36000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1afa10737122a5a8846212bdf1cb37a947f7f3466deb192f6268f38aa7db2ec +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/38000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/38000 new file mode 100644 index 0000000000000000000000000000000000000000..15654875fe5ea5740205d48b0d643e93fc9e5322 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/38000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2674c35051503f006f3cf7ccc741b5ec8a23adb7d1689032d28052854f7e9a4 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/4000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/4000 new file mode 100644 index 0000000000000000000000000000000000000000..d7473a89700671f7e24ac44973a1421a0e7f9bf0 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/4000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c21a42fbbdc59897b61286188a960dc272bb7adf923b71d44ab7747e641c7cd +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/6000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/6000 new file mode 100644 index 0000000000000000000000000000000000000000..cb572990c46f9eb15d47de909225ff00455c0683 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/6000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597070c437aff8684099e86b0834823bd2ac3c7617a6f83ae179d90abd253a90 +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/8000 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/8000 new file mode 100644 index 0000000000000000000000000000000000000000..075d0af61aaf90727300f967d86ea98944319385 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/8000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6f63b5e5ec646ec018a8978ca57b2a8180f61bd3748da9cb471a4cab5d821db +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/best b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/best new file mode 100644 index 0000000000000000000000000000000000000000..e7f87e8cf816bb13de588be54d738d8f6335463b --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/models/best @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02aaf9e92804edca69782db608b29e80329c013ccd696461f4f0d36ae7ee41ca +size 1084125 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/tb_logs/interact/events.out.tfevents.1685118539.DESKTOP-H34HQIQ.43940.0 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/tb_logs/interact/events.out.tfevents.1685118539.DESKTOP-H34HQIQ.43940.0 new file mode 100644 index 0000000000000000000000000000000000000000..4ea38df63d81cc2257a41f7f6dbfd3bbfe3e6aa8 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/tb_logs/interact/events.out.tfevents.1685118539.DESKTOP-H34HQIQ.43940.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd8d5a353d2b792ec15a8f461b4db9441c83919ca43d4305fee5ddaa62b01532 +size 19780 diff --git a/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/tb_logs/model/events.out.tfevents.1685118539.DESKTOP-H34HQIQ.43940.1 b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/tb_logs/model/events.out.tfevents.1685118539.DESKTOP-H34HQIQ.43940.1 new file mode 100644 index 0000000000000000000000000000000000000000..d54487dffeb8a6a904a61aea2d254d988a935391 --- /dev/null +++ b/ClassControl/Pendulum-v1/Train_single_Pendulum-v1_DDPG_20230527-002859/tb_logs/model/events.out.tfevents.1685118539.DESKTOP-H34HQIQ.43940.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8047094aa74a6136b7eace7758fcc2778e725590edcf43b910e8bf76f6b0c28 +size 6609301 diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/config.yaml b/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/config.yaml deleted file mode 100644 index e27b3dca8fe4c2a3174684a23aa950b22540d994..0000000000000000000000000000000000000000 --- a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/config.yaml +++ /dev/null @@ -1,27 +0,0 @@ -general_cfg: - algo_name: DDPG - device: cuda - env_name: Pendulum-v1 - eval_eps: 10 - eval_per_episode: 5 - load_checkpoint: false - load_path: Train_CartPole-v1_DQN_20221026-054757 - max_steps: 200 - mode: train - new_step_api: true - render: false - save_fig: true - seed: 10 - show_fig: false - test_eps: 10 - train_eps: 400 - wrapper: null -algo_cfg: - actor_hidden_dim: 256 - actor_lr: 0.0001 - batch_size: 128 - buffer_size: 8000 - critic_hidden_dim: 256 - critic_lr: 0.001 - gamma: 0.99 - tau: 0.001 diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/logs/log.txt b/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/logs/log.txt deleted file mode 100644 index 34d6b2285ac685ecbdb243cb427b4c5592942b59..0000000000000000000000000000000000000000 --- a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/logs/log.txt +++ /dev/null @@ -1,454 +0,0 @@ -2022-12-01 11:47:04 - r - INFO: - Hyperparameters: -2022-12-01 11:47:04 - r - INFO: - ================================================================================ -2022-12-01 11:47:04 - r - INFO: - Name Value Type -2022-12-01 11:47:04 - r - INFO: - env_name Pendulum-v1 -2022-12-01 11:47:04 - r - INFO: - new_step_api 1 -2022-12-01 11:47:04 - r - INFO: - wrapper None -2022-12-01 11:47:04 - r - INFO: - render 0 -2022-12-01 11:47:04 - r - INFO: - algo_name DDPG -2022-12-01 11:47:04 - r - INFO: - mode train -2022-12-01 11:47:04 - r - INFO: - seed 10 -2022-12-01 11:47:04 - r - INFO: - device cuda -2022-12-01 11:47:04 - r - INFO: - train_eps 400 -2022-12-01 11:47:04 - r - INFO: - test_eps 10 -2022-12-01 11:47:04 - r - INFO: - eval_eps 10 -2022-12-01 11:47:04 - r - INFO: - eval_per_episode 5 -2022-12-01 11:47:04 - r - INFO: - max_steps 200 -2022-12-01 11:47:04 - r - INFO: - load_checkpoint 0 -2022-12-01 11:47:04 - r - INFO: - load_path Train_CartPole-v1_DQN_20221026-054757 -2022-12-01 11:47:04 - r - INFO: - show_fig 0 -2022-12-01 11:47:04 - r - INFO: - save_fig 1 -2022-12-01 11:47:04 - r - INFO: - gamma 0.99 -2022-12-01 11:47:04 - r - INFO: - critic_lr 0.001 -2022-12-01 11:47:04 - r - INFO: - actor_lr 0.0001 -2022-12-01 11:47:04 - r - INFO: - buffer_size 8000 -2022-12-01 11:47:04 - r - INFO: - batch_size 128 -2022-12-01 11:47:04 - r - INFO: - tau 0.001 -2022-12-01 11:47:04 - r - INFO: - critic_hidden_dim 256 -2022-12-01 11:47:04 - r - INFO: - actor_hidden_dim 256 -2022-12-01 11:47:04 - r - INFO: - ================================================================================ -2022-12-01 11:47:04 - r - INFO: - action_bound: 2.0 -2022-12-01 11:47:04 - r - INFO: - n_states: 3, n_actions: 1 -2022-12-01 11:47:07 - r - INFO: - Start training! -2022-12-01 11:47:07 - r - INFO: - Env: Pendulum-v1, Algorithm: DDPG, Device: cuda -2022-12-01 11:47:08 - r - INFO: - Episode: 1/400, Reward: -1212.568, Step: 200 -2022-12-01 11:47:08 - r - INFO: - Episode: 2/400, Reward: -1623.901, Step: 