diff --git a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/logs/log.txt b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/logs/log.txt deleted file mode 100644 index 25e2a2849ab6f7ccb66bb0cea27e40f4a148128e..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/logs/log.txt +++ /dev/null @@ -1,57 +0,0 @@ -2023-05-18 13:38:24 - SimpleLog - INFO: - General Configs: -2023-05-18 13:38:24 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:38:24 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:38:24 - SimpleLog - INFO: - env_name gym -2023-05-18 13:38:24 - SimpleLog - INFO: - algo_name NoisyDQN -2023-05-18 13:38:24 - SimpleLog - INFO: - mode test -2023-05-18 13:38:24 - SimpleLog - INFO: - device cpu -2023-05-18 13:38:24 - SimpleLog - INFO: - seed 1 -2023-05-18 13:38:24 - SimpleLog - INFO: - max_episode 10 -2023-05-18 13:38:24 - SimpleLog - INFO: - max_step 200 -2023-05-18 13:38:24 - SimpleLog - INFO: - collect_traj 0 -2023-05-18 13:38:24 - SimpleLog - INFO: - mp_backend single -2023-05-18 13:38:24 - SimpleLog - INFO: - n_workers 2 -2023-05-18 13:38:24 - SimpleLog - INFO: - n_learners 1 -2023-05-18 13:38:24 - SimpleLog - INFO: - share_buffer 1 -2023-05-18 13:38:24 - SimpleLog - INFO: - online_eval 1 -2023-05-18 13:38:24 - SimpleLog - INFO: - online_eval_episode 10 -2023-05-18 13:38:24 - SimpleLog - INFO: - model_save_fre 500 -2023-05-18 13:38:24 - SimpleLog - INFO: - load_checkpoint 1 -2023-05-18 13:38:24 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_NoisyDQN_20230518-133737 -2023-05-18 13:38:24 - SimpleLog - INFO: - load_model_step best -2023-05-18 13:38:24 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:38:24 - SimpleLog - INFO: - Algo Configs: -2023-05-18 13:38:24 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:38:24 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:38:24 - SimpleLog - INFO: - epsilon_start 0.95 -2023-05-18 13:38:24 - SimpleLog - INFO: - epsilon_end 0.01 -2023-05-18 13:38:24 - SimpleLog - INFO: - epsilon_decay 500 -2023-05-18 13:38:24 - SimpleLog - INFO: - gamma 0.99 -2023-05-18 13:38:24 - SimpleLog - INFO: - lr 0.0001 -2023-05-18 13:38:24 - SimpleLog - INFO: - buffer_size 100000 -2023-05-18 13:38:24 - SimpleLog - INFO: - batch_size 64 -2023-05-18 13:38:24 - SimpleLog - INFO: - target_update 4 -2023-05-18 13:38:24 - SimpleLog - INFO: - value_layers [{'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}, {'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}] -2023-05-18 13:38:24 - SimpleLog - INFO: - buffer_type REPLAY_QUE -2023-05-18 13:38:24 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:38:24 - SimpleLog - INFO: - Env Configs: -2023-05-18 13:38:24 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:38:24 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:38:24 - SimpleLog - INFO: - id CartPole-v1 -2023-05-18 13:38:24 - SimpleLog - INFO: - render_mode None -2023-05-18 13:38:24 - SimpleLog - INFO: - wrapper None -2023-05-18 13:38:24 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] -2023-05-18 13:38:24 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:38:24 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2) -2023-05-18 13:38:24 - SimpleLog - INFO: - Start testing! -2023-05-18 13:38:24 - SimpleLog - INFO: - episode: 0, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:24 - SimpleLog - INFO: - episode: 1, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:24 - SimpleLog - INFO: - episode: 2, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:24 - SimpleLog - INFO: - episode: 3, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:24 - SimpleLog - INFO: - episode: 4, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:25 - SimpleLog - INFO: - episode: 5, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:25 - SimpleLog - INFO: - episode: 6, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:25 - SimpleLog - INFO: - episode: 7, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:25 - SimpleLog - INFO: - episode: 8, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:25 - SimpleLog - INFO: - episode: 9, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:38:25 - SimpleLog - INFO: - Finish testing! total time consumed: 0.26s diff --git a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/tb_logs/interact/events.out.tfevents.1684388304.JMac.local.86491.0 b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/tb_logs/interact/events.out.tfevents.1684388304.JMac.local.86491.0 deleted file mode 100644 index f86a02769b3b3d06635d5a78555496f79857f0d6..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/tb_logs/interact/events.out.tfevents.1684388304.JMac.local.86491.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a888c1468be41447e5aec55b8e1cac6bb28792c9a6d11eb37f43f8db1a1ec315 -size 1056 diff --git a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/tb_logs/model/events.out.tfevents.1684388304.JMac.local.86491.1 b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/tb_logs/model/events.out.tfevents.1684388304.JMac.local.86491.1 deleted file mode 100644 index c48f7fbcf9258a8ac94085c3de6ebdabfd11050a..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/tb_logs/model/events.out.tfevents.1684388304.JMac.local.86491.1 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e5ef74ab61b4fd87898bdb34cad1df3bbf05d7edf30ae81504f7d09bb4f75ffd -size 40 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/config.yaml b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/config.yaml similarity index 87% rename from ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/config.yaml rename to ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/config.yaml index c69bd9442fff201ebe58683768db17f54ccf0eae..b7bb0418329cd03c1c223ed45936e2ed54de32f1 100644 --- a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/config.yaml +++ b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/config.yaml @@ -3,12 +3,12 @@ general_cfg: collect_traj: false device: cpu env_name: gym - load_checkpoint: false + load_checkpoint: true load_model_step: best - load_path: Train_CartPole-v1_DQN_20221026-054757 - max_episode: 100 + load_path: Train_ray_CartPole-v1_NoisyDQN_20230518-172642 + max_episode: 10 max_step: 200 - mode: train + mode: test model_save_fre: 500 mp_backend: single n_learners: 1 diff --git a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/logs/log.txt b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..7afe3aeb1b79a6fee0fecf7427072990f863a093 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/logs/log.txt @@ -0,0 +1,57 @@ +2023-05-18 17:34:26 - SimpleLog - INFO: - General Configs: +2023-05-18 17:34:26 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:34:26 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:34:26 - SimpleLog - INFO: - env_name gym +2023-05-18 17:34:26 - SimpleLog - INFO: - algo_name NoisyDQN +2023-05-18 17:34:26 - SimpleLog - INFO: - mode test +2023-05-18 17:34:26 - SimpleLog - INFO: - device cpu +2023-05-18 17:34:26 - SimpleLog - INFO: - seed 1 +2023-05-18 17:34:26 - SimpleLog - INFO: - max_episode 10 +2023-05-18 17:34:26 - SimpleLog - INFO: - max_step 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - collect_traj 0 +2023-05-18 17:34:26 - SimpleLog - INFO: - mp_backend single +2023-05-18 17:34:26 - SimpleLog - INFO: - n_workers 2 +2023-05-18 17:34:26 - SimpleLog - INFO: - n_learners 1 +2023-05-18 17:34:26 - SimpleLog - INFO: - share_buffer 1 +2023-05-18 17:34:26 - SimpleLog - INFO: - online_eval 1 +2023-05-18 17:34:26 - SimpleLog - INFO: - online_eval_episode 10 +2023-05-18 17:34:26 - SimpleLog - INFO: - model_save_fre 500 +2023-05-18 17:34:26 - SimpleLog - INFO: - load_checkpoint 1 +2023-05-18 17:34:26 - SimpleLog - INFO: - load_path Train_ray_CartPole-v1_NoisyDQN_20230518-172642 +2023-05-18 17:34:26 - SimpleLog - INFO: - load_model_step best +2023-05-18 17:34:26 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:34:26 - SimpleLog - INFO: - Algo Configs: +2023-05-18 17:34:26 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:34:26 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:34:26 - SimpleLog - INFO: - epsilon_start 0.95 +2023-05-18 17:34:26 - SimpleLog - INFO: - epsilon_end 0.01 +2023-05-18 17:34:26 - SimpleLog - INFO: - epsilon_decay 500 +2023-05-18 17:34:26 - SimpleLog - INFO: - gamma 0.99 +2023-05-18 17:34:26 - SimpleLog - INFO: - lr 0.0001 +2023-05-18 17:34:26 - SimpleLog - INFO: - buffer_size 100000 +2023-05-18 17:34:26 - SimpleLog - INFO: - batch_size 64 +2023-05-18 17:34:26 - SimpleLog - INFO: - target_update 4 +2023-05-18 17:34:26 - SimpleLog - INFO: - value_layers [{'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}, {'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}] +2023-05-18 17:34:26 - SimpleLog - INFO: - buffer_type REPLAY_QUE +2023-05-18 17:34:26 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:34:26 - SimpleLog - INFO: - Env Configs: +2023-05-18 17:34:26 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:34:26 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:34:26 - SimpleLog - INFO: - id CartPole-v1 +2023-05-18 17:34:26 - SimpleLog - INFO: - render_mode None +2023-05-18 17:34:26 - SimpleLog - INFO: - wrapper None +2023-05-18 17:34:26 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-18 17:34:26 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:34:26 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2) +2023-05-18 17:34:26 - SimpleLog - INFO: - Start testing! +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 0, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 1, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 2, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 3, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 4, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 5, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 6, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 7, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 8, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - episode: 9, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:34:26 - SimpleLog - INFO: - Finish testing! total time consumed: 0.40s diff --git a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/tb_logs/interact/events.out.tfevents.1684402466.JMac.local.93018.0 b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/tb_logs/interact/events.out.tfevents.1684402466.JMac.local.93018.0 new file mode 100644 index 0000000000000000000000000000000000000000..ba2d6387c03e64cd2ac500851437d4bbb38af867 --- /dev/null +++ b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/tb_logs/interact/events.out.tfevents.1684402466.JMac.local.93018.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:258880c4de60e1559379aafb2b9a88c8acae2bc5837b2aac244ad616e98826bb +size 1056 diff --git a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/tb_logs/model/events.out.tfevents.1684402466.JMac.local.93018.1 b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/tb_logs/model/events.out.tfevents.1684402466.JMac.local.93018.1 new file mode 100644 index 0000000000000000000000000000000000000000..4d6ff682d098f7398490844f9766cd8bd904844c --- /dev/null +++ b/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-173426/tb_logs/model/events.out.tfevents.1684402466.JMac.local.93018.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8f09f32b8bf3b696ef8955e087d48e6aa80c7f6a142450bf7bcc7d25282a26 +size 40 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/.DS_Store b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/.DS_Store deleted file mode 100644 index b8ede2ae7112d7ae2b38866a49526a0dd67f83de..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/.DS_Store and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/logs/log.txt b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/logs/log.txt deleted file mode 100644 index f273aaccf27603d3b2207b8e4e9b79b3d5f6be55..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/logs/log.txt +++ /dev/null @@ -1,168 +0,0 @@ -2023-05-18 13:39:47 - SimpleLog - INFO: - General Configs: -2023-05-18 13:39:47 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:39:47 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:39:47 - SimpleLog - INFO: - env_name gym -2023-05-18 13:39:47 - SimpleLog - INFO: - algo_name NoisyDQN -2023-05-18 13:39:47 - SimpleLog - INFO: - mode train -2023-05-18 13:39:47 - SimpleLog - INFO: - device cpu -2023-05-18 13:39:47 - SimpleLog - INFO: - seed 1 -2023-05-18 13:39:47 - SimpleLog - INFO: - max_episode 100 -2023-05-18 13:39:47 - SimpleLog - INFO: - max_step 200 -2023-05-18 13:39:47 - SimpleLog - INFO: - collect_traj 0 -2023-05-18 13:39:47 - SimpleLog - INFO: - mp_backend ray -2023-05-18 13:39:47 - SimpleLog - INFO: - n_workers 2 -2023-05-18 13:39:47 - SimpleLog - INFO: - n_learners 1 -2023-05-18 13:39:47 - SimpleLog - INFO: - share_buffer 1 -2023-05-18 13:39:47 - SimpleLog - INFO: - online_eval 1 -2023-05-18 13:39:47 - SimpleLog - INFO: - online_eval_episode 10 -2023-05-18 13:39:47 - SimpleLog - INFO: - model_save_fre 500 -2023-05-18 13:39:47 - SimpleLog - INFO: - load_checkpoint 0 -2023-05-18 13:39:47 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_NoisyDQN_20230518-133737 -2023-05-18 13:39:47 - SimpleLog - INFO: - load_model_step best -2023-05-18 13:39:47 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:39:47 - SimpleLog - INFO: - Algo Configs: -2023-05-18 13:39:47 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:39:47 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:39:47 - SimpleLog - INFO: - epsilon_start 0.95 -2023-05-18 13:39:47 - SimpleLog - INFO: - epsilon_end 0.01 -2023-05-18 13:39:47 - SimpleLog - INFO: - epsilon_decay 500 -2023-05-18 13:39:47 - SimpleLog - INFO: - gamma 0.99 -2023-05-18 13:39:47 - SimpleLog - INFO: - lr 0.0001 -2023-05-18 13:39:47 - SimpleLog - INFO: - buffer_size 100000 -2023-05-18 13:39:47 - SimpleLog - INFO: - batch_size 64 -2023-05-18 13:39:47 - SimpleLog - INFO: - target_update 4 -2023-05-18 13:39:47 - SimpleLog - INFO: - value_layers [{'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}, {'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}] -2023-05-18 13:39:47 - SimpleLog - INFO: - buffer_type REPLAY_QUE -2023-05-18 13:39:47 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:39:47 - SimpleLog - INFO: - Env Configs: -2023-05-18 13:39:47 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:39:47 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:39:47 - SimpleLog - INFO: - id CartPole-v1 -2023-05-18 13:39:47 - SimpleLog - INFO: - render_mode None -2023-05-18 13:39:47 - SimpleLog - INFO: - wrapper None -2023-05-18 13:39:47 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] -2023-05-18 13:39:47 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:39:54 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2) -2023-05-18 13:39:59 - RayLog - INFO: - Worker 0 finished episode 0 with reward 14.0 in 14 steps -2023-05-18 13:39:59 - RayLog - INFO: - Worker 1 finished episode 0 with reward 22.0 in 22 steps -2023-05-18 13:40:01 - RayLog - INFO: - Worker 1 finished episode 2 with reward 33.0 in 33 steps -2023-05-18 13:40:01 - RayLog - INFO: - Worker 0 finished episode 2 with reward 38.0 in 38 steps -2023-05-18 13:40:01 - RayLog - INFO: - Worker 0 finished episode 4 with reward 15.0 in 15 steps -2023-05-18 13:40:02 - RayLog - INFO: - Worker 0 finished episode 5 with reward 26.0 in 26 steps -2023-05-18 13:40:02 - RayLog - INFO: - Worker 1 finished episode 3 with reward 53.0 in 53 steps -2023-05-18 13:40:02 - RayLog - INFO: - Worker 0 finished episode 6 with reward 11.0 in 11 steps -2023-05-18 13:40:02 - RayLog - INFO: - Worker 1 finished episode 7 with reward 12.0 in 12 steps -2023-05-18 13:40:02 - RayLog - INFO: - Worker 0 finished episode 8 with reward 14.0 in 14 steps -2023-05-18 13:40:02 - RayLog - INFO: - Worker 1 finished episode 9 with reward 13.0 in 13 steps -2023-05-18 13:40:02 - RayLog - INFO: - Worker 0 finished episode 10 with reward 12.0 in 12 steps -2023-05-18 13:40:02 - RayLog - INFO: - Worker 1 finished episode 11 with reward 10.0 in 10 steps -2023-05-18 13:40:03 - RayLog - INFO: - Worker 0 finished episode 12 with reward 9.0 in 9 steps -2023-05-18 13:40:03 - RayLog - INFO: - Worker 1 finished episode 13 with reward 12.0 in 12 steps -2023-05-18 13:40:03 - RayLog - INFO: - Worker 0 finished episode 14 with reward 11.0 in 11 steps -2023-05-18 13:40:03 - RayLog - INFO: - Worker 1 finished episode 15 with reward 11.0 in 11 steps -2023-05-18 13:40:03 - RayLog - INFO: - Worker 0 finished episode 16 with reward 9.0 in 9 steps -2023-05-18 13:40:03 - RayLog - INFO: - Worker 1 finished episode 17 with reward 20.0 in 20 steps -2023-05-18 13:40:03 - RayLog - INFO: - Worker 0 finished episode 18 with reward 20.0 in 20 steps -2023-05-18 13:40:04 - RayLog - INFO: - Worker 0 finished episode 20 with reward 12.0 in 12 steps -2023-05-18 13:40:04 - RayLog - INFO: - Worker 0 finished episode 21 with reward 13.0 in 13 steps -2023-05-18 13:40:04 - RayLog - INFO: - Worker 1 finished episode 19 with reward 31.0 in 31 steps -2023-05-18 13:40:04 - RayLog - INFO: - Worker 0 finished episode 22 with reward 10.0 in 10 steps -2023-05-18 13:40:04 - RayLog - INFO: - Worker 1 finished episode 23 with reward 9.0 in 9 steps -2023-05-18 13:40:04 - RayLog - INFO: - Worker 0 finished episode 24 with reward 12.0 in 12 steps -2023-05-18 13:40:04 - RayLog - INFO: - Worker 1 finished episode 25 with reward 11.0 in 11 steps -2023-05-18 13:40:04 - RayLog - INFO: - Worker 0 finished episode 26 with reward 12.0 in 12 steps -2023-05-18 13:40:05 - RayLog - INFO: - Worker 1 finished episode 27 with reward 12.0 in 12 steps -2023-05-18 13:40:05 - RayLog - INFO: - Worker 0 finished episode 28 with reward 13.0 in 13 steps -2023-05-18 13:40:05 - RayLog - INFO: - Worker 1 finished episode 29 with reward 13.0 in 13 steps -2023-05-18 13:40:05 - RayLog - INFO: - Worker 0 finished episode 30 with reward 12.0 in 12 steps -2023-05-18 13:40:05 - RayLog - INFO: - Worker 1 finished episode 31 with reward 14.0 in 14 steps -2023-05-18 13:40:05 - RayLog - INFO: - Worker 0 finished episode 32 with reward 14.0 in 14 steps -2023-05-18 13:40:07 - RayLog - INFO: - learner id: 0, update_step: 500, online_eval_reward: 10.000 -2023-05-18 13:40:07 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 10.000, save the best model! -2023-05-18 13:40:07 - RayLog - INFO: - Worker 1 finished episode 33 with reward 14.0 in 14 steps -2023-05-18 13:40:07 - RayLog - INFO: - Worker 0 finished episode 34 with reward 11.0 in 11 steps -2023-05-18 13:40:07 - RayLog - INFO: - Worker 1 finished episode 35 with reward 13.0 in 13 steps -2023-05-18 13:40:07 - RayLog - INFO: - Worker 1 finished episode 37 with reward 10.0 in 10 steps -2023-05-18 13:40:07 - RayLog - INFO: - Worker 1 finished episode 38 with reward 11.0 in 11 steps -2023-05-18 13:40:07 - RayLog - INFO: - Worker 0 finished episode 36 with reward 29.0 in 29 steps -2023-05-18 13:40:08 - RayLog - INFO: - Worker 1 finished episode 39 with reward 9.0 in 9 steps -2023-05-18 13:40:08 - RayLog - INFO: - Worker 0 finished episode 40 with reward 11.0 in 11 steps -2023-05-18 13:40:08 - RayLog - INFO: - Worker 0 finished episode 42 with reward 35.0 in 35 steps -2023-05-18 13:40:08 - RayLog - INFO: - Worker 1 finished episode 41 with reward 49.0 in 49 steps -2023-05-18 13:40:09 - RayLog - INFO: - Worker 0 finished episode 43 with reward 36.0 in 36 steps -2023-05-18 13:40:09 - RayLog - INFO: - Worker 1 finished episode 44 with reward 35.0 in 35 steps -2023-05-18 13:40:10 - RayLog - INFO: - Worker 0 finished episode 45 with reward 42.0 in 42 steps -2023-05-18 13:40:10 - RayLog - INFO: - Worker 1 finished episode 46 with reward 44.0 in 44 steps -2023-05-18 13:40:10 - RayLog - INFO: - Worker 0 finished episode 47 with reward 36.0 in 36 steps -2023-05-18 13:40:11 - RayLog - INFO: - Worker 1 finished episode 48 with reward 44.0 in 44 steps -2023-05-18 13:40:11 - RayLog - INFO: - Worker 0 finished episode 49 with reward 37.0 in 37 steps -2023-05-18 13:40:12 - RayLog - INFO: - learner id: 0, update_step: 1000, online_eval_reward: 51.000 -2023-05-18 13:40:12 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 51.000, save the best model! -2023-05-18 13:40:13 - RayLog - INFO: - Worker 0 finished episode 51 with reward 76.0 in 76 steps -2023-05-18 13:40:13 - RayLog - INFO: - Worker 1 finished episode 50 with reward 109.0 in 109 steps -2023-05-18 13:40:15 - RayLog - INFO: - Worker 0 finished episode 52 with reward 119.0 in 119 steps -2023-05-18 13:40:15 - RayLog - INFO: - Worker 1 finished episode 53 with reward 120.0 in 120 steps -2023-05-18 13:40:16 - RayLog - INFO: - Worker 0 finished episode 54 with reward 57.0 in 57 steps -2023-05-18 13:40:16 - RayLog - INFO: - Worker 1 finished episode 55 with reward 44.0 in 44 steps -2023-05-18 13:40:16 - RayLog - INFO: - learner id: 0, update_step: 1500, online_eval_reward: 53.000 -2023-05-18 13:40:16 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 53.000, save the best model! -2023-05-18 13:40:17 - RayLog - INFO: - Worker 1 finished episode 57 with reward 43.0 in 43 steps -2023-05-18 13:40:18 - RayLog - INFO: - Worker 0 finished episode 56 with reward 72.0 in 72 steps -2023-05-18 13:40:18 - RayLog - INFO: - Worker 1 finished episode 58 with reward 35.0 in 35 steps -2023-05-18 13:40:19 - RayLog - INFO: - Worker 1 finished episode 60 with reward 48.0 in 48 steps -2023-05-18 13:40:19 - RayLog - INFO: - Worker 0 finished episode 59 with reward 64.0 in 64 steps -2023-05-18 13:40:19 - RayLog - INFO: - Worker 1 finished episode 61 with reward 36.0 in 36 steps -2023-05-18 13:40:20 - RayLog - INFO: - Worker 0 finished episode 62 with reward 57.0 in 57 steps -2023-05-18 13:40:20 - RayLog - INFO: - Worker 1 finished episode 63 with reward 42.0 in 42 steps -2023-05-18 13:40:21 - RayLog - INFO: - learner id: 0, update_step: 2000, online_eval_reward: 143.000 -2023-05-18 13:40:21 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 143.000, save the best model! -2023-05-18 13:40:23 - RayLog - INFO: - Worker 1 finished episode 65 with reward 100.0 in 100 steps -2023-05-18 13:40:23 - RayLog - INFO: - Worker 0 finished episode 64 with reward 153.0 in 153 steps -2023-05-18 13:40:24 - RayLog - INFO: - Worker 1 finished episode 66 with reward 61.0 in 61 steps -2023-05-18 13:40:25 - RayLog - INFO: - Worker 0 finished episode 67 with reward 111.0 in 111 steps -2023-05-18 13:40:26 - RayLog - INFO: - Worker 1 finished episode 68 with reward 103.0 in 103 steps -2023-05-18 13:40:27 - RayLog - INFO: - learner id: 0, update_step: 2500, online_eval_reward: 85.000 -2023-05-18 13:40:28 - RayLog - INFO: - Worker 1 finished episode 70 with reward 127.0 in 127 steps -2023-05-18 13:40:29 - RayLog - INFO: - Worker 0 finished episode 69 with reward 164.0 in 164 steps -2023-05-18 13:40:32 - RayLog - INFO: - learner id: 0, update_step: 3000, online_eval_reward: 74.000 -2023-05-18 13:40:32 - RayLog - INFO: - Worker 1 finished episode 71 with reward 200.0 in 200 steps -2023-05-18 13:40:32 - RayLog - INFO: - Worker 0 finished episode 72 with reward 186.0 in 186 steps -2023-05-18 13:40:35 - RayLog - INFO: - Worker 1 finished episode 73 with reward 114.0 in 114 steps -2023-05-18 13:40:35 - RayLog - INFO: - Worker 0 finished episode 74 with reward 109.0 in 109 steps -2023-05-18 13:40:36 - RayLog - INFO: - Worker 1 finished episode 75 with reward 72.0 in 72 steps -2023-05-18 13:40:37 - RayLog - INFO: - learner id: 0, update_step: 3500, online_eval_reward: 83.000 -2023-05-18 13:40:37 - RayLog - INFO: - Worker 0 finished episode 76 with reward 96.0 in 96 steps -2023-05-18 13:40:37 - RayLog - INFO: - Worker 1 finished episode 77 with reward 62.0 in 62 steps -2023-05-18 13:40:38 - RayLog - INFO: - Worker 0 finished episode 78 with reward 88.0 in 88 steps -2023-05-18 13:40:39 - RayLog - INFO: - Worker 1 finished episode 79 with reward 70.0 in 70 steps -2023-05-18 13:40:40 - RayLog - INFO: - Worker 1 finished episode 81 with reward 77.0 in 77 steps -2023-05-18 13:40:42 - RayLog - INFO: - learner id: 0, update_step: 4000, online_eval_reward: 123.000 -2023-05-18 13:40:42 - RayLog - INFO: - Worker 0 finished episode 80 with reward 181.0 in 181 steps -2023-05-18 13:40:42 - RayLog - INFO: - Worker 1 finished episode 82 with reward 105.0 in 105 steps -2023-05-18 13:40:46 - RayLog - INFO: - Worker 0 finished episode 83 with reward 200.0 in 200 steps -2023-05-18 13:40:47 - RayLog - INFO: - Worker 1 finished episode 84 with reward 200.0 in 200 steps -2023-05-18 13:40:47 - RayLog - INFO: - learner id: 0, update_step: 4500, online_eval_reward: 200.000 -2023-05-18 13:40:47 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 200.000, save the best model! -2023-05-18 13:40:51 - RayLog - INFO: - Worker 0 finished episode 85 with reward 200.0 in 200 steps -2023-05-18 13:40:51 - RayLog - INFO: - Worker 1 finished episode 86 with reward 200.0 in 200 steps -2023-05-18 13:40:53 - RayLog - INFO: - learner id: 0, update_step: 5000, online_eval_reward: 200.000 -2023-05-18 13:40:56 - RayLog - INFO: - Worker 0 finished episode 87 with reward 200.0 in 200 steps -2023-05-18 13:40:56 - RayLog - INFO: - Worker 1 finished episode 88 with reward 200.0 in 200 steps -2023-05-18 13:40:59 - RayLog - INFO: - learner id: 0, update_step: 5500, online_eval_reward: 200.000 -2023-05-18 13:41:00 - RayLog - INFO: - Worker 0 finished episode 89 with reward 200.0 in 200 steps -2023-05-18 13:41:01 - RayLog - INFO: - Worker 1 finished episode 90 with reward 200.0 in 200 steps -2023-05-18 13:41:05 - RayLog - INFO: - learner id: 0, update_step: 6000, online_eval_reward: 200.000 -2023-05-18 13:41:05 - RayLog - INFO: - Worker 0 finished episode 91 with reward 200.0 in 200 steps -2023-05-18 13:41:05 - RayLog - INFO: - Worker 1 finished episode 92 with reward 200.0 in 200 steps -2023-05-18 13:41:10 - RayLog - INFO: - Worker 0 finished episode 93 with reward 200.0 in 200 steps -2023-05-18 13:41:10 - RayLog - INFO: - Worker 1 finished episode 94 with reward 200.0 in 200 steps -2023-05-18 13:41:11 - RayLog - INFO: - learner id: 0, update_step: 6500, online_eval_reward: 200.000 -2023-05-18 13:41:15 - RayLog - INFO: - Worker 0 finished episode 95 with reward 200.0 in 200 steps -2023-05-18 13:41:15 - RayLog - INFO: - Worker 1 finished episode 96 with reward 200.0 in 200 steps -2023-05-18 13:41:17 - RayLog - INFO: - learner id: 0, update_step: 7000, online_eval_reward: 200.000 -2023-05-18 13:41:19 - RayLog - INFO: - Worker 0 finished episode 97 with reward 200.0 in 200 steps -2023-05-18 13:41:20 - RayLog - INFO: - Worker 1 finished episode 98 with reward 200.0 in 200 steps -2023-05-18 13:41:23 - RayLog - INFO: - learner id: 0, update_step: 7500, online_eval_reward: 200.000 -2023-05-18 13:41:24 - RayLog - INFO: - Worker 0 finished episode 99 with reward 200.0 in 200 steps -2023-05-18 13:41:25 - RayLog - INFO: - Worker 1 finished episode 100 with reward 200.0 in 200 steps -2023-05-18 13:41:28 - SimpleLog - INFO: - Finish training! total time consumed: 100.97s diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/1000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/1000 deleted file mode 100644 index 74e47feb7a24f50f810c9b7363b233a0326da957..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/1000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/1500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/1500 deleted file mode 100644 index fcf4f1cf8b15576174682078fd929fa9628c2277..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/1500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/2000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/2000 deleted file mode 100644 index 755a1c7fc9df14aabede89b4b2171730cf295f57..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/2000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/2500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/2500 deleted file mode 100644 index 07c910744feaf07798eb1b9b339ce3db6f4e93ed..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/2500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/3000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/3000 deleted file mode 100644 index c61013298531435a056aa82fbc2bb40800b44d11..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/3000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/3500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/3500 deleted file mode 100644 index 926cce05ffbc708cece3a7ee1008c30e48cebfa4..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/3500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/4000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/4000 deleted file mode 100644 index c9d0dc07fd37a07376b4c3d877a5b2ca5c87b6e3..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/4000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/4500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/4500 deleted file mode 100644 index d94502e1889c18e29b2b3b1509a4e7b5e5098672..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/4500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/500 deleted file mode 100644 index ed38cb30fe096739b7aa71a21df31b3fbe19bd27..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/5000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/5000 deleted file mode 100644 index 0215111a35a49a2f7400916d4720e49b9eea3762..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/5000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/5500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/5500 deleted file mode 100644 index cf0237614550d25362fb619aea38e07ede55f475..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/5500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/6000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/6000 deleted file mode 100644 index 65293febc436b6c2c02014283eafa5e81457fb83..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/6000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/6500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/6500 deleted file mode 100644 index 8010d65fd82b91227765a96f36cf5cbcd75e2709..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/6500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/7000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/7000 deleted file mode 100644 index e4705b62089b56812d3c2633544c58f22756bc4a..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/7000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/7500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/7500 deleted file mode 100644 index b6b6156fea87497141abc96e14ca4176af8b9130..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/7500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/best b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/best deleted file mode 100644 index d94502e1889c18e29b2b3b1509a4e7b5e5098672..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/models/best and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/interact/events.out.tfevents.1684388387.JMac.local.86757.0 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/interact/events.out.tfevents.1684388387.JMac.local.86757.0 deleted file mode 100644 index f7faafe6c2b6faa8af858204bc769a50dbb92de2..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/interact/events.out.tfevents.1684388387.JMac.local.86757.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e571710bb077a186d5841f41570cb79c0d8364b23ad6c763b1b9296ceaf0284f -size 40 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/interact/events.out.tfevents.1684388398.JMac.local.86815.0 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/interact/events.out.tfevents.1684388398.JMac.local.86815.0 deleted file mode 100644 index 46cd80b5f2d0156cdabca3a13ae067311fb60c02..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/interact/events.out.tfevents.1684388398.JMac.local.86815.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:836310578ed6206604d3b1432fc5f35019c383105fbb64f1505a5bd72baf68cb -size 10028 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/model/events.out.tfevents.1684388387.JMac.local.86757.1 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/model/events.out.tfevents.1684388387.JMac.local.86757.1 deleted file mode 100644 index 8db3775f5995cb0d7756083bf2c042a2f313cf09..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/model/events.out.tfevents.1684388387.JMac.local.86757.1 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:104eaae7368044a1396e1f0288356e64792ffebc2905456d3a98edd39438d03c -size 40 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/model/events.out.tfevents.1684388398.JMac.local.86815.1 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/model/events.out.tfevents.1684388398.JMac.local.86815.1 deleted file mode 100644 index c16a4edccd9deded79b4f91247e3d96257e82955..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/tb_logs/model/events.out.tfevents.1684388398.JMac.local.86815.1 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8fd21541f93e709c2d2db525eb5b8fb4569896f9ec747de14ab5193752825d5f -size 375106 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/config.yaml b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/config.yaml similarity index 100% rename from ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-133947/config.yaml rename to ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/config.yaml diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/logs/log.txt b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..5dd46efd9d6f5d751a574f7aa82ff47a8f9faaed --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/logs/log.txt @@ -0,0 +1,168 @@ +2023-05-18 17:26:42 - SimpleLog - INFO: - General Configs: +2023-05-18 17:26:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:26:42 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:26:42 - SimpleLog - INFO: - env_name gym +2023-05-18 17:26:42 - SimpleLog - INFO: - algo_name NoisyDQN +2023-05-18 17:26:42 - SimpleLog - INFO: - mode train +2023-05-18 17:26:42 - SimpleLog - INFO: - device cpu +2023-05-18 17:26:42 - SimpleLog - INFO: - seed 1 +2023-05-18 17:26:42 - SimpleLog - INFO: - max_episode 100 +2023-05-18 17:26:42 - SimpleLog - INFO: - max_step 200 +2023-05-18 17:26:42 - SimpleLog - INFO: - collect_traj 0 +2023-05-18 17:26:42 - SimpleLog - INFO: - mp_backend ray +2023-05-18 17:26:42 - SimpleLog - INFO: - n_workers 2 +2023-05-18 17:26:42 - SimpleLog - INFO: - n_learners 1 +2023-05-18 17:26:42 - SimpleLog - INFO: - share_buffer 1 +2023-05-18 17:26:42 - SimpleLog - INFO: - online_eval 1 +2023-05-18 17:26:42 - SimpleLog - INFO: - online_eval_episode 10 +2023-05-18 17:26:42 - SimpleLog - INFO: - model_save_fre 500 +2023-05-18 17:26:42 - SimpleLog - INFO: - load_checkpoint 0 +2023-05-18 17:26:42 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_NoisyDQN_20230518-133737 +2023-05-18 17:26:42 - SimpleLog - INFO: - load_model_step best +2023-05-18 17:26:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:26:42 - SimpleLog - INFO: - Algo Configs: +2023-05-18 17:26:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:26:42 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:26:42 - SimpleLog - INFO: - epsilon_start 0.95 +2023-05-18 17:26:42 - SimpleLog - INFO: - epsilon_end 0.01 +2023-05-18 17:26:42 - SimpleLog - INFO: - epsilon_decay 500 +2023-05-18 17:26:42 - SimpleLog - INFO: - gamma 0.99 +2023-05-18 17:26:42 - SimpleLog - INFO: - lr 0.0001 +2023-05-18 17:26:42 - SimpleLog - INFO: - buffer_size 100000 +2023-05-18 17:26:42 - SimpleLog - INFO: - batch_size 64 +2023-05-18 17:26:42 - SimpleLog - INFO: - target_update 4 +2023-05-18 17:26:42 - SimpleLog - INFO: - value_layers [{'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}, {'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}] +2023-05-18 17:26:42 - SimpleLog - INFO: - buffer_type REPLAY_QUE +2023-05-18 17:26:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:26:42 - SimpleLog - INFO: - Env Configs: +2023-05-18 17:26:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:26:42 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:26:42 - SimpleLog - INFO: - id CartPole-v1 +2023-05-18 17:26:42 - SimpleLog - INFO: - render_mode None +2023-05-18 17:26:42 - SimpleLog - INFO: - wrapper None +2023-05-18 17:26:42 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-18 17:26:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:26:49 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2) +2023-05-18 17:26:56 - RayLog - INFO: - Worker 1 finished episode 0 with reward 41.0 in 41 steps +2023-05-18 17:26:57 - RayLog - INFO: - Worker 0 finished episode 0 with reward 55.0 in 55 steps +2023-05-18 17:26:57 - RayLog - INFO: - Worker 1 finished episode 1 with reward 15.0 in 15 steps +2023-05-18 17:26:57 - RayLog - INFO: - Worker 0 finished episode 2 with reward 17.0 in 