200 -2022-12-01 11:47:09 - r - INFO: - Episode: 3/400, Reward: -1487.254, Step: 200 -2022-12-01 11:47:10 - r - INFO: - Episode: 4/400, Reward: -1453.605, Step: 200 -2022-12-01 11:47:10 - r - INFO: - Episode: 5/400, Reward: -1673.476, Step: 200 -2022-12-01 11:47:11 - r - INFO: - Current episode 5 has the best eval reward: -1636.256 -2022-12-01 11:47:12 - r - INFO: - Episode: 6/400, Reward: -1414.224, Step: 200 -2022-12-01 11:47:12 - r - INFO: - Episode: 7/400, Reward: -1510.705, Step: 200 -2022-12-01 11:47:13 - r - INFO: - Episode: 8/400, Reward: -1501.576, Step: 200 -2022-12-01 11:47:14 - r - INFO: - Episode: 9/400, Reward: -1512.594, Step: 200 -2022-12-01 11:47:14 - r - INFO: - Episode: 10/400, Reward: -1524.774, Step: 200 -2022-12-01 11:47:15 - r - INFO: - Current episode 10 has the best eval reward: -1574.442 -2022-12-01 11:47:16 - r - INFO: - Episode: 11/400, Reward: -1354.692, Step: 200 -2022-12-01 11:47:16 - r - INFO: - Episode: 12/400, Reward: -1554.375, Step: 200 -2022-12-01 11:47:17 - r - INFO: - Episode: 13/400, Reward: -1569.261, Step: 200 -2022-12-01 11:47:18 - r - INFO: - Episode: 14/400, Reward: -1497.939, Step: 200 -2022-12-01 11:47:18 - r - INFO: - Episode: 15/400, Reward: -1569.101, Step: 200 -2022-12-01 11:47:20 - r - INFO: - Episode: 16/400, Reward: -1253.003, Step: 200 -2022-12-01 11:47:20 - r - INFO: - Episode: 17/400, Reward: -1545.806, Step: 200 -2022-12-01 11:47:21 - r - INFO: - Episode: 18/400, Reward: -1265.231, Step: 200 -2022-12-01 11:47:22 - r - INFO: - Episode: 19/400, Reward: -305.823, Step: 200 -2022-12-01 11:47:22 - r - INFO: - Episode: 20/400, Reward: -1357.265, Step: 200 -2022-12-01 11:47:23 - r - INFO: - Current episode 20 has the best eval reward: -1434.902 -2022-12-01 11:47:24 - r - INFO: - Episode: 21/400, Reward: -1296.912, Step: 200 -2022-12-01 11:47:25 - r - INFO: - Episode: 22/400, Reward: -1314.462, Step: 200 -2022-12-01 11:47:25 - r - INFO: - Episode: 23/400, Reward: -1249.900, Step: 200 -2022-12-01 11:47:26 - r - INFO: - Episode: 24/400, Reward: -1339.911, Step: 200 -2022-12-01 11:47:27 - r - INFO: - Episode: 25/400, Reward: -1366.518, Step: 200 -2022-12-01 11:47:27 - r - INFO: - Current episode 25 has the best eval reward: -1369.715 -2022-12-01 11:47:28 - r - INFO: - Episode: 26/400, Reward: -1260.492, Step: 200 -2022-12-01 11:47:29 - r - INFO: - Episode: 27/400, Reward: -1194.335, Step: 200 -2022-12-01 11:47:29 - r - INFO: - Episode: 28/400, Reward: -1153.404, Step: 200 -2022-12-01 11:47:30 - r - INFO: - Episode: 29/400, Reward: -1082.368, Step: 200 -2022-12-01 11:47:31 - r - INFO: - Episode: 30/400, Reward: -1171.469, Step: 200 -2022-12-01 11:47:31 - r - INFO: - Current episode 30 has the best eval reward: -1277.884 -2022-12-01 11:47:32 - r - INFO: - Episode: 31/400, Reward: -1200.771, Step: 200 -2022-12-01 11:47:33 - r - INFO: - Episode: 32/400, Reward: -1032.577, Step: 200 -2022-12-01 11:47:33 - r - INFO: - Episode: 33/400, Reward: -1118.504, Step: 200 -2022-12-01 11:47:34 - r - INFO: - Episode: 34/400, Reward: -812.889, Step: 200 -2022-12-01 11:47:35 - r - INFO: - Episode: 35/400, Reward: -1346.486, Step: 200 -2022-12-01 11:47:35 - r - INFO: - Current episode 35 has the best eval reward: -1259.006 -2022-12-01 11:47:36 - r - INFO: - Episode: 36/400, Reward: -1150.214, Step: 200 -2022-12-01 11:47:37 - r - INFO: - Episode: 37/400, Reward: -1270.615, Step: 200 -2022-12-01 11:47:38 - r - INFO: - Episode: 38/400, Reward: -1016.817, Step: 200 -2022-12-01 11:47:38 - r - INFO: - Episode: 39/400, Reward: -663.595, Step: 200 -2022-12-01 11:47:39 - r - INFO: - Episode: 40/400, Reward: -138.012, Step: 200 -2022-12-01 11:47:40 - r - INFO: - Current episode 40 has the best eval reward: -1166.679 -2022-12-01 11:47:41 - r - INFO: - Episode: 41/400, Reward: -934.253, Step: 200 -2022-12-01 11:47:41 - r - INFO: - Episode: 42/400, Reward: -260.424, Step: 200 -2022-12-01 11:47:42 - r - INFO: - Episode: 43/400, Reward: -326.425, Step: 200 -2022-12-01 11:47:43 - r - INFO: - Episode: 44/400, Reward: -133.962, Step: 200 -2022-12-01 11:47:43 - r - INFO: - Episode: 45/400, Reward: -264.038, Step: 200 -2022-12-01 11:47:44 - r - INFO: - Current episode 45 has the best eval reward: -917.545 -2022-12-01 11:47:45 - r - INFO: - Episode: 46/400, Reward: -1091.756, Step: 200 -2022-12-01 11:47:45 - r - INFO: - Episode: 47/400, Reward: -0.407, Step: 200 -2022-12-01 11:47:46 - r - INFO: - Episode: 48/400, Reward: -131.840, Step: 200 -2022-12-01 11:47:47 - r - INFO: - Episode: 49/400, Reward: -129.614, Step: 200 -2022-12-01 11:47:47 - r - INFO: - Episode: 50/400, Reward: -128.357, Step: 200 -2022-12-01 11:47:48 - r - INFO: - Current episode 50 has the best eval reward: -781.569 -2022-12-01 11:47:49 - r - INFO: - Episode: 51/400, Reward: -407.419, Step: 200 -2022-12-01 11:47:49 - r - INFO: - Episode: 52/400, Reward: -402.595, Step: 200 -2022-12-01 11:47:50 - r - INFO: - Episode: 53/400, Reward: -0.787, Step: 200 -2022-12-01 11:47:51 - r - INFO: - Episode: 54/400, Reward: -442.559, Step: 200 -2022-12-01 11:47:52 - r - INFO: - Episode: 55/400, Reward: -244.390, Step: 200 -2022-12-01 11:47:52 - r - INFO: - Current episode 55 has the best eval reward: -613.927 -2022-12-01 11:47:53 - r - INFO: - Episode: 56/400, Reward: -281.037, Step: 200 -2022-12-01 11:47:54 - r - INFO: - Episode: 57/400, Reward: -131.178, Step: 200 -2022-12-01 11:47:54 - r - INFO: - Episode: 58/400, Reward: -1.174, Step: 200 -2022-12-01 11:47:55 - r - INFO: - Episode: 59/400, Reward: -260.898, Step: 200 -2022-12-01 11:47:56 - r - INFO: - Episode: 60/400, Reward: -389.764, Step: 200 -2022-12-01 11:47:56 - r - INFO: - Current episode 60 has the best eval reward: -581.082 -2022-12-01 11:47:57 - r - INFO: - Episode: 61/400, Reward: -263.920, Step: 200 -2022-12-01 11:47:58 - r - INFO: - Episode: 62/400, Reward: -1.243, Step: 200 -2022-12-01 11:47:58 - r - INFO: - Episode: 63/400, Reward: -1256.841, Step: 200 -2022-12-01 11:47:59 - r - INFO: - Episode: 64/400, Reward: -132.499, Step: 200 -2022-12-01 11:48:00 - r - INFO: - Episode: 65/400, Reward: -397.011, Step: 200 -2022-12-01 11:48:00 - r - INFO: - Current episode 65 has the best eval reward: -390.975 -2022-12-01 11:48:01 - r - INFO: - Episode: 66/400, Reward: -124.641, Step: 200 -2022-12-01 11:48:02 - r - INFO: - Episode: 67/400, Reward: -263.838, Step: 200 -2022-12-01 11:48:02 - r - INFO: - Episode: 68/400, Reward: -384.373, Step: 200 -2022-12-01 11:48:03 - r - INFO: - Episode: 69/400, Reward: -123.299, Step: 200 -2022-12-01 11:48:04 - r - INFO: - Episode: 70/400, Reward: -1502.847, Step: 200 -2022-12-01 11:48:05 - r - INFO: - Episode: 71/400, Reward: -354.070, Step: 200 -2022-12-01 11:48:06 - r - INFO: - Episode: 72/400, Reward: -1039.914, Step: 200 -2022-12-01 11:48:06 - r - INFO: - Episode: 73/400, Reward: -242.399, Step: 200 -2022-12-01 11:48:07 - r - INFO: - Episode: 74/400, Reward: -122.664, Step: 200 -2022-12-01 11:48:08 - r - INFO: - Episode: 75/400, Reward: -125.647, Step: 200 -2022-12-01 11:48:09 - r - INFO: - Episode: 76/400, Reward: -785.472, Step: 200 -2022-12-01 11:48:10 - r - INFO: - Episode: 77/400, Reward: -239.213, Step: 200 -2022-12-01 11:48:10 - r - INFO: - Episode: 78/400, Reward: -237.476, Step: 200 -2022-12-01 11:48:11 - r - INFO: - Episode: 79/400, Reward: -240.762, Step: 200 -2022-12-01 11:48:12 - r - INFO: - Episode: 80/400, Reward: -497.246, Step: 200 -2022-12-01 11:48:13 - r - INFO: - Episode: 81/400, Reward: -389.137, Step: 200 -2022-12-01 11:48:14 - r - INFO: - Episode: 82/400, Reward: -0.271, Step: 200 -2022-12-01 11:48:15 - r - INFO: - Episode: 83/400, Reward: -0.309, Step: 200 -2022-12-01 11:48:16 - r - INFO: - Episode: 84/400, Reward: -243.787, Step: 200 -2022-12-01 11:48:17 - r - INFO: - Episode: 85/400, Reward: -0.285, Step: 200 -2022-12-01 11:48:18 - r - INFO: - Episode: 86/400, Reward: -129.952, Step: 200 -2022-12-01 11:48:19 - r - INFO: - Episode: 87/400, Reward: -128.368, Step: 200 -2022-12-01 11:48:19 - r - INFO: - Episode: 88/400, Reward: -0.698, Step: 200 -2022-12-01 11:48:20 - r - INFO: - Episode: 89/400, Reward: -120.313, Step: 200 -2022-12-01 11:48:21 - r - INFO: - Episode: 90/400, Reward: -127.307, Step: 200 -2022-12-01 11:48:22 - r - INFO: - Current episode 90 has the best eval reward: -359.406 -2022-12-01 11:48:22 - r - INFO: - Episode: 91/400, Reward: -126.289, Step: 200 -2022-12-01 11:48:23 - r - INFO: - Episode: 92/400, Reward: -129.531, Step: 200 -2022-12-01 11:48:24 - r - INFO: - Episode: 93/400, Reward: -1.561, Step: 200 -2022-12-01 11:48:25 - r - INFO: - Episode: 94/400, Reward: -130.035, Step: 200 -2022-12-01 11:48:26 - r - INFO: - Episode: 95/400, Reward: -241.012, Step: 200 -2022-12-01 11:48:26 - r - INFO: - Current episode 95 has the best eval reward: -306.512 -2022-12-01 11:48:27 - r - INFO: - Episode: 96/400, Reward: -118.295, Step: 200 -2022-12-01 11:48:28 - r - INFO: - Episode: 97/400, Reward: -245.900, Step: 200 -2022-12-01 11:48:29 - r - INFO: - Episode: 98/400, Reward: -1.181, Step: 200 -2022-12-01 11:48:29 - r - INFO: - Episode: 99/400, Reward: -126.194, Step: 200 -2022-12-01 11:48:30 - r - INFO: - Episode: 100/400, Reward: -127.803, Step: 200 -2022-12-01 11:48:31 - r - INFO: - Episode: 101/400, Reward: -117.819, Step: 200 -2022-12-01 11:48:32 - r - INFO: - Episode: 102/400, Reward: -119.513, Step: 200 -2022-12-01 11:48:33 - r - INFO: - Episode: 103/400, Reward: -221.549, Step: 200 -2022-12-01 11:48:34 - r - INFO: - Episode: 104/400, Reward: -244.916, Step: 200 -2022-12-01 11:48:35 - r - INFO: - Episode: 105/400, Reward: -126.866, Step: 200 -2022-12-01 11:48:36 - r - INFO: - Episode: 106/400, Reward: -358.937, Step: 200 -2022-12-01 11:48:37 - r - INFO: - Episode: 107/400, Reward: -125.261, Step: 200 -2022-12-01 11:48:38 - r - INFO: - Episode: 108/400, Reward: -127.865, Step: 200 -2022-12-01 11:48:39 - r - INFO: - Episode: 109/400, Reward: -357.778, Step: 200 -2022-12-01 11:48:40 - r - INFO: - Episode: 110/400, Reward: -124.891, Step: 200 -2022-12-01 11:48:40 - r - INFO: - Current episode 110 has the best eval reward: -303.949 -2022-12-01 11:48:41 - r - INFO: - Episode: 111/400, Reward: -383.057, Step: 200 -2022-12-01 11:48:42 - r - INFO: - Episode: 112/400, Reward: -3.618, Step: 200 -2022-12-01 11:48:43 - r - INFO: - Episode: 113/400, Reward: -248.158, Step: 200 -2022-12-01 11:48:44 - r - INFO: - Episode: 114/400, Reward: -349.098, Step: 200 -2022-12-01 11:48:44 - r - INFO: - Episode: 115/400, Reward: -126.353, Step: 200 -2022-12-01 11:48:45 - r - INFO: - Current episode 115 has the best eval reward: -201.906 -2022-12-01 11:48:46 - r - INFO: - Episode: 116/400, Reward: -237.635, Step: 200 -2022-12-01 11:48:47 - r - INFO: - Episode: 117/400, Reward: -118.228, Step: 200 -2022-12-01 11:48:48 - r - INFO: - Episode: 118/400, Reward: -119.511, Step: 200 -2022-12-01 11:48:48 - r - INFO: - Episode: 119/400, Reward: -120.025, Step: 200 -2022-12-01 11:48:49 - r - INFO: - Episode: 120/400, Reward: -377.781, Step: 200 -2022-12-01 11:48:51 - r - INFO: - Episode: 121/400, Reward: -129.686, Step: 200 -2022-12-01 11:48:51 - r - INFO: - Episode: 122/400, Reward: -248.889, Step: 200 -2022-12-01 11:48:52 - r - INFO: - Episode: 123/400, Reward: -128.352, Step: 200 -2022-12-01 11:48:53 - r - INFO: - Episode: 124/400, Reward: -242.038, Step: 200 -2022-12-01 11:48:54 - r - INFO: - Episode: 125/400, Reward: -116.703, Step: 200 -2022-12-01 11:48:55 - r - INFO: - Episode: 126/400, Reward: -364.826, Step: 200 -2022-12-01 11:48:56 - r - INFO: - Episode: 127/400, Reward: -1.162, Step: 200 -2022-12-01 11:48:57 - r - INFO: - Episode: 128/400, Reward: -126.903, Step: 200 -2022-12-01 11:48:58 - r - INFO: - Episode: 129/400, Reward: -249.294, Step: 200 -2022-12-01 11:48:59 - r - INFO: - Episode: 130/400, Reward: -1.437, Step: 200 -2022-12-01 11:49:00 - r - INFO: - Episode: 131/400, Reward: -1.518, Step: 200 -2022-12-01 11:49:01 - r - INFO: - Episode: 132/400, Reward: -1.269, Step: 200 -2022-12-01 11:49:02 - r - INFO: - Episode: 133/400, Reward: -242.660, Step: 200 -2022-12-01 11:49:03 - r - INFO: - Episode: 134/400, Reward: -122.925, Step: 200 -2022-12-01 11:49:03 - r - INFO: - Episode: 135/400, Reward: -121.282, Step: 200 -2022-12-01 11:49:05 - r - INFO: - Episode: 136/400, Reward: -122.574, Step: 200 -2022-12-01 11:49:06 - r - INFO: - Episode: 137/400, Reward: -121.215, Step: 200 -2022-12-01 11:49:06 - r - INFO: - Episode: 138/400, Reward: -250.123, Step: 200 -2022-12-01 11:49:07 - r - INFO: - Episode: 139/400, Reward: -327.829, Step: 200 -2022-12-01 11:49:08 - r - INFO: - Episode: 140/400, Reward: -125.407, Step: 200 -2022-12-01 11:49:10 - r - INFO: - Episode: 141/400, Reward: -116.500, Step: 200 -2022-12-01 11:49:10 - r - INFO: - Episode: 142/400, Reward: -336.258, Step: 200 -2022-12-01 11:49:11 - r - INFO: - Episode: 143/400, Reward: -230.379, Step: 200 -2022-12-01 11:49:12 - r - INFO: - Episode: 144/400, Reward: -127.153, Step: 200 -2022-12-01 11:49:13 - r - INFO: - Episode: 145/400, Reward: -244.796, Step: 200 -2022-12-01 11:49:14 - r - INFO: - Episode: 146/400, Reward: -325.592, Step: 200 -2022-12-01 11:49:15 - r - INFO: - Episode: 147/400, Reward: -1.020, Step: 200 -2022-12-01 11:49:16 - r - INFO: - Episode: 148/400, Reward: -123.722, Step: 200 -2022-12-01 11:49:17 - r - INFO: - Episode: 149/400, Reward: -123.822, Step: 200 -2022-12-01 11:49:18 - r - INFO: - Episode: 150/400, Reward: -128.729, Step: 200 -2022-12-01 11:49:19 - r - INFO: - Episode: 151/400, Reward: -119.312, Step: 200 -2022-12-01 11:49:20 - r - INFO: - Episode: 152/400, Reward: -269.220, Step: 200 -2022-12-01 11:49:21 - r - INFO: - Episode: 153/400, Reward: -364.687, Step: 200 -2022-12-01 11:49:22 - r - INFO: - Episode: 154/400, Reward: -224.135, Step: 200 -2022-12-01 11:49:22 - r - INFO: - Episode: 155/400, Reward: -125.227, Step: 200 -2022-12-01 11:49:23 - r - INFO: - Current episode 155 has the best eval reward: -194.534 -2022-12-01 11:49:24 - r - INFO: - Episode: 156/400, Reward: -127.929, Step: 200 -2022-12-01 11:49:25 - r - INFO: - Episode: 157/400, Reward: -129.891, Step: 200 -2022-12-01 11:49:25 - r - INFO: - Episode: 158/400, Reward: -126.725, Step: 200 -2022-12-01 11:49:26 - r - INFO: - Episode: 159/400, Reward: -119.785, Step: 200 -2022-12-01 11:49:27 - r - INFO: - Episode: 160/400, Reward: -346.210, Step: 200 -2022-12-01 11:49:28 - r - INFO: - Episode: 161/400, Reward: -368.187, Step: 200 -2022-12-01 11:49:29 - r - INFO: - Episode: 162/400, Reward: -246.304, Step: 200 -2022-12-01 11:49:30 - r - INFO: - Episode: 163/400, Reward: -1.275, Step: 200 -2022-12-01 11:49:31 - r - INFO: - Episode: 164/400, Reward: -117.674, Step: 200 -2022-12-01 11:49:32 - r - INFO: - Episode: 165/400, Reward: -336.285, Step: 200 -2022-12-01 11:49:33 - r - INFO: - Episode: 166/400, Reward: -1.146, Step: 200 -2022-12-01 11:49:34 - r - INFO: - Episode: 167/400, Reward: -1.339, Step: 200 -2022-12-01 11:49:35 - r - INFO: - Episode: 168/400, Reward: -118.357, Step: 200 -2022-12-01 11:49:36 - r - INFO: - Episode: 169/400, Reward: -242.254, Step: 200 -2022-12-01 11:49:37 - r - INFO: - Episode: 170/400, Reward: -123.858, Step: 200 -2022-12-01 11:49:38 - r - INFO: - Episode: 171/400, Reward: -117.109, Step: 200 -2022-12-01 11:49:39 - r - INFO: - Episode: 172/400, Reward: -123.739, Step: 200 -2022-12-01 11:49:40 - r - INFO: - Episode: 173/400, Reward: -115.141, Step: 200 -2022-12-01 11:49:41 - r - INFO: - Episode: 174/400, Reward: -119.847, Step: 200 -2022-12-01 11:49:42 - r - INFO: - Episode: 175/400, Reward: -120.644, Step: 200 -2022-12-01 11:49:43 - r - INFO: - Episode: 176/400, Reward: -116.678, Step: 200 -2022-12-01 11:49:44 - r - INFO: - Episode: 177/400, Reward: -117.131, Step: 200 -2022-12-01 11:49:45 - r - INFO: - Episode: 178/400, Reward: -122.806, Step: 200 -2022-12-01 11:49:46 - r - INFO: - Episode: 179/400, Reward: -127.810, Step: 200 -2022-12-01 11:49:47 - r - INFO: - Episode: 180/400, Reward: -239.768, Step: 200 -2022-12-01 11:49:48 - r - INFO: - Episode: 181/400, Reward: -221.090, Step: 200 -2022-12-01 11:49:49 - r - INFO: - Episode: 182/400, Reward: -121.223, Step: 200 -2022-12-01 11:49:50 - r - INFO: - Episode: 183/400, Reward: -227.651, Step: 200 -2022-12-01 11:49:51 - r - INFO: - Episode: 184/400, Reward: -322.285, Step: 200 -2022-12-01 11:49:52 - r - INFO: - Episode: 185/400, Reward: -123.356, Step: 200 -2022-12-01 11:49:52 - r - INFO: - Current episode 185 has the best eval reward: -169.112 -2022-12-01 11:49:53 - r - INFO: - Episode: 186/400, Reward: -119.883, Step: 200 -2022-12-01 11:49:54 - r - INFO: - Episode: 187/400, Reward: -121.378, Step: 200 -2022-12-01 11:49:55 - r - INFO: - Episode: 188/400, Reward: -0.875, Step: 200 -2022-12-01 11:49:56 - r - INFO: - Episode: 189/400, Reward: -358.294, Step: 200 -2022-12-01 11:49:57 - r - INFO: - Episode: 190/400, Reward: -119.036, Step: 200 -2022-12-01 11:49:58 - r - INFO: - Episode: 191/400, Reward: -1.170, Step: 200 -2022-12-01 11:49:59 - r - INFO: - Episode: 192/400, Reward: -113.781, Step: 200 -2022-12-01 11:50:00 - r - INFO: - Episode: 193/400, Reward: -119.419, Step: 200 -2022-12-01 11:50:01 - r - INFO: - Episode: 194/400, Reward: -121.292, Step: 200 -2022-12-01 11:50:02 - r - INFO: - Episode: 195/400, Reward: -330.155, Step: 200 -2022-12-01 11:50:03 - r - INFO: - Episode: 196/400, Reward: -119.069, Step: 200 -2022-12-01 11:50:04 - r - INFO: - Episode: 197/400, Reward: -123.463, Step: 200 -2022-12-01 11:50:05 - r - INFO: - Episode: 198/400, Reward: -126.123, Step: 200 -2022-12-01 11:50:06 - r - INFO: - Episode: 199/400, Reward: -0.956, Step: 200 -2022-12-01 11:50:07 - r - INFO: - Episode: 200/400, Reward: -115.547, Step: 200 -2022-12-01 11:50:09 - r - INFO: - Episode: 201/400, Reward: -345.353, Step: 200 -2022-12-01 11:50:09 - r - INFO: - Episode: 202/400, Reward: -122.789, Step: 200 -2022-12-01 11:50:10 - r - INFO: - Episode: 203/400, Reward: -129.462, Step: 200 -2022-12-01 11:50:11 - r - INFO: - Episode: 204/400, Reward: -126.246, Step: 200 -2022-12-01 11:50:12 - r - INFO: - Episode: 205/400, Reward: -128.631, Step: 200 -2022-12-01 11:50:14 - r - INFO: - Episode: 206/400, Reward: -354.559, Step: 200 -2022-12-01 11:50:15 - r - INFO: - Episode: 207/400, Reward: -1.449, Step: 200 -2022-12-01 11:50:16 - r - INFO: - Episode: 208/400, Reward: -121.555, Step: 200 -2022-12-01 11:50:17 - r - INFO: - Episode: 209/400, Reward: -118.753, Step: 200 -2022-12-01 11:50:18 - r - INFO: - Episode: 210/400, Reward: -361.083, Step: 200 -2022-12-01 11:50:19 - r - INFO: - Episode: 211/400, Reward: -227.722, Step: 200 -2022-12-01 11:50:20 - r - INFO: - Episode: 212/400, Reward: -256.454, Step: 200 -2022-12-01 11:50:21 - r - INFO: - Episode: 213/400, Reward: -123.373, Step: 200 -2022-12-01 11:50:22 - r - INFO: - Episode: 214/400, Reward: -114.304, Step: 200 -2022-12-01 11:50:23 - r - INFO: - Episode: 215/400, Reward: -1.312, Step: 200 -2022-12-01 11:50:24 - r - INFO: - Episode: 216/400, Reward: -239.796, Step: 200 -2022-12-01 11:50:25 - r - INFO: - Episode: 217/400, Reward: -126.548, Step: 200 -2022-12-01 11:50:26 - r - INFO: - Episode: 218/400, Reward: -126.639, Step: 200 -2022-12-01 11:50:27 - r - INFO: - Episode: 219/400, Reward: -125.775, Step: 200 -2022-12-01 11:50:28 - r - INFO: - Episode: 220/400, Reward: -1.940, Step: 200 -2022-12-01 11:50:29 - r - INFO: - Episode: 221/400, Reward: -124.998, Step: 200 -2022-12-01 11:50:30 - r - INFO: - Episode: 222/400, Reward: -353.236, Step: 200 -2022-12-01 11:50:31 - r - INFO: - Episode: 223/400, Reward: -357.056, Step: 200 -2022-12-01 11:50:31 - r - INFO: - Episode: 224/400, Reward: -114.204, Step: 200 -2022-12-01 11:50:32 - r - INFO: - Episode: 225/400, Reward: -125.223, Step: 200 -2022-12-01 11:50:34 - r - INFO: - Episode: 226/400, Reward: -227.426, Step: 200 -2022-12-01 11:50:35 - r - INFO: - Episode: 227/400, Reward: -3.664, Step: 200 -2022-12-01 11:50:35 - r - INFO: - Episode: 228/400, Reward: -123.205, Step: 200 -2022-12-01 11:50:36 - r - INFO: - Episode: 229/400, Reward: -124.514, Step: 200 -2022-12-01 11:50:37 - r - INFO: - Episode: 230/400, Reward: -118.301, Step: 200 -2022-12-01 11:50:38 - r - INFO: - Episode: 231/400, Reward: -243.096, Step: 200 -2022-12-01 11:50:39 - r - INFO: - Episode: 232/400, Reward: -126.697, Step: 200 -2022-12-01 11:50:40 - r - INFO: - Episode: 233/400, Reward: -1.867, Step: 200 -2022-12-01 11:50:41 - r - INFO: - Episode: 234/400, Reward: -119.831, Step: 200 -2022-12-01 11:50:42 - r - INFO: - Episode: 235/400, Reward: -117.760, Step: 200 -2022-12-01 11:50:43 - r - INFO: - Episode: 236/400, Reward: -123.939, Step: 200 -2022-12-01 11:50:44 - r - INFO: - Episode: 237/400, Reward: -1.717, Step: 200 -2022-12-01 11:50:45 - r - INFO: - Episode: 238/400, Reward: -128.808, Step: 200 -2022-12-01 11:50:46 - r - INFO: - Episode: 239/400, Reward: -131.194, Step: 200 -2022-12-01 11:50:46 - r - INFO: - Episode: 240/400, Reward: -352.905, Step: 200 -2022-12-01 11:50:48 - r - INFO: - Episode: 241/400, Reward: -233.712, Step: 200 -2022-12-01 11:50:49 - r - INFO: - Episode: 242/400, Reward: -262.387, Step: 200 -2022-12-01 11:50:49 - r - INFO: - Episode: 243/400, Reward: -3.707, Step: 200 -2022-12-01 11:50:50 - r - INFO: - Episode: 244/400, Reward: -126.616, Step: 200 -2022-12-01 11:50:51 - r - INFO: - Episode: 245/400, Reward: -230.692, Step: 200 -2022-12-01 11:50:52 - r - INFO: - Episode: 246/400, Reward: -1.252, Step: 200 -2022-12-01 11:50:53 - r - INFO: - Episode: 247/400, Reward: -118.523, Step: 200 -2022-12-01 11:50:53 - r - INFO: - Episode: 248/400, Reward: -125.407, Step: 200 -2022-12-01 11:50:54 - r - INFO: - Episode: 249/400, Reward: -117.500, Step: 200 -2022-12-01 11:50:55 - r - INFO: - Episode: 250/400, Reward: -393.070, Step: 200 -2022-12-01 11:50:56 - r - INFO: - Episode: 251/400, Reward: -118.367, Step: 200 -2022-12-01 11:50:57 - r - INFO: - Episode: 252/400, Reward: -128.272, Step: 200 -2022-12-01 11:50:57 - r - INFO: - Episode: 253/400, Reward: -245.614, Step: 200 -2022-12-01 11:50:58 - r - INFO: - Episode: 254/400, Reward: -122.880, Step: 200 -2022-12-01 11:50:59 - r - INFO: - Episode: 255/400, Reward: -239.682, Step: 200 -2022-12-01 11:51:00 - r - INFO: - Episode: 256/400, Reward: -124.537, Step: 200 -2022-12-01 11:51:01 - r - INFO: - Episode: 257/400, Reward: -1.111, Step: 200 -2022-12-01 11:51:01 - r - INFO: - Episode: 258/400, Reward: -117.201, Step: 200 -2022-12-01 11:51:02 - r - INFO: - Episode: 259/400, Reward: -128.891, Step: 200 -2022-12-01 11:51:03 - r - INFO: - Episode: 260/400, Reward: -126.265, Step: 200 -2022-12-01 11:51:04 - r - INFO: - Episode: 261/400, Reward: -231.952, Step: 200 -2022-12-01 11:51:05 - r - INFO: - Episode: 262/400, Reward: -119.314, Step: 200 -2022-12-01 11:51:06 - r - INFO: - Episode: 263/400, Reward: -125.479, Step: 200 -2022-12-01 11:51:07 - r - INFO: - Episode: 264/400, Reward: -3.259, Step: 200 -2022-12-01 11:51:07 - r - INFO: - Episode: 265/400, Reward: -127.222, Step: 200 -2022-12-01 11:51:09 - r - INFO: - Episode: 266/400, Reward: -117.150, Step: 200 -2022-12-01 11:51:10 - r - INFO: - Episode: 267/400, Reward: -126.775, Step: 200 -2022-12-01 11:51:10 - r - INFO: - Episode: 268/400, Reward: -286.837, Step: 200 -2022-12-01 11:51:11 - r - INFO: - Episode: 269/400, Reward: -119.631, Step: 200 -2022-12-01 11:51:12 - r - INFO: - Episode: 270/400, Reward: -117.221, Step: 200 -2022-12-01 11:51:13 - r - INFO: - Episode: 271/400, Reward: -127.008, Step: 200 -2022-12-01 11:51:14 - r - INFO: - Episode: 272/400, Reward: -125.160, Step: 200 -2022-12-01 11:51:15 - r - INFO: - Episode: 273/400, Reward: -119.650, Step: 200 -2022-12-01 11:51:16 - r - INFO: - Episode: 274/400, Reward: -126.034, Step: 200 -2022-12-01 11:51:17 - r - INFO: - Episode: 275/400, Reward: -117.445, Step: 200 -2022-12-01 11:51:17 - r - INFO: - Current episode 275 has the best eval reward: -168.495 -2022-12-01 11:51:18 - r - INFO: - Episode: 276/400, Reward: -353.132, Step: 200 -2022-12-01 11:51:19 - r - INFO: - Episode: 277/400, Reward: -123.565, Step: 200 -2022-12-01 11:51:20 - r - INFO: - Episode: 278/400, Reward: -226.007, Step: 200 -2022-12-01 11:51:21 - r - INFO: - Episode: 279/400, Reward: -0.719, Step: 200 -2022-12-01 11:51:21 - r - INFO: - Episode: 280/400, Reward: -119.678, Step: 200 -2022-12-01 11:51:23 - r - INFO: - Episode: 281/400, Reward: -124.168, Step: 200 -2022-12-01 11:51:24 - r - INFO: - Episode: 282/400, Reward: -126.560, Step: 200 -2022-12-01 11:51:25 - r - INFO: - Episode: 283/400, Reward: -300.111, Step: 200 -2022-12-01 11:51:25 - r - INFO: - Episode: 284/400, Reward: -360.951, Step: 200 -2022-12-01 11:51:26 - r - INFO: - Episode: 285/400, Reward: -125.889, Step: 200 -2022-12-01 11:51:28 - r - INFO: - Episode: 286/400, Reward: -247.302, Step: 200 -2022-12-01 11:51:28 - r - INFO: - Episode: 287/400, Reward: -131.289, Step: 200 -2022-12-01 11:51:29 - r - INFO: - Episode: 288/400, Reward: -240.206, Step: 200 -2022-12-01 11:51:30 - r - INFO: - Episode: 289/400, Reward: -287.705, Step: 200 -2022-12-01 11:51:31 - r - INFO: - Episode: 290/400, Reward: -227.766, Step: 200 -2022-12-01 11:51:32 - r - INFO: - Episode: 291/400, Reward: -123.641, Step: 200 -2022-12-01 11:51:33 - r - INFO: - Episode: 292/400, Reward: -1.027, Step: 200 -2022-12-01 11:51:34 - r - INFO: - Episode: 293/400, Reward: -251.142, Step: 200 -2022-12-01 11:51:35 - r - INFO: - Episode: 294/400, Reward: -124.858, Step: 200 -2022-12-01 11:51:36 - r - INFO: - Episode: 295/400, Reward: -120.365, Step: 200 -2022-12-01 11:51:37 - r - INFO: - Episode: 296/400, Reward: -116.219, Step: 200 -2022-12-01 11:51:38 - r - INFO: - Episode: 297/400, Reward: -126.511, Step: 200 -2022-12-01 11:51:39 - r - INFO: - Episode: 298/400, Reward: -245.523, Step: 200 -2022-12-01 11:51:39 - r - INFO: - Episode: 299/400, Reward: -234.450, Step: 200 -2022-12-01 11:51:40 - r - INFO: - Episode: 300/400, Reward: -119.541, Step: 200 -2022-12-01 11:51:41 - r - INFO: - Episode: 301/400, Reward: -378.112, Step: 200 -2022-12-01 11:51:42 - r - INFO: - Episode: 302/400, Reward: -235.862, Step: 200 -2022-12-01 11:51:43 - r - INFO: - Episode: 303/400, Reward: -231.766, Step: 200 -2022-12-01 11:51:44 - r - INFO: - Episode: 304/400, Reward: -114.889, Step: 200 -2022-12-01 11:51:45 - r - INFO: - Episode: 305/400, Reward: -124.536, Step: 200 -2022-12-01 11:51:46 - r - INFO: - Episode: 306/400, Reward: -127.555, Step: 200 -2022-12-01 11:51:47 - r - INFO: - Episode: 307/400, Reward: -242.659, Step: 200 -2022-12-01 11:51:48 - r - INFO: - Episode: 308/400, Reward: -121.678, Step: 200 -2022-12-01 11:51:48 - r - INFO: - Episode: 309/400, Reward: -233.681, Step: 200 -2022-12-01 11:51:49 - r - INFO: - Episode: 310/400, Reward: -125.020, Step: 200 -2022-12-01 11:51:51 - r - INFO: - Episode: 311/400, Reward: -121.913, Step: 200 -2022-12-01 11:51:51 - r - INFO: - Episode: 312/400, Reward: -123.341, Step: 200 -2022-12-01 11:51:52 - r - INFO: - Episode: 313/400, Reward: -251.091, Step: 200 -2022-12-01 11:51:53 - r - INFO: - Episode: 314/400, Reward: -119.395, Step: 200 -2022-12-01 11:51:54 - r - INFO: - Episode: 315/400, Reward: -233.410, Step: 200 -2022-12-01 11:51:55 - r - INFO: - Episode: 316/400, Reward: -124.669, Step: 200 -2022-12-01 11:51:56 - r - INFO: - Episode: 317/400, Reward: -240.765, Step: 200 -2022-12-01 11:51:57 - r - INFO: - Episode: 318/400, Reward: -116.002, Step: 200 -2022-12-01 11:51:58 - r - INFO: - Episode: 319/400, Reward: -233.707, Step: 200 -2022-12-01 11:51:59 - r - INFO: - Episode: 320/400, Reward: -126.942, Step: 200 -2022-12-01 11:52:00 - r - INFO: - Episode: 321/400, Reward: -120.706, Step: 200 -2022-12-01 11:52:01 - r - INFO: - Episode: 322/400, Reward: -118.342, Step: 200 -2022-12-01 11:52:02 - r - INFO: - Episode: 323/400, Reward: -230.450, Step: 200 -2022-12-01 11:52:03 - r - INFO: - Episode: 324/400, Reward: -0.747, Step: 200 -2022-12-01 11:52:04 - r - INFO: - Episode: 325/400, Reward: -123.279, Step: 200 -2022-12-01 11:52:04 - r - INFO: - Current episode 325 has the best eval reward: -159.430 -2022-12-01 11:52:05 - r - INFO: - Episode: 326/400, Reward: -227.798, Step: 200 -2022-12-01 11:52:06 - r - INFO: - Episode: 327/400, Reward: -244.460, Step: 200 -2022-12-01 11:52:07 - r - INFO: - Episode: 328/400, Reward: -118.017, Step: 200 -2022-12-01 11:52:08 - r - INFO: - Episode: 329/400, Reward: -0.858, Step: 200 -2022-12-01 11:52:08 - r - INFO: - Episode: 330/400, Reward: -342.191, Step: 200 -2022-12-01 11:52:10 - r - INFO: - Episode: 331/400, Reward: -113.292, Step: 200 -2022-12-01 11:52:11 - r - INFO: - Episode: 332/400, Reward: -125.138, Step: 200 -2022-12-01 11:52:12 - r - INFO: - Episode: 333/400, Reward: -236.427, Step: 200 -2022-12-01 11:52:12 - r - INFO: - Episode: 334/400, Reward: -353.551, Step: 200 -2022-12-01 11:52:13 - r - INFO: - Episode: 335/400, Reward: -126.451, Step: 200 -2022-12-01 11:52:15 - r - INFO: - Episode: 336/400, Reward: -123.233, Step: 200 -2022-12-01 11:52:15 - r - INFO: - Episode: 337/400, Reward: -242.726, Step: 200 -2022-12-01 11:52:16 - r - INFO: - Episode: 338/400, Reward: -118.301, Step: 200 -2022-12-01 11:52:17 - r - INFO: - Episode: 339/400, Reward: -238.164, Step: 200 -2022-12-01 11:52:18 - r - INFO: - Episode: 340/400, Reward: -393.018, Step: 200 -2022-12-01 11:52:19 - r - INFO: - Episode: 341/400, Reward: -4.361, Step: 200 -2022-12-01 11:52:20 - r - INFO: - Episode: 342/400, Reward: -118.507, Step: 200 -2022-12-01 11:52:21 - r - INFO: - Episode: 343/400, Reward: -122.249, Step: 200 -2022-12-01 11:52:22 - r - INFO: - Episode: 344/400, Reward: -253.743, Step: 200 -2022-12-01 11:52:23 - r - INFO: - Episode: 345/400, Reward: -339.840, Step: 200 -2022-12-01 11:52:24 - r - INFO: - Episode: 346/400, Reward: -124.519, Step: 200 -2022-12-01 11:52:25 - r - INFO: - Episode: 347/400, Reward: -125.941, Step: 200 -2022-12-01 11:52:26 - r - INFO: - Episode: 348/400, Reward: -119.085, Step: 200 -2022-12-01 11:52:27 - r - INFO: - Episode: 349/400, Reward: -123.989, Step: 200 -2022-12-01 11:52:28 - r - INFO: - Episode: 350/400, Reward: -242.460, Step: 200 -2022-12-01 11:52:29 - r - INFO: - Episode: 351/400, Reward: -236.760, Step: 200 -2022-12-01 11:52:30 - r - INFO: - Episode: 352/400, Reward: -1.233, Step: 200 -2022-12-01 11:52:30 - r - INFO: - Episode: 353/400, Reward: -118.372, Step: 200 -2022-12-01 11:52:31 - r - INFO: - Episode: 354/400, Reward: -355.525, Step: 200 -2022-12-01 11:52:32 - r - INFO: - Episode: 355/400, Reward: -357.921, Step: 200 -2022-12-01 11:52:34 - r - INFO: - Episode: 356/400, Reward: -238.332, Step: 200 -2022-12-01 11:52:34 - r - INFO: - Episode: 357/400, Reward: -130.658, Step: 200 -2022-12-01 11:52:35 - r - INFO: - Episode: 358/400, Reward: -126.854, Step: 200 -2022-12-01 11:52:36 - r - INFO: - Episode: 359/400, Reward: -116.509, Step: 200 -2022-12-01 11:52:37 - r - INFO: - Episode: 360/400, Reward: -123.745, Step: 200 -2022-12-01 11:52:38 - r - INFO: - Episode: 361/400, Reward: -368.148, Step: 200 -2022-12-01 11:52:39 - r - INFO: - Episode: 362/400, Reward: -126.382, Step: 200 -2022-12-01 11:52:40 - r - INFO: - Episode: 363/400, Reward: -236.524, Step: 200 -2022-12-01 11:52:41 - r - INFO: - Episode: 364/400, Reward: -240.952, Step: 200 -2022-12-01 11:52:42 - r - INFO: - Episode: 365/400, Reward: -117.773, Step: 200 -2022-12-01 11:52:43 - r - INFO: - Episode: 366/400, Reward: -247.744, Step: 200 -2022-12-01 11:52:44 - r - INFO: - Episode: 367/400, Reward: -124.078, Step: 200 -2022-12-01 11:52:45 - r - INFO: - Episode: 368/400, Reward: -126.035, Step: 200 -2022-12-01 11:52:46 - r - INFO: - Episode: 369/400, Reward: -244.663, Step: 200 -2022-12-01 11:52:47 - r - INFO: - Episode: 370/400, Reward: -250.769, Step: 200 -2022-12-01 11:52:48 - r - INFO: - Episode: 371/400, Reward: -2.284, Step: 200 -2022-12-01 11:52:49 - r - INFO: - Episode: 372/400, Reward: -124.358, Step: 200 -2022-12-01 11:52:50 - r - INFO: - Episode: 373/400, Reward: -124.564, Step: 200 -2022-12-01 11:52:51 - r - INFO: - Episode: 374/400, Reward: -352.073, Step: 200 -2022-12-01 11:52:51 - r - INFO: - Episode: 375/400, Reward: -1.262, Step: 200 -2022-12-01 11:52:53 - r - INFO: - Episode: 376/400, Reward: -241.049, Step: 200 -2022-12-01 11:52:54 - r - INFO: - Episode: 377/400, Reward: -125.765, Step: 200 -2022-12-01 11:52:54 - r - INFO: - Episode: 378/400, Reward: -118.270, Step: 200 -2022-12-01 11:52:55 - r - INFO: - Episode: 379/400, Reward: -1.971, Step: 200 -2022-12-01 11:52:56 - r - INFO: - Episode: 380/400, Reward: -234.409, Step: 200 -2022-12-01 11:52:57 - r - INFO: - Episode: 381/400, Reward: -347.749, Step: 200 -2022-12-01 11:52:58 - r - INFO: - Episode: 382/400, Reward: -116.178, Step: 200 -2022-12-01 11:52:59 - r - INFO: - Episode: 383/400, Reward: -231.128, Step: 200 -2022-12-01 11:53:00 - r - INFO: - Episode: 384/400, Reward: -254.934, Step: 200 -2022-12-01 11:53:01 - r - INFO: - Episode: 385/400, Reward: -236.741, Step: 200 -2022-12-01 11:53:02 - r - INFO: - Episode: 386/400, Reward: -121.548, Step: 200 -2022-12-01 11:53:03 - r - INFO: - Episode: 387/400, Reward: -235.556, Step: 200 -2022-12-01 11:53:04 - r - INFO: - Episode: 388/400, Reward: -364.689, Step: 200 -2022-12-01 11:53:05 - r - INFO: - Episode: 389/400, Reward: -234.825, Step: 200 -2022-12-01 11:53:06 - r - INFO: - Episode: 390/400, Reward: -122.418, Step: 200 -2022-12-01 11:53:07 - r - INFO: - Episode: 391/400, Reward: -114.974, Step: 200 -2022-12-01 11:53:08 - r - INFO: - Episode: 392/400, Reward: -126.728, Step: 200 -2022-12-01 11:53:09 - r - INFO: - Episode: 