17 steps +2023-05-18 17:26:57 - RayLog - INFO: - Worker 1 finished episode 3 with reward 24.0 in 24 steps +2023-05-18 17:26:57 - RayLog - INFO: - Worker 0 finished episode 4 with reward 12.0 in 12 steps +2023-05-18 17:26:57 - RayLog - INFO: - Worker 0 finished episode 6 with reward 9.0 in 9 steps +2023-05-18 17:26:57 - RayLog - INFO: - Worker 1 finished episode 5 with reward 17.0 in 17 steps +2023-05-18 17:26:58 - RayLog - INFO: - Worker 0 finished episode 7 with reward 11.0 in 11 steps +2023-05-18 17:26:58 - RayLog - INFO: - Worker 1 finished episode 8 with reward 11.0 in 11 steps +2023-05-18 17:26:58 - RayLog - INFO: - Worker 0 finished episode 9 with reward 11.0 in 11 steps +2023-05-18 17:26:58 - RayLog - INFO: - Worker 1 finished episode 10 with reward 13.0 in 13 steps +2023-05-18 17:26:58 - RayLog - INFO: - Worker 0 finished episode 11 with reward 11.0 in 11 steps +2023-05-18 17:26:58 - RayLog - INFO: - Worker 1 finished episode 12 with reward 16.0 in 16 steps +2023-05-18 17:26:58 - RayLog - INFO: - Worker 0 finished episode 13 with reward 12.0 in 12 steps +2023-05-18 17:26:59 - RayLog - INFO: - Worker 0 finished episode 15 with reward 11.0 in 11 steps +2023-05-18 17:26:59 - RayLog - INFO: - Worker 1 finished episode 14 with reward 13.0 in 13 steps +2023-05-18 17:26:59 - RayLog - INFO: - Worker 0 finished episode 16 with reward 14.0 in 14 steps +2023-05-18 17:26:59 - RayLog - INFO: - Worker 0 finished episode 18 with reward 10.0 in 10 steps +2023-05-18 17:26:59 - RayLog - INFO: - Worker 1 finished episode 17 with reward 24.0 in 24 steps +2023-05-18 17:26:59 - RayLog - INFO: - Worker 0 finished episode 19 with reward 12.0 in 12 steps +2023-05-18 17:27:00 - RayLog - INFO: - Worker 1 finished episode 20 with reward 17.0 in 17 steps +2023-05-18 17:27:00 - RayLog - INFO: - Worker 0 finished episode 21 with reward 14.0 in 14 steps +2023-05-18 17:27:00 - RayLog - INFO: - Worker 1 finished episode 22 with reward 9.0 in 9 steps +2023-05-18 17:27:00 - RayLog - INFO: - Worker 1 finished episode 24 with reward 9.0 in 9 steps +2023-05-18 17:27:00 - RayLog - INFO: - Worker 0 finished episode 23 with reward 17.0 in 17 steps +2023-05-18 17:27:00 - RayLog - INFO: - Worker 1 finished episode 25 with reward 13.0 in 13 steps +2023-05-18 17:27:01 - RayLog - INFO: - Worker 0 finished episode 26 with reward 15.0 in 15 steps +2023-05-18 17:27:01 - RayLog - INFO: - Worker 1 finished episode 27 with reward 13.0 in 13 steps +2023-05-18 17:27:01 - RayLog - INFO: - Worker 0 finished episode 28 with reward 11.0 in 11 steps +2023-05-18 17:27:01 - RayLog - INFO: - Worker 1 finished episode 29 with reward 9.0 in 9 steps +2023-05-18 17:27:01 - RayLog - INFO: - Worker 0 finished episode 30 with reward 15.0 in 15 steps +2023-05-18 17:27:01 - RayLog - INFO: - Worker 1 finished episode 31 with reward 16.0 in 16 steps +2023-05-18 17:27:01 - RayLog - INFO: - Worker 0 finished episode 32 with reward 10.0 in 10 steps +2023-05-18 17:27:01 - RayLog - INFO: - Worker 1 finished episode 33 with reward 9.0 in 9 steps +2023-05-18 17:27:02 - RayLog - INFO: - Worker 0 finished episode 34 with reward 10.0 in 10 steps +2023-05-18 17:27:02 - RayLog - INFO: - Worker 1 finished episode 35 with reward 9.0 in 9 steps +2023-05-18 17:27:03 - RayLog - INFO: - learner id: 0, update_step: 500, online_eval_reward: 10.000 +2023-05-18 17:27:03 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 10.000, save the best model! +2023-05-18 17:27:03 - RayLog - INFO: - Worker 0 finished episode 36 with reward 12.0 in 12 steps +2023-05-18 17:27:03 - RayLog - INFO: - Worker 1 finished episode 37 with reward 17.0 in 17 steps +2023-05-18 17:27:05 - RayLog - INFO: - Worker 0 finished episode 38 with reward 92.0 in 92 steps +2023-05-18 17:27:06 - RayLog - INFO: - Worker 1 finished episode 39 with reward 99.0 in 99 steps +2023-05-18 17:27:06 - RayLog - INFO: - Worker 0 finished episode 40 with reward 26.0 in 26 steps +2023-05-18 17:27:07 - RayLog - INFO: - Worker 0 finished episode 42 with reward 23.0 in 23 steps +2023-05-18 17:27:07 - RayLog - INFO: - Worker 1 finished episode 41 with reward 40.0 in 40 steps +2023-05-18 17:27:07 - RayLog - INFO: - Worker 0 finished episode 43 with reward 21.0 in 21 steps +2023-05-18 17:27:07 - RayLog - INFO: - Worker 1 finished episode 44 with reward 32.0 in 32 steps +2023-05-18 17:27:08 - RayLog - INFO: - Worker 0 finished episode 45 with reward 20.0 in 20 steps +2023-05-18 17:27:08 - RayLog - INFO: - Worker 1 finished episode 46 with reward 28.0 in 28 steps +2023-05-18 17:27:08 - RayLog - INFO: - Worker 0 finished episode 47 with reward 27.0 in 27 steps +2023-05-18 17:27:09 - RayLog - INFO: - Worker 0 finished episode 49 with reward 21.0 in 21 steps +2023-05-18 17:27:09 - RayLog - INFO: - Worker 1 finished episode 48 with reward 30.0 in 30 steps +2023-05-18 17:27:09 - RayLog - INFO: - learner id: 0, update_step: 1000, online_eval_reward: 25.000 +2023-05-18 17:27:09 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 25.000, save the best model! +2023-05-18 17:27:09 - RayLog - INFO: - Worker 1 finished episode 51 with reward 18.0 in 18 steps +2023-05-18 17:27:09 - RayLog - INFO: - Worker 0 finished episode 50 with reward 24.0 in 24 steps +2023-05-18 17:27:10 - RayLog - INFO: - Worker 0 finished episode 53 with reward 24.0 in 24 steps +2023-05-18 17:27:10 - RayLog - INFO: - Worker 1 finished episode 52 with reward 29.0 in 29 steps +2023-05-18 17:27:11 - RayLog - INFO: - Worker 0 finished episode 54 with reward 24.0 in 24 steps +2023-05-18 17:27:11 - RayLog - INFO: - Worker 1 finished episode 55 with reward 29.0 in 29 steps +2023-05-18 17:27:11 - RayLog - INFO: - Worker 0 finished episode 56 with reward 23.0 in 23 steps +2023-05-18 17:27:11 - RayLog - INFO: - Worker 1 finished episode 57 with reward 33.0 in 33 steps +2023-05-18 17:27:12 - RayLog - INFO: - Worker 0 finished episode 58 with reward 31.0 in 31 steps +2023-05-18 17:27:12 - RayLog - INFO: - Worker 0 finished episode 60 with reward 25.0 in 25 steps +2023-05-18 17:27:12 - RayLog - INFO: - Worker 1 finished episode 59 with reward 39.0 in 39 steps +2023-05-18 17:27:13 - RayLog - INFO: - Worker 0 finished episode 61 with reward 33.0 in 33 steps +2023-05-18 17:27:14 - RayLog - INFO: - Worker 1 finished episode 62 with reward 60.0 in 60 steps +2023-05-18 17:27:14 - RayLog - INFO: - Worker 0 finished episode 63 with reward 39.0 in 39 steps +2023-05-18 17:27:15 - RayLog - INFO: - Worker 0 finished episode 65 with reward 37.0 in 37 steps +2023-05-18 17:27:16 - RayLog - INFO: - learner id: 0, update_step: 1500, online_eval_reward: 35.000 +2023-05-18 17:27:16 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 35.000, save the best model! +2023-05-18 17:27:16 - RayLog - INFO: - Worker 1 finished episode 64 with reward 58.0 in 58 steps +2023-05-18 17:27:17 - RayLog - INFO: - Worker 0 finished episode 66 with reward 53.0 in 53 steps +2023-05-18 17:27:19 - RayLog - INFO: - Worker 1 finished episode 67 with reward 99.0 in 99 steps +2023-05-18 17:27:19 - RayLog - INFO: - Worker 0 finished episode 68 with reward 91.0 in 91 steps +2023-05-18 17:27:21 - RayLog - INFO: - Worker 1 finished episode 69 with reward 106.0 in 106 steps +2023-05-18 17:27:23 - RayLog - INFO: - learner id: 0, update_step: 2000, online_eval_reward: 200.000 +2023-05-18 17:27:23 - RayLog - INFO: - learner 0 for current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:27:25 - RayLog - INFO: - Worker 0 finished episode 70 with reward 200.0 in 200 steps +2023-05-18 17:27:27 - RayLog - INFO: - Worker 1 finished episode 71 with reward 200.0 in 200 steps +2023-05-18 17:27:29 - RayLog - INFO: - learner id: 0, update_step: 2500, online_eval_reward: 200.000 +2023-05-18 17:27:30 - RayLog - INFO: - Worker 0 finished episode 72 with reward 200.0 in 200 steps +2023-05-18 17:27:32 - RayLog - INFO: - Worker 1 finished episode 73 with reward 200.0 in 200 steps +2023-05-18 17:27:36 - RayLog - INFO: - Worker 0 finished episode 74 with reward 200.0 in 200 steps +2023-05-18 17:27:37 - RayLog - INFO: - learner id: 0, update_step: 3000, online_eval_reward: 200.000 +2023-05-18 17:27:39 - RayLog - INFO: - Worker 1 finished episode 75 with reward 200.0 in 200 steps +2023-05-18 17:27:42 - RayLog - INFO: - Worker 0 finished episode 76 with reward 200.0 in 200 steps +2023-05-18 17:27:44 - RayLog - INFO: - learner id: 0, update_step: 3500, online_eval_reward: 200.000 +2023-05-18 17:27:44 - RayLog - INFO: - Worker 1 finished episode 77 with reward 200.0 in 200 steps +2023-05-18 17:27:48 - RayLog - INFO: - Worker 0 finished episode 78 with reward 200.0 in 200 steps +2023-05-18 17:27:50 - RayLog - INFO: - Worker 1 finished episode 79 with reward 200.0 in 200 steps +2023-05-18 17:27:52 - RayLog - INFO: - learner id: 0, update_step: 4000, online_eval_reward: 200.000 +2023-05-18 17:27:54 - RayLog - INFO: - Worker 0 finished episode 80 with reward 200.0 in 200 steps +2023-05-18 17:27:56 - RayLog - INFO: - Worker 1 finished episode 81 with reward 200.0 in 200 steps +2023-05-18 17:27:59 - RayLog - INFO: - learner id: 0, update_step: 4500, online_eval_reward: 200.000 +2023-05-18 17:28:00 - RayLog - INFO: - Worker 0 finished episode 82 with reward 200.0 in 200 steps +2023-05-18 17:28:02 - RayLog - INFO: - Worker 1 finished episode 83 with reward 200.0 in 200 steps +2023-05-18 17:28:06 - RayLog - INFO: - Worker 0 finished episode 84 with reward 200.0 in 200 steps +2023-05-18 17:28:06 - RayLog - INFO: - learner id: 0, update_step: 5000, online_eval_reward: 200.000 +2023-05-18 17:28:08 - RayLog - INFO: - Worker 1 finished episode 85 with reward 200.0 in 200 steps +2023-05-18 17:28:12 - RayLog - INFO: - Worker 0 finished episode 86 with reward 200.0 in 200 steps +2023-05-18 17:28:14 - RayLog - INFO: - learner id: 0, update_step: 5500, online_eval_reward: 200.000 +2023-05-18 17:28:14 - RayLog - INFO: - Worker 1 finished episode 87 with reward 200.0 in 200 steps +2023-05-18 17:28:18 - RayLog - INFO: - Worker 0 finished episode 88 with reward 200.0 in 200 steps +2023-05-18 17:28:20 - RayLog - INFO: - Worker 1 finished episode 89 with reward 200.0 in 200 steps +2023-05-18 17:28:21 - RayLog - INFO: - learner id: 0, update_step: 6000, online_eval_reward: 200.000 +2023-05-18 17:28:24 - RayLog - INFO: - Worker 0 finished episode 90 with reward 200.0 in 200 steps +2023-05-18 17:28:26 - RayLog - INFO: - Worker 1 finished episode 91 with reward 200.0 in 200 steps +2023-05-18 17:28:29 - RayLog - INFO: - learner id: 0, update_step: 6500, online_eval_reward: 200.000 +2023-05-18 17:28:30 - RayLog - INFO: - Worker 0 finished episode 92 with reward 200.0 in 200 steps +2023-05-18 17:28:32 - RayLog - INFO: - Worker 1 finished episode 93 with reward 200.0 in 200 steps +2023-05-18 17:28:37 - RayLog - INFO: - Worker 0 finished episode 94 with reward 200.0 in 200 steps +2023-05-18 17:28:38 - RayLog - INFO: - learner id: 0, update_step: 7000, online_eval_reward: 200.000 +2023-05-18 17:28:40 - RayLog - INFO: - Worker 1 finished episode 95 with reward 200.0 in 200 steps +2023-05-18 17:28:44 - RayLog - INFO: - Worker 0 finished episode 96 with reward 200.0 in 200 steps +2023-05-18 17:28:47 - RayLog - INFO: - learner id: 0, update_step: 7500, online_eval_reward: 200.000 +2023-05-18 17:28:47 - RayLog - INFO: - Worker 1 finished episode 97 with reward 200.0 in 200 steps +2023-05-18 17:28:52 - RayLog - INFO: - Worker 0 finished episode 98 with reward 200.0 in 200 steps +2023-05-18 17:28:54 - RayLog - INFO: - Worker 1 finished episode 99 with reward 200.0 in 200 steps +2023-05-18 17:28:56 - RayLog - INFO: - learner id: 0, update_step: 8000, online_eval_reward: 200.000 +2023-05-18 17:28:58 - RayLog - INFO: - Worker 0 finished episode 100 with reward 200.0 in 200 steps +2023-05-18 17:29:01 - SimpleLog - INFO: - Finish training! total time consumed: 138.97s diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/1000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/1000 new file mode 100644 index 0000000000000000000000000000000000000000..d52196dd804c28e56a40df8cd1667e7cf09cb6c4 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/1000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d57deeb0464b6e9f89819ad546824a3f1e2e8002aeade1276ae5ac422b081c5 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/1500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/1500 new file mode 100644 index 0000000000000000000000000000000000000000..95030a5afa98d8c38b5669d307b156eb81cf1c4f --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/1500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b19df30e46730d16ec3413c9280b0e4f07632abe78cd54eda08ea40ae04ad21 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/2000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/2000 new file mode 100644 index 0000000000000000000000000000000000000000..ff72447f3825f6b37bd94e3b13b90848c80a05c1 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/2000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a27127e0838f8ad9672fae3534b7bd294ad20c815367138448f010969632952 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/2500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/2500 new file mode 100644 index 0000000000000000000000000000000000000000..6d6a3de600f8b057ad34c203c89d654dca71b63e --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/2500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03690ae5376aff9ec01509b969d554b453b7b2ecf5770777009f6cd80a02034d +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/3000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/3000 new file mode 100644 index 0000000000000000000000000000000000000000..50905ebc7612e1f7f81394ab34185d326f0044ee --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/3000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d1fab6ad841dfd4d452cd883b9cc61d6a6d3fec15a540c8de29e92926ede97 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/3500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/3500 new file mode 100644 index 0000000000000000000000000000000000000000..7d29af88e55f11797b80be088caf78e29ecf348f --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/3500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:619aa81383729fe98f60d0fdb71018605f747253585949decb77c121a8979586 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/4000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/4000 new file mode 100644 index 0000000000000000000000000000000000000000..f8f8b939fd300b793540eb4a8d0c08a47b1c68d0 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/4000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e37b97bc88d3e21e31fdd4d53e7a16c90a73c850156cc5bba2076113a599b80 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/4500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/4500 new file mode 100644 index 0000000000000000000000000000000000000000..d1a402146c1b5dc96558a088df5773ef2899370d --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/4500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca2009138f869be797b7f9e4efa341d831e9ec677607648c46790983e480d93 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/500 new file mode 100644 index 0000000000000000000000000000000000000000..a880a6aa8ba7082f23e1456623b03b4513edce62 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4089a151d252a9e0cf8721e74b8b636eded43d173e8f1848c12d4240d4e47ec1 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/5000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/5000 new file mode 100644 index 0000000000000000000000000000000000000000..69aede0484d57dc50e1af6d8b275c9edbee48d3f --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/5000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c22f9833c9e8c13d971b2c012fdb3cc4e85d76bb8efaccc5d3767e4d7befd5 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/5500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/5500 new file mode 100644 index 0000000000000000000000000000000000000000..48f143593b1bea2716875193c3709146aeec25a1 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/5500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4273ff1ab2f0024f3562fac0d9b57e356410996ac13f6a0c512e918b1dce59f6 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/6000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/6000 new file mode 100644 index 0000000000000000000000000000000000000000..5a8f946429bd85bd69f786f212982568de7f4ef9 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/6000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcc1f49e420050d54de512a0ec1d1a9713b10017e4159527cef1812df30a5fd9 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/6500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/6500 new file mode 100644 index 0000000000000000000000000000000000000000..41c89973ff1ef863006d4706c8f20541dcb87cc9 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/6500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937fdc23e792e243262fa7bacf8e1f28b092ed885df060a6aab7baa953cfd941 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/7000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/7000 new file mode 100644 index 0000000000000000000000000000000000000000..a61733898e872fd83cc32f52314a08a1f2c51a96 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/7000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f766ef6a6a2270f18a559238f85b14f3ca5beb4fa98bb45d85aba35629541732 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/7500 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/7500 new file mode 100644 index 0000000000000000000000000000000000000000..82cd9f42f3e62345f13dbf8c7d5bd1887fc86f60 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/7500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d765cdf390b5197972a3d250edd2993bb91c764bfacac17fe66207b336276d +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/8000 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/8000 new file mode 100644 index 0000000000000000000000000000000000000000..599d99aeab687f1ccd892d20893985beb04d3bb4 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/8000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04527e16df0a53f53764515da214ee67a5e4c5cf821e612c35df5ec94b43d6d8 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/best b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/best new file mode 100644 index 0000000000000000000000000000000000000000..ff72447f3825f6b37bd94e3b13b90848c80a05c1 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/models/best @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a27127e0838f8ad9672fae3534b7bd294ad20c815367138448f010969632952 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/interact/events.out.tfevents.1684402002.JMac.local.91984.0 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/interact/events.out.tfevents.1684402002.JMac.local.91984.0 new file mode 100644 index 0000000000000000000000000000000000000000..3ec5de782df5a17e9020312988f220c76d6079eb --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/interact/events.out.tfevents.1684402002.JMac.local.91984.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dbe30ce02b42e95b4b867ddfc2e8e68cc94f87181bc659a19e4f5c174c5b93b +size 40 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/interact/events.out.tfevents.1684402014.JMac.local.92035.0 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/interact/events.out.tfevents.1684402014.JMac.local.92035.0 new file mode 100644 index 0000000000000000000000000000000000000000..c9d9297cd22b46e51033dedec6cd37ef8a652126 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/interact/events.out.tfevents.1684402014.JMac.local.92035.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0232091096dd5fa4d72d8b15deebf885a69d7fe03e4dff2c31ddbc5901549b +size 10028 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/model/events.out.tfevents.1684402002.JMac.local.91984.1 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/model/events.out.tfevents.1684402002.JMac.local.91984.1 new file mode 100644 index 0000000000000000000000000000000000000000..e5db1fe5f8af3dce1f83723bd887b708cd2423ad --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/model/events.out.tfevents.1684402002.JMac.local.91984.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1036e7f4f8114338b83bb2e5160a9a5dd32b4633240d896320ca7ab39b3071 +size 40 diff --git a/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/model/events.out.tfevents.1684402014.JMac.local.92035.1 b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/model/events.out.tfevents.1684402014.JMac.local.92035.1 new file mode 100644 index 0000000000000000000000000000000000000000..ac5f8a8306ff84c092668727c3c6c73b2f966652 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_ray_CartPole-v1_NoisyDQN_20230518-172642/tb_logs/model/events.out.tfevents.1684402014.JMac.local.92035.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad53b18f0687e7143053cd41109992ca0386d5cda19cedc69f9af251ef4d746e +size 394608 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/logs/log.txt b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/logs/log.txt deleted file mode 100644 index dfd7219b62f7ceb730768e2629b02e74709829df..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/logs/log.txt +++ /dev/null @@ -1,164 +0,0 @@ -2023-05-18 13:37:37 - SimpleLog - INFO: - General Configs: -2023-05-18 13:37:37 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:37:37 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:37:37 - SimpleLog - INFO: - env_name gym -2023-05-18 13:37:37 - SimpleLog - INFO: - algo_name NoisyDQN -2023-05-18 13:37:37 - SimpleLog - INFO: - mode train -2023-05-18 13:37:37 - SimpleLog - INFO: - device cpu -2023-05-18 13:37:37 - SimpleLog - INFO: - seed 1 -2023-05-18 13:37:37 - SimpleLog - INFO: - max_episode 100 -2023-05-18 13:37:37 - SimpleLog - INFO: - max_step 200 -2023-05-18 13:37:37 - SimpleLog - INFO: - collect_traj 0 -2023-05-18 13:37:37 - SimpleLog - INFO: - mp_backend single -2023-05-18 13:37:37 - SimpleLog - INFO: - n_workers 2 -2023-05-18 13:37:37 - SimpleLog - INFO: - n_learners 1 -2023-05-18 13:37:37 - SimpleLog - INFO: - share_buffer 1 -2023-05-18 13:37:37 - SimpleLog - INFO: - online_eval 1 -2023-05-18 13:37:37 - SimpleLog - INFO: - online_eval_episode 10 -2023-05-18 13:37:37 - SimpleLog - INFO: - model_save_fre 500 -2023-05-18 13:37:37 - SimpleLog - INFO: - load_checkpoint 0 -2023-05-18 13:37:37 - SimpleLog - INFO: - load_path Train_CartPole-v1_DQN_20221026-054757 -2023-05-18 13:37:37 - SimpleLog - INFO: - load_model_step best -2023-05-18 13:37:37 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:37:37 - SimpleLog - INFO: - Algo Configs: -2023-05-18 13:37:37 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:37:37 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:37:37 - SimpleLog - INFO: - epsilon_start 0.95 -2023-05-18 13:37:37 - SimpleLog - INFO: - epsilon_end 0.01 -2023-05-18 13:37:37 - SimpleLog - INFO: - epsilon_decay 500 -2023-05-18 13:37:37 - SimpleLog - INFO: - gamma 0.99 -2023-05-18 13:37:37 - SimpleLog - INFO: - lr 0.0001 -2023-05-18 13:37:37 - SimpleLog - INFO: - buffer_size 100000 -2023-05-18 13:37:37 - SimpleLog - INFO: - batch_size 64 -2023-05-18 13:37:37 - SimpleLog - INFO: - target_update 4 -2023-05-18 13:37:37 - SimpleLog - INFO: - value_layers [{'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}, {'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}] -2023-05-18 13:37:37 - SimpleLog - INFO: - buffer_type REPLAY_QUE -2023-05-18 13:37:37 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:37:37 - SimpleLog - INFO: - Env Configs: -2023-05-18 13:37:37 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:37:37 - SimpleLog - INFO: - Name Value Type -2023-05-18 13:37:37 - SimpleLog - INFO: - id CartPole-v1 -2023-05-18 13:37:37 - SimpleLog - INFO: - render_mode None -2023-05-18 13:37:37 - SimpleLog - INFO: - wrapper None -2023-05-18 13:37:37 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] -2023-05-18 13:37:37 - SimpleLog - INFO: - ================================================================================ -2023-05-18 13:37:37 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2) -2023-05-18 13:37:37 - SimpleLog - INFO: - Start training! -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 0, ep_reward: 12.0, ep_step: 12 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 1, ep_reward: 23.0, ep_step: 23 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 2, ep_reward: 21.0, ep_step: 21 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 3, ep_reward: 14.0, ep_step: 14 