393/400, Reward: -0.804, Step: 200 -2022-12-01 11:53:09 - r - INFO: - Episode: 394/400, Reward: -122.792, Step: 200 -2022-12-01 11:53:10 - r - INFO: - Episode: 395/400, Reward: -122.466, Step: 200 -2022-12-01 11:53:12 - r - INFO: - Episode: 396/400, Reward: -368.470, Step: 200 -2022-12-01 11:53:12 - r - INFO: - Episode: 397/400, Reward: -122.965, Step: 200 -2022-12-01 11:53:13 - r - INFO: - Episode: 398/400, Reward: -228.855, Step: 200 -2022-12-01 11:53:14 - r - INFO: - Episode: 399/400, Reward: -233.288, Step: 200 -2022-12-01 11:53:15 - r - INFO: - Episode: 400/400, Reward: -124.666, Step: 200 -2022-12-01 11:53:15 - r - INFO: - Finish training! diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/models/actor_checkpoint.pt b/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/models/actor_checkpoint.pt deleted file mode 100644 index da3a5d2ee860077b7903a5a01180b99cd52bba1c..0000000000000000000000000000000000000000 --- a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/models/actor_checkpoint.pt +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8e597766d4cbb7f45b4829f08fb296e02f880c06a5f1c7e8914ae3edfffd5b27 -size 270231 diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/results/learning_curve.png b/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/results/learning_curve.png deleted file mode 100644 index 639711d84263c662ab96c5cf47c8407ddf991c9f..0000000000000000000000000000000000000000 Binary files a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/results/learning_curve.png and /dev/null differ diff --git a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/results/res.csv b/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/results/res.csv deleted file mode 100644 index 850114376768eb0712bfd7e776daa0b4617abd7f..0000000000000000000000000000000000000000 --- a/Pendulum-v1/Train_Pendulum-v1_DDPG_20221201-114704/results/res.csv +++ /dev/null @@ -1,401 +0,0 @@ -episodes,rewards,steps -0,-1212.567790509667,200 -1,-1623.90050898633,200 -2,-1487.2540570510778,200 -3,-1453.6050208134404,200 -4,-1673.4762545138892,200 -5,-1414.2243811733215,200 -6,-1510.7052200180894,200 -7,-1501.575665761993,200 -8,-1512.5944531574316,200 -9,-1524.7744177918894,200 -10,-1354.692085392766,200 -11,-1554.3746703287636,200 -12,-1569.2612397054797,200 -13,-1497.9386660259095,200 -14,-1569.1011909824151,200 -15,-1253.0033379748509,200 -16,-1545.8060145381855,200 -17,-1265.2311705490215,200 -18,-305.82276280873407,200 -19,-1357.2647833743379,200 -20,-1296.9116241813176,200 -21,-1314.4621209531194,200 -22,-1249.9004458012248,200 -23,-1339.9108332691255,200 -24,-1366.5184464046633,200 -25,-1260.4917067598642,200 -26,-1194.3352827285053,200 -27,-1153.4043499440857,200 -28,-1082.3681931274152,200 -29,-1171.4685875728028,200 -30,-1200.7706507466314,200 -31,-1032.5769585027751,200 -32,-1118.503759148228,200 -33,-812.889261032345,200 -34,-1346.485781190277,200 -35,-1150.2140348230303,200 -36,-1270.614689092599,200 -37,-1016.8168272147682,200 -38,-663.5954619737352,200 -39,-138.01214689008125,200 -40,-934.2527412964954,200 -41,-260.4236560115692,200 -42,-326.42485912322536,200 -43,-133.96159257769474,200 -44,-264.0377370283736,200 -45,-1091.7560930763104,200 -46,-0.4068611028228804,200 -47,-131.84009403179755,200 -48,-129.61386019610077,200 -49,-128.35718529417167,200 -50,-407.41856177348257,200 -51,-402.5949012730138,200 -52,-0.7871212444572683,200 -53,-442.5590939848539,200 -54,-244.39037528009618,200 -55,-281.0373284085536,200 -56,-131.17759345587862,200 -57,-1.1744234280309984,200 -58,-260.8982646552037,200 -59,-389.7637508199495,200 -60,-263.9201033034666,200 -61,-1.242859023783189,200 -62,-1256.8407202519154,200 -63,-132.49857524719138,200 -64,-397.0109133415189,200 -65,-124.64071860239733,200 -66,-263.83847787328176,200 -67,-384.3725051863925,200 -68,-123.29930919574642,200 -69,-1502.8471749197145,200 -70,-354.07000984950906,200 -71,-1039.9138673842492,200 -72,-242.39933426350547,200 -73,-122.6644138115817,200 -74,-125.64699662000082,200 -75,-785.4715017999798,200 -76,-239.2134448316515,200 -77,-237.47579487864564,200 -78,-240.7615577353036,200 -79,-497.2460269290864,200 -80,-389.137335314073,200 -81,-0.27112735186688924,200 -82,-0.3086774869748233,200 -83,-243.78677419611907,200 -84,-0.2849053573155253,200 -85,-129.95249846428172,200 -86,-128.36770876164985,200 -87,-0.6982052614212529,200 -88,-120.31324877134472,200 -89,-127.30701950283134,200 -90,-126.28860194823548,200 -91,-129.5309528856722,200 -92,-1.5610275380910392,200 -93,-130.0354013298848,200 -94,-241.0117247029227,200 -95,-118.29451152645855,200 -96,-245.90024271631833,200 -97,-1.1813720795550908,200 -98,-126.19409898092339,200 -99,-127.8032220593728,200 -100,-117.81936279930302,200 -101,-119.51315376165093,200 -102,-221.54855948109116,200 -103,-244.9161107009129,200 -104,-126.86578869001644,200 -105,-358.9366505581329,200 -106,-125.26087242054723,200 -107,-127.86492374431437,200 -108,-357.7782206605127,200 -109,-124.89145418273924,200 -110,-383.05708561048414,200 -111,-3.6178136145142172,200 -112,-248.15786033784366,200 -113,-349.09786434723947,200 -114,-126.35251122697167,200 -115,-237.63522300410204,200 -116,-118.22756919715725,200 -117,-119.5107377539306,200 -118,-120.02511282093975,200 -119,-377.78066789153604,200 -120,-129.68571250046196,200 -121,-248.8885368760876,200 -122,-128.35179793591774,200 -123,-242.03786282740847,200 -124,-116.70300814145506,200 -125,-364.82645829556594,200 -126,-1.1622811754968918,200 -127,-126.90344264006548,200 -128,-249.2942262287832,200 -129,-1.4371265779706741,200 -130,-1.5182421074658987,200 -131,-1.2689996792696698,200 -132,-242.66029747420913,200 -133,-122.9252356038692,200 -134,-121.28216804628428,200 -135,-122.57424341607928,200 -136,-121.21456479996444,200 -137,-250.12296949439366,200 -138,-327.82923872836636,200 -139,-125.40699584708844,200 -140,-116.5002658634688,200 -141,-336.25842699755134,200 -142,-230.37864406642584,200 -143,-127.15311834771302,200 -144,-244.79627483953058,200 -145,-325.5923495673209,200 -146,-1.0204374551306619,200 -147,-123.72243711538715,200 -148,-123.82166233262521,200 -149,-128.7294156369154,200 -150,-119.31209044975706,200 -151,-269.22027954032365,200 -152,-364.6870939981257,200 -153,-224.13468420403024,200 -154,-125.22730098623303,200 -155,-127.92895036690234,200 -156,-129.89097457605777,200 -157,-126.72531700681934,200 -158,-119.7850032893606,200 -159,-346.2098208053867,200 -160,-368.1867319651628,200 -161,-246.30367497072865,200 -162,-1.275297347971024,200 -163,-117.67350478628695,200 -164,-336.28518788986725,200 -165,-1.1462767825080664,200 -166,-1.3387542122282372,200 -167,-118.35652425364356,200 -168,-242.2539368184398,200 -169,-123.85838031428564,200 -170,-117.10879553128855,200 -171,-123.73929437000524,200 -172,-115.14099346906151,200 -173,-119.84652598178756,200 -174,-120.6439962098665,200 -175,-116.67769122806183,200 -176,-117.13116926949454,200 -177,-122.80600166027432,200 -178,-127.8101911457023,200 -179,-239.76783023149943,200 -180,-221.0901580192667,200 -181,-121.22306496994257,200 -182,-227.6510141301169,200 -183,-322.2846238986938,200 -184,-123.35597643103705,200 -185,-119.88288970007227,200 -186,-121.37823501360883,200 -187,-0.8747798993382542,200 -188,-358.29401380245605,200 -189,-119.03620186476329,200 -190,-1.170334861365693,200 -191,-113.78093682410294,200 -192,-119.41905481185384,200 -193,-121.29170944293014,200 -194,-330.15508271137554,200 -195,-119.06855822794175,200 -196,-123.46342605614734,200 -197,-126.12295482657818,200 -198,-0.955593205782399,200 -199,-115.54698221933135,200 -200,-345.35321174334746,200 -201,-122.7889263059338,200 -202,-129.46245591059238,200 -203,-126.24627838077089,200 -204,-128.6314658171212,200 -205,-354.558816181193,200 -206,-1.4488718026188616,200 -207,-121.55541576988286,200 -208,-118.75282946826736,200 -209,-361.0832345263783,200 -210,-227.72158476257837,200 -211,-256.45444130035406,200 -212,-123.37300964883983,200 -213,-114.30419425385213,200 -214,-1.3116631626515545,200 -215,-239.79627193349634,200 -216,-126.54756458516205,200 -217,-126.63939754488048,200 -218,-125.77463478109455,200 -219,-1.9399912963507502,200 -220,-124.99821624523541,200 -221,-353.2355290431278,200 -222,-357.0561822988093,200 -223,-114.20404230922577,200 -224,-125.2228216148647,200 -225,-227.42607572499656,200 -226,-3.66384583645844,200 -227,-123.20482956417794,200 -228,-124.5137660280843,200 -229,-118.301096765625,200 -230,-243.09590482871403,200 -231,-126.69723215895019,200 -232,-1.8669578864483127,200 -233,-119.8310527422825,200 -234,-117.76012570850753,200 -235,-123.93871282364343,200 -236,-1.7168797790561883,200 -237,-128.80820035416008,200 -238,-131.19391957459277,200 -239,-352.9046065501171,200 -240,-233.71249387417777,200 -241,-262.38672404161645,200 -242,-3.7069104404948297,200 -243,-126.6161194862307,200 -244,-230.69221157544033,200 -245,-1.2520344535505652,200 -246,-118.52263815670227,200 -247,-125.4068792476078,200 -248,-117.50017500673853,200 -249,-393.0699409612341,200 -250,-118.36656247252151,200 -251,-128.272032138697,200 -252,-245.6135875368202,200 -253,-122.88025794109298,200 -254,-239.6816900060018,200 -255,-124.53719203788097,200 -256,-1.1110322441728246,200 -257,-117.20115177155951,200 -258,-128.8907428246222,200 -259,-126.26518534927192,200 -260,-231.9515597068849,200 -261,-119.31353102451676,200 -262,-125.47907416411866,200 -263,-3.2585418147910055,200 -264,-127.22228346638764,200 -265,-117.15003991870962,200 -266,-126.77484246849679,200 -267,-286.8372750075032,200 -268,-119.63108646198032,200 -269,-117.220849256608,200 -270,-127.00824262198856,200 -271,-125.15956992929272,200 -272,-119.6498891175291,200 -273,-126.03370110237906,200 -274,-117.44506818609379,200 -275,-353.1321992630821,200 -276,-123.565078688204,200 -277,-226.00677123406874,200 -278,-0.7194826217112447,200 -279,-119.67832887804394,200 -280,-124.16811583775699,200 -281,-126.55993876412806,200 -282,-300.110749858184,200 -283,-360.95109190345244,200 -284,-125.88939413633598,200 -285,-247.30239878930985,200 -286,-131.289320755518,200 -287,-240.20601948049932,200 -288,-287.7052948722776,200 -289,-227.7658190183464,200 -290,-123.64110999426921,200 -291,-1.0271528840463287,200 -292,-251.14233972806213,200 -293,-124.85806098908452,200 -294,-120.36459740707978,200 -295,-116.21907154645311,200 -296,-126.51066109761726,200 -297,-245.52260164448222,200 -298,-234.4504681050107,200 -299,-119.54139726250581,200 -300,-378.11171464427173,200 -301,-235.86244730196216,200 -302,-231.76624873360237,200 -303,-114.88863260226945,200 -304,-124.5356898260653,200 -305,-127.55482707894846,200 -306,-242.65874525848005,200 -307,-121.6784359890847,200 -308,-233.6810974953129,200 -309,-125.02006124532345,200 -310,-121.91305443133672,200 -311,-123.34111389595492,200 -312,-251.0910698407238,200 -313,-119.39482989042334,200 -314,-233.40984081275317,200 -315,-124.66862728081996,200 -316,-240.7649857554929,200 -317,-116.00214081668108,200 -318,-233.7073249326516,200 -319,-126.94237135466841,200 -320,-120.70553886869959,200 -321,-118.34220148948498,200 -322,-230.44955958950447,200 -323,-0.7470952202906396,200 -324,-123.27938468334166,200 -325,-227.79804661024497,200 -326,-244.46032058496195,200 -327,-118.01693537671495,200 -328,-0.8577964297833797,200 -329,-342.1907112204193,200 -330,-113.29167706692641,200 -331,-125.13843346097002,200 -332,-236.42717212029493,200 -333,-353.5506948429681,200 -334,-126.4512296912333,200 -335,-123.23258988570352,200 -336,-242.72594865912376,200 -337,-118.30122180805739,200 -338,-238.16429341163462,200 -339,-393.01794480450354,200 -340,-4.361374395916245,200 -341,-118.50650965284454,200 -342,-122.2488070906401,200 -343,-253.74250826722954,200 -344,-339.8398544082274,200 -345,-124.51878691095172,200 -346,-125.94094059928794,200 -347,-119.08482859899843,200 -348,-123.98865217909652,200 -349,-242.46016054535525,200 -350,-236.76009860870204,200 -351,-1.2333958948568258,200 -352,-118.37166997000097,200 -353,-355.52450936234607,200 -354,-357.92143547778466,200 -355,-238.33173281615038,200 -356,-130.65792019641003,200 -357,-126.8544313444508,200 -358,-116.50940457252848,200 -359,-123.74509048396844,200 -360,-368.14830160700626,200 -361,-126.38208229049773,200 -362,-236.523521747964,200 -363,-240.95223515670057,200 -364,-117.77302567733554,200 -365,-247.7438030784602,200 -366,-124.07828253073873,200 -367,-126.03525592405485,200 -368,-244.66335723451874,200 -369,-250.76922693289163,200 -370,-2.2836473101239783,200 -371,-124.35833030447026,200 -372,-124.56362051691382,200 -373,-352.07315122967464,200 -374,-1.261706373658124,200 -375,-241.04932240175708,200 -376,-125.76478713066989,200 -377,-118.26990865551241,200 -378,-1.971486854330923,200 -379,-234.40885710658657,200 -380,-347.7489301944504,200 -381,-116.17842157604629,200 -382,-231.12814154316845,200 -383,-254.93448140941447,200 -384,-236.74147909076814,200 -385,-121.5477601851976,200 -386,-235.55563255180687,200 -387,-364.6886726900155,200 -388,-234.8246762310216,200 -389,-122.41849376434521,200 -390,-114.97416181206125,200 -391,-126.7282667590554,200 -392,-0.8040550197181987,200 -393,-122.79156418968286,200 -394,-122.46642961981983,200 -395,-368.4695035569944,200 -396,-122.96452798166366,200 -397,-228.85482334086666,200 -398,-233.28839642937024,200 -399,-124.66577454411869,200