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 4, ep_reward: 24.0, ep_step: 24 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 5, ep_reward: 18.0, ep_step: 18 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 6, ep_reward: 45.0, ep_step: 45 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 7, ep_reward: 30.0, ep_step: 30 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 8, ep_reward: 25.0, ep_step: 25 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 9, ep_reward: 29.0, ep_step: 29 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 10, ep_reward: 13.0, ep_step: 13 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 11, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 12, ep_reward: 11.0, ep_step: 11 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 13, ep_reward: 14.0, ep_step: 14 -2023-05-18 13:37:37 - SimpleLog - INFO: - episode: 14, ep_reward: 12.0, ep_step: 12 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 15, ep_reward: 11.0, ep_step: 11 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 16, ep_reward: 11.0, ep_step: 11 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 17, ep_reward: 28.0, ep_step: 28 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 18, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 19, ep_reward: 13.0, ep_step: 13 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 20, ep_reward: 15.0, ep_step: 15 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 21, ep_reward: 13.0, ep_step: 13 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 22, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 23, ep_reward: 17.0, ep_step: 17 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 24, ep_reward: 21.0, ep_step: 21 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 25, ep_reward: 12.0, ep_step: 12 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 26, ep_reward: 16.0, ep_step: 16 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 27, ep_reward: 13.0, ep_step: 13 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 28, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 29, ep_reward: 12.0, ep_step: 12 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 30, ep_reward: 22.0, ep_step: 22 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 31, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 32, ep_reward: 13.0, ep_step: 13 -2023-05-18 13:37:38 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 10.000 -2023-05-18 13:37:38 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 10.000, save the best model! -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 33, ep_reward: 14.0, ep_step: 14 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 34, ep_reward: 9.0, ep_step: 9 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 35, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 36, ep_reward: 11.0, ep_step: 11 -2023-05-18 13:37:38 - SimpleLog - INFO: - episode: 37, ep_reward: 9.0, ep_step: 9 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 38, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 39, ep_reward: 14.0, ep_step: 14 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 40, ep_reward: 9.0, ep_step: 9 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 41, ep_reward: 11.0, ep_step: 11 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 42, ep_reward: 9.0, ep_step: 9 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 43, ep_reward: 9.0, ep_step: 9 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 44, ep_reward: 15.0, ep_step: 15 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 45, ep_reward: 15.0, ep_step: 15 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 46, ep_reward: 9.0, ep_step: 9 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 47, ep_reward: 11.0, ep_step: 11 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 48, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 49, ep_reward: 9.0, ep_step: 9 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 50, ep_reward: 12.0, ep_step: 12 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 51, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 52, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 53, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 54, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 55, ep_reward: 10.0, ep_step: 10 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 56, ep_reward: 39.0, ep_step: 39 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 57, ep_reward: 17.0, ep_step: 17 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 58, ep_reward: 20.0, ep_step: 20 -2023-05-18 13:37:39 - SimpleLog - INFO: - episode: 59, ep_reward: 21.0, ep_step: 21 -2023-05-18 13:37:40 - SimpleLog - INFO: - episode: 60, ep_reward: 55.0, ep_step: 55 -2023-05-18 13:37:40 - SimpleLog - INFO: - episode: 61, ep_reward: 26.0, ep_step: 26 -2023-05-18 13:37:40 - SimpleLog - INFO: - episode: 62, ep_reward: 29.0, ep_step: 29 -2023-05-18 13:37:40 - SimpleLog - INFO: - episode: 63, ep_reward: 35.0, ep_step: 35 -2023-05-18 13:37:40 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 27.000 -2023-05-18 13:37:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 27.000, save the best model! -2023-05-18 13:37:40 - SimpleLog - INFO: - episode: 64, ep_reward: 27.0, ep_step: 27 -2023-05-18 13:37:40 - SimpleLog - INFO: - episode: 65, ep_reward: 41.0, ep_step: 41 -2023-05-18 13:37:40 - SimpleLog - INFO: - episode: 66, ep_reward: 91.0, ep_step: 91 -2023-05-18 13:37:41 - SimpleLog - INFO: - episode: 67, ep_reward: 71.0, ep_step: 71 -2023-05-18 13:37:41 - SimpleLog - INFO: - episode: 68, ep_reward: 72.0, ep_step: 72 -2023-05-18 13:37:41 - SimpleLog - INFO: - episode: 69, ep_reward: 24.0, ep_step: 24 -2023-05-18 13:37:41 - SimpleLog - INFO: - episode: 70, ep_reward: 50.0, ep_step: 50 -2023-05-18 13:37:41 - SimpleLog - INFO: - episode: 71, ep_reward: 85.0, ep_step: 85 -2023-05-18 13:37:42 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 66.000 -2023-05-18 13:37:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 66.000, save the best model! -2023-05-18 13:37:42 - SimpleLog - INFO: - episode: 72, ep_reward: 183.0, ep_step: 183 -2023-05-18 13:37:42 - SimpleLog - INFO: - episode: 73, ep_reward: 124.0, ep_step: 124 -2023-05-18 13:37:43 - SimpleLog - INFO: - episode: 74, ep_reward: 123.0, ep_step: 123 -2023-05-18 13:37:43 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: 102.000 -2023-05-18 13:37:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 102.000, save the best model! -2023-05-18 13:37:43 - SimpleLog - INFO: - episode: 75, ep_reward: 192.0, ep_step: 192 -2023-05-18 13:37:44 - SimpleLog - INFO: - episode: 76, ep_reward: 115.0, ep_step: 115 -2023-05-18 13:37:44 - SimpleLog - INFO: - episode: 77, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:37:45 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 99.000 -2023-05-18 13:37:45 - SimpleLog - INFO: - episode: 78, ep_reward: 171.0, ep_step: 171 -2023-05-18 13:37:45 - SimpleLog - INFO: - episode: 79, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:37:46 - SimpleLog - INFO: - episode: 80, ep_reward: 125.0, ep_step: 125 -2023-05-18 13:37:46 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: 90.000 -2023-05-18 13:37:46 - SimpleLog - INFO: - episode: 81, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:37:47 - SimpleLog - INFO: - episode: 82, ep_reward: 140.0, ep_step: 140 -2023-05-18 13:37:47 - SimpleLog - INFO: - episode: 83, ep_reward: 172.0, ep_step: 172 -2023-05-18 13:37:48 - SimpleLog - INFO: - episode: 84, ep_reward: 78.0, ep_step: 78 -2023-05-18 13:37:48 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: 82.000 -2023-05-18 13:37:48 - SimpleLog - INFO: - episode: 85, ep_reward: 92.0, ep_step: 92 -2023-05-18 13:37:48 - SimpleLog - INFO: - episode: 86, ep_reward: 104.0, ep_step: 104 -2023-05-18 13:37:49 - SimpleLog - INFO: - episode: 87, ep_reward: 99.0, ep_step: 99 -2023-05-18 13:37:49 - SimpleLog - INFO: - episode: 88, ep_reward: 81.0, ep_step: 81 -2023-05-18 13:37:49 - SimpleLog - INFO: - episode: 89, ep_reward: 97.0, ep_step: 97 -2023-05-18 13:37:49 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: 106.000 -2023-05-18 13:37:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 106.000, save the best model! -2023-05-18 13:37:49 - SimpleLog - INFO: - episode: 90, ep_reward: 99.0, ep_step: 99 -2023-05-18 13:37:50 - SimpleLog - INFO: - episode: 91, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:37:50 - SimpleLog - INFO: - episode: 92, ep_reward: 93.0, ep_step: 93 -2023-05-18 13:37:51 - SimpleLog - INFO: - episode: 93, ep_reward: 127.0, ep_step: 127 -2023-05-18 13:37:51 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: 200.000 -2023-05-18 13:37:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! -2023-05-18 13:37:51 - SimpleLog - INFO: - episode: 94, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:37:52 - SimpleLog - INFO: - episode: 95, ep_reward: 145.0, ep_step: 145 -2023-05-18 13:37:53 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: 200.000 -2023-05-18 13:37:53 - SimpleLog - INFO: - episode: 96, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:37:53 - SimpleLog - INFO: - episode: 97, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:37:54 - SimpleLog - INFO: - episode: 98, ep_reward: 168.0, ep_step: 168 -2023-05-18 13:37:54 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: 200.000 -2023-05-18 13:37:55 - SimpleLog - INFO: - episode: 99, ep_reward: 200.0, ep_step: 200 -2023-05-18 13:37:55 - SimpleLog - INFO: - Finish training! total time consumed: 17.76s diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/1000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/1000 deleted file mode 100644 index a00854259473db0232c28f5034fdb693693f2c98..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/1000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/1500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/1500 deleted file mode 100644 index e47105cd78b3aae8108c4489e5a6ffa42c62cff6..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/1500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/2000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/2000 deleted file mode 100644 index 8117923d0ce025d142f1c92f2618017e77afefc6..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/2000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/2500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/2500 deleted file mode 100644 index cfd02b8c034e52278b98eedcff3d8a163742e9d2..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/2500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/3000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/3000 deleted file mode 100644 index bb96a281b667bd68b14379bfb53d67815e6cbc82..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/3000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/3500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/3500 deleted file mode 100644 index dac226b686bab871a2d3cd74ac2b117339b87470..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/3500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/4000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/4000 deleted file mode 100644 index 5d56258c54214abe346018c54630fae29bccfd97..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/4000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/4500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/4500 deleted file mode 100644 index 256385d9a14af6907e8d4f9357a38474bc084476..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/4500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/500 deleted file mode 100644 index e0229aa8dd73defe3331a33c26d2f6f118c5139b..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/5000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/5000 deleted file mode 100644 index 9e92d6344ad25415bfd91e4d2999aba9697742e7..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/5000 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/5500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/5500 deleted file mode 100644 index f7467f4ae4a76e74964283bd11a432ade2eb067c..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/5500 and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/best b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/best deleted file mode 100644 index 256385d9a14af6907e8d4f9357a38474bc084476..0000000000000000000000000000000000000000 Binary files a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/models/best and /dev/null differ diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/tb_logs/interact/events.out.tfevents.1684388257.JMac.local.86406.0 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/tb_logs/interact/events.out.tfevents.1684388257.JMac.local.86406.0 deleted file mode 100644 index cf124daffd873d7c796bd43c0f2719882536ab1e..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/tb_logs/interact/events.out.tfevents.1684388257.JMac.local.86406.0 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a11e5bd8547e9f08ec39d9101d864b0c14b56d98b9f5599088f630547c6ef2a9 -size 10436 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/tb_logs/model/events.out.tfevents.1684388257.JMac.local.86406.1 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/tb_logs/model/events.out.tfevents.1684388257.JMac.local.86406.1 deleted file mode 100644 index 172c6199d6af643d1ca5829e7eda51e10d2a66c2..0000000000000000000000000000000000000000 --- a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-133737/tb_logs/model/events.out.tfevents.1684388257.JMac.local.86406.1 +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4e0d109f0247d75bc2227d6d1e7141259fe5312d79d5a5002b4705cddd707059 -size 272941 diff --git a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/config.yaml b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/config.yaml similarity index 93% rename from ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/config.yaml rename to ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/config.yaml index 960b350d3388aeafb57bb6a9f610ccfcb3c519aa..ff3ae60c209acf55c35b06f42a4d8aed3ee50ab6 100644 --- a/ClassControl/CartPole-v1/Test_single_CartPole-v1_NoisyDQN_20230518-133824/config.yaml +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/config.yaml @@ -3,12 +3,12 @@ general_cfg: collect_traj: false device: cpu env_name: gym - load_checkpoint: true + load_checkpoint: false load_model_step: best load_path: Train_single_CartPole-v1_NoisyDQN_20230518-133737 - max_episode: 10 + max_episode: 100 max_step: 200 - mode: test + mode: train model_save_fre: 500 mp_backend: single n_learners: 1 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/logs/log.txt b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..6c6774375970d22966106f0c9f0d5a6e921589f9 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/logs/log.txt @@ -0,0 +1,176 @@ +2023-05-18 17:32:42 - SimpleLog - INFO: - General Configs: +2023-05-18 17:32:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:32:42 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:32:42 - SimpleLog - INFO: - env_name gym +2023-05-18 17:32:42 - SimpleLog - INFO: - algo_name NoisyDQN +2023-05-18 17:32:42 - SimpleLog - INFO: - mode train +2023-05-18 17:32:42 - SimpleLog - INFO: - device cpu +2023-05-18 17:32:42 - SimpleLog - INFO: - seed 1 +2023-05-18 17:32:42 - SimpleLog - INFO: - max_episode 100 +2023-05-18 17:32:42 - SimpleLog - INFO: - max_step 200 +2023-05-18 17:32:42 - SimpleLog - INFO: - collect_traj 0 +2023-05-18 17:32:42 - SimpleLog - INFO: - mp_backend single +2023-05-18 17:32:42 - SimpleLog - INFO: - n_workers 2 +2023-05-18 17:32:42 - SimpleLog - INFO: - n_learners 1 +2023-05-18 17:32:42 - SimpleLog - INFO: - share_buffer 1 +2023-05-18 17:32:42 - SimpleLog - INFO: - online_eval 1 +2023-05-18 17:32:42 - SimpleLog - INFO: - online_eval_episode 10 +2023-05-18 17:32:42 - SimpleLog - INFO: - model_save_fre 500 +2023-05-18 17:32:42 - SimpleLog - INFO: - load_checkpoint 0 +2023-05-18 17:32:42 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_NoisyDQN_20230518-133737 +2023-05-18 17:32:42 - SimpleLog - INFO: - load_model_step best +2023-05-18 17:32:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:32:42 - SimpleLog - INFO: - Algo Configs: +2023-05-18 17:32:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:32:42 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:32:42 - SimpleLog - INFO: - epsilon_start 0.95 +2023-05-18 17:32:42 - SimpleLog - INFO: - epsilon_end 0.01 +2023-05-18 17:32:42 - SimpleLog - INFO: - epsilon_decay 500 +2023-05-18 17:32:42 - SimpleLog - INFO: - gamma 0.99 +2023-05-18 17:32:42 - SimpleLog - INFO: - lr 0.0001 +2023-05-18 17:32:42 - SimpleLog - INFO: - buffer_size 100000 +2023-05-18 17:32:42 - SimpleLog - INFO: - batch_size 64 +2023-05-18 17:32:42 - SimpleLog - INFO: - target_update 4 +2023-05-18 17:32:42 - SimpleLog - INFO: - value_layers [{'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}, {'layer_type': 'noisy_linear', 'layer_size': [256], 'activation': 'relu', 'std_init': 0.4}] +2023-05-18 17:32:42 - SimpleLog - INFO: - buffer_type REPLAY_QUE +2023-05-18 17:32:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:32:42 - SimpleLog - INFO: - Env Configs: +2023-05-18 17:32:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:32:42 - SimpleLog - INFO: - Name Value Type +2023-05-18 17:32:42 - SimpleLog - INFO: - id CartPole-v1 +2023-05-18 17:32:42 - SimpleLog - INFO: - render_mode None +2023-05-18 17:32:42 - SimpleLog - INFO: - wrapper None +2023-05-18 17:32:42 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-18 17:32:42 - SimpleLog - INFO: - ================================================================================ +2023-05-18 17:32:42 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2) +2023-05-18 17:32:42 - SimpleLog - INFO: - Start training! +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 0, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 1, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 2, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 3, ep_reward: 18.0, ep_step: 18 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 4, ep_reward: 36.0, ep_step: 36 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 5, ep_reward: 12.0, ep_step: 12 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 6, ep_reward: 13.0, ep_step: 13 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 7, ep_reward: 13.0, ep_step: 13 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 8, ep_reward: 16.0, ep_step: 16 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 9, ep_reward: 11.0, ep_step: 11 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 10, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:42 - SimpleLog - INFO: - episode: 11, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 12, ep_reward: 22.0, ep_step: 22 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 13, ep_reward: 18.0, ep_step: 18 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 14, ep_reward: 20.0, ep_step: 20 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 15, ep_reward: 11.0, ep_step: 11 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 16, ep_reward: 13.0, ep_step: 13 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 17, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 18, ep_reward: 9.0, ep_step: 9 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 19, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 20, ep_reward: 11.0, ep_step: 11 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 21, ep_reward: 17.0, ep_step: 17 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 22, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 23, ep_reward: 25.0, ep_step: 25 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 24, ep_reward: 11.0, ep_step: 11 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 25, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:43 - SimpleLog - INFO: - episode: 26, ep_reward: 12.0, ep_step: 12 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 27, ep_reward: 22.0, ep_step: 22 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 28, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 29, ep_reward: 15.0, ep_step: 15 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 30, ep_reward: 10.0, ep_step: 10 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 31, ep_reward: 11.0, ep_step: 11 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 32, ep_reward: 13.0, ep_step: 13 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 33, ep_reward: 15.0, ep_step: 15 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 34, ep_reward: 16.0, ep_step: 16 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 35, ep_reward: 13.0, ep_step: 13 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 36, ep_reward: 13.0, ep_step: 13 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 37, ep_reward: 20.0, ep_step: 20 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 38, ep_reward: 11.0, ep_step: 11 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 39, ep_reward: 12.0, ep_step: 12 +2023-05-18 17:32:44 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 10.000 +2023-05-18 17:32:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 10.000, save the best model! +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 40, ep_reward: 12.0, ep_step: 12 +2023-05-18 17:32:44 - SimpleLog - INFO: - episode: 41, ep_reward: 12.0, ep_step: 12 +2023-05-18 17:32:45 - SimpleLog - INFO: - episode: 42, ep_reward: 11.0, ep_step: 11 +2023-05-18 17:32:45 - SimpleLog - INFO: - episode: 43, ep_reward: 11.0, ep_step: 11 +2023-05-18 17:32:45 - SimpleLog - INFO: - episode: 44, ep_reward: 19.0, ep_step: 19 +2023-05-18 17:32:45 - SimpleLog - INFO: - episode: 45, ep_reward: 21.0, ep_step: 21 +2023-05-18 17:32:45 - SimpleLog - INFO: - episode: 46, ep_reward: 24.0, ep_step: 24 +2023-05-18 17:32:45 - SimpleLog - INFO: - episode: 47, ep_reward: 15.0, ep_step: 15 +2023-05-18 17:32:45 - SimpleLog - INFO: - episode: 48, ep_reward: 74.0, ep_step: 74 +2023-05-18 17:32:46 - SimpleLog - INFO: - episode: 49, ep_reward: 37.0, ep_step: 37 +2023-05-18 17:32:46 - SimpleLog - INFO: - episode: 50, ep_reward: 29.0, ep_step: 29 +2023-05-18 17:32:46 - SimpleLog - INFO: - episode: 51, ep_reward: 51.0, ep_step: 51 +2023-05-18 17:32:46 - SimpleLog - INFO: - episode: 52, ep_reward: 62.0, ep_step: 62 +2023-05-18 17:32:47 - SimpleLog - INFO: - episode: 53, ep_reward: 75.0, ep_step: 75 +2023-05-18 17:32:47 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 48.000 +2023-05-18 17:32:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 48.000, save the best model! +2023-05-18 17:32:48 - SimpleLog - INFO: - episode: 54, ep_reward: 150.0, ep_step: 150 +2023-05-18 17:32:48 - SimpleLog - INFO: - episode: 55, ep_reward: 118.0, ep_step: 118 +2023-05-18 17:32:49 - SimpleLog - INFO: - episode: 56, ep_reward: 154.0, ep_step: 154 +2023-05-18 17:32:50 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 125.000 +2023-05-18 17:32:50 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 125.000, save the best model! +2023-05-18 17:32:50 - SimpleLog - INFO: - episode: 57, ep_reward: 157.0, ep_step: 157 +2023-05-18 17:32:51 - SimpleLog - INFO: - episode: 58, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:32:51 - SimpleLog - INFO: - episode: 59, ep_reward: 98.0, ep_step: 98 +2023-05-18 17:32:52 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: 146.000 +2023-05-18 17:32:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 146.000, save the best model! +2023-05-18 17:32:52 - SimpleLog - INFO: - episode: 60, ep_reward: 175.0, ep_step: 175 +2023-05-18 17:32:53 - SimpleLog - INFO: - episode: 61, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:32:54 - SimpleLog - INFO: - episode: 62, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:32:55 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 200.000 +2023-05-18 17:32:55 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:32:55 - SimpleLog - INFO: - episode: 63, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:32:56 - SimpleLog - INFO: - episode: 64, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:32:58 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: 200.000 +2023-05-18 17:32:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:32:58 - SimpleLog - INFO: - episode: 65, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:32:59 - SimpleLog - INFO: - episode: 66, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:00 - SimpleLog - INFO: - episode: 67, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:01 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: 200.000 +2023-05-18 17:33:01 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:33:01 - SimpleLog - INFO: - episode: 68, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:02 - SimpleLog - INFO: - episode: 69, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:03 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: 200.000 +2023-05-18 17:33:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:33:03 - SimpleLog - INFO: - episode: 70, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:04 - SimpleLog - INFO: - episode: 71, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:05 - SimpleLog - INFO: - episode: 72, ep_reward: 118.0, ep_step: 118 +2023-05-18 17:33:06 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: 108.000 +2023-05-18 17:33:06 - SimpleLog - INFO: - episode: 73, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:07 - SimpleLog - INFO: - episode: 74, ep_reward: 120.0, ep_step: 120 +2023-05-18 17:33:07 - SimpleLog - INFO: - episode: 75, ep_reward: 99.0, ep_step: 99 +2023-05-18 17:33:08 - SimpleLog - INFO: - episode: 76, ep_reward: 100.0, ep_step: 100 +2023-05-18 17:33:08 - SimpleLog - INFO: - episode: 77, ep_reward: 94.0, ep_step: 94 +2023-05-18 17:33:09 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: 99.000 +2023-05-18 17:33:09 - SimpleLog - INFO: - episode: 78, ep_reward: 183.0, ep_step: 183 +2023-05-18 17:33:10 - SimpleLog - INFO: - episode: 79, ep_reward: 81.0, ep_step: 81 +2023-05-18 17:33:10 - SimpleLog - INFO: - episode: 80, ep_reward: 96.0, ep_step: 96 +2023-05-18 17:33:11 - SimpleLog - INFO: - episode: 81, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:12 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: 200.000 +2023-05-18 17:33:12 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:33:12 - SimpleLog - INFO: - episode: 82, ep_reward: 125.0, ep_step: 125 +2023-05-18 17:33:13 - SimpleLog - INFO: - episode: 83, ep_reward: 101.0, ep_step: 101 +2023-05-18 17:33:13 - SimpleLog - INFO: - episode: 84, ep_reward: 72.0, ep_step: 72 +2023-05-18 17:33:14 - SimpleLog - INFO: - episode: 85, ep_reward: 65.0, ep_step: 65 +2023-05-18 17:33:14 - SimpleLog - INFO: - episode: 86, ep_reward: 82.0, ep_step: 82 +2023-05-18 17:33:15 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: 92.000 +2023-05-18 17:33:15 - SimpleLog - INFO: - episode: 87, ep_reward: 97.0, ep_step: 97 +2023-05-18 17:33:16 - SimpleLog - INFO: - episode: 88, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:17 - SimpleLog - INFO: - episode: 89, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:18 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: 200.000 +2023-05-18 17:33:18 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:33:18 - SimpleLog - INFO: - episode: 90, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:19 - SimpleLog - INFO: - episode: 91, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:21 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: 200.000 +2023-05-18 17:33:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:33:21 - SimpleLog - INFO: - episode: 92, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:22 - SimpleLog - INFO: - episode: 93, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:23 - SimpleLog - INFO: - episode: 94, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:24 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: 200.000 +2023-05-18 17:33:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:33:24 - SimpleLog - INFO: - episode: 95, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:26 - SimpleLog - INFO: - episode: 96, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:27 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: 200.000 +2023-05-18 17:33:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model! +2023-05-18 17:33:27 - SimpleLog - INFO: - episode: 97, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:28 - SimpleLog - INFO: - episode: 98, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:29 - SimpleLog - INFO: - episode: 99, ep_reward: 200.0, ep_step: 200 +2023-05-18 17:33:29 - SimpleLog - INFO: - Finish training! total time consumed: 47.23s diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/1000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/1000 new file mode 100644 index 0000000000000000000000000000000000000000..30bd742a8a58313f81a0b51e152a662bddf4db2e --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/1000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8caede3c42d7e4014482b1695e0390d4f1c5ce1f513bae655393185c0783e8dc +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/1500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/1500 new file mode 100644 index 0000000000000000000000000000000000000000..701cebd524db215f93e512cf4286d919faa15169 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/1500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfaf941fb4faf6de620c972a136ce2c18ef26449560bee28062f1ca5312a67ce +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/2000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/2000 new file mode 100644 index 0000000000000000000000000000000000000000..d48591088569a9b0846294d1c18f254be8e30bfa --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/2000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f60918cc7da801b27183d672557820cd493c21272c66d27d7e0d115678b2698 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/2500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/2500 new file mode 100644 index 0000000000000000000000000000000000000000..d6465b66333fbee7512d4b29d3e8c0454b4ec741 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/2500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce9c337bf9070e2cb58e57457fe23a1f4ab2bb942ebee4d04b885bd458436d75 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/3000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/3000 new file mode 100644 index 0000000000000000000000000000000000000000..47419d3714e78e882e6d82a1319932ba5b095c6b --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/3000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d089219a9c922eff974da61514b69a7ba863cd133982210d259772df11b7d0 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/3500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/3500 new file mode 100644 index 0000000000000000000000000000000000000000..5d1afddf0e573211c962facb07b7e7d90f8ea2c8 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/3500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46497188ac3c64658cdd78212b7f77ad4a43af97bb5908f623cc970ecb1fcc8e +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/4000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/4000 new file mode 100644 index 0000000000000000000000000000000000000000..9d16632b07d140dfb582c08df1b4d72594f8598f --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/4000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7da2cd71fbe34106ab6513e2b057d77f762ebf48da85ff5d05f77ca6dbe474a +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/4500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/4500 new file mode 100644 index 0000000000000000000000000000000000000000..32ea10df143c3f21c815c3aab4ddd9312efb08c5 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/4500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4970d162ebc53515c37b7b3ca728fa739ffc6d52aa6726c0f5c2d3f583b6be46 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/500 new file mode 100644 index 0000000000000000000000000000000000000000..b86828876027b2e987ee5c0f7e536863b82fc0a9 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c24ac3441a879351c35f59e50a76a3ac80b5718a6f3ffb2bc587c30f285628 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/5000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/5000 new file mode 100644 index 0000000000000000000000000000000000000000..90e8dccef93f019952f9f186deaaf9115c2e6537 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/5000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0966cfbfd016c15cfd8772c66ed195ed081d4dede5663230fa6f36599fa925fa +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/5500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/5500 new file mode 100644 index 0000000000000000000000000000000000000000..39a8ba1f643e517fa60db7491e349a83e27fc767 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/5500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca80656b6fe48d11b0aa4991c37dc4f6488856a372a19d8a20ef766ce5c2b2fe +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/6000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/6000 new file mode 100644 index 0000000000000000000000000000000000000000..137dca53e7fa56dcfa0a4f0831d828ec510ba949 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/6000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:883e018a1367e8800ea47e3b1d25274f3184b45332d713014a16a4876fe51f9e +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/6500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/6500 new file mode 100644 index 0000000000000000000000000000000000000000..f525a84a8fab516a475f78af2efa88b8d1930554 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/6500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd2f75bef055194c8edd72d3c698171ad5645f85cfa967f12ef9f35f19b6bf7 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/7000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/7000 new file mode 100644 index 0000000000000000000000000000000000000000..b0e6d27219de4b4a3ae879e91690b5c887e0fa82 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/7000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58dce3ae8cfcba12286dc5741dc792b49b00cc01730d81b86cbbbc10bb32f0e5 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/7500 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/7500 new file mode 100644 index 0000000000000000000000000000000000000000..d8fdb159ca40e05664791c39efc669e542b627c6 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/7500 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107baff9818221ac00571e8db25f8e413cdefba46bfe28cbe98f7b2c020907b4 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/8000 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/8000 new file mode 100644 index 0000000000000000000000000000000000000000..2efa4ca946aca82c4326a53b53ae150ec9333e27 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/8000 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc3b4f4a5950136ec053817364479f4a72096ae5c070cdbf7b7eeb86ecd5678 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/best b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/best new file mode 100644 index 0000000000000000000000000000000000000000..2efa4ca946aca82c4326a53b53ae150ec9333e27 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/models/best @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc3b4f4a5950136ec053817364479f4a72096ae5c070cdbf7b7eeb86ecd5678 +size 1622673 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/tb_logs/interact/events.out.tfevents.1684402362.JMac.local.92711.0 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/tb_logs/interact/events.out.tfevents.1684402362.JMac.local.92711.0 new file mode 100644 index 0000000000000000000000000000000000000000..eb950035fd676d027617de2426959d8c305d74f1 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/tb_logs/interact/events.out.tfevents.1684402362.JMac.local.92711.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7fe1c86f4e2cfda6be24fa55e0793f44f255540f58211e10355b82886e9438 +size 10436 diff --git a/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/tb_logs/model/events.out.tfevents.1684402362.JMac.local.92711.1 b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/tb_logs/model/events.out.tfevents.1684402362.JMac.local.92711.1 new file mode 100644 index 0000000000000000000000000000000000000000..4d8ba4b12ede5a83e5a2ec8690c201663b690a93 --- /dev/null +++ b/ClassControl/CartPole-v1/Train_single_CartPole-v1_NoisyDQN_20230518-173242/tb_logs/model/events.out.tfevents.1684402362.JMac.local.92711.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e642ee664be88476d88aae9b5b44924c939443779667ddf08405210823b7e89 +size 413179