diff --git a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/config.yaml b/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/config.yaml deleted file mode 100644 index 0579a96367861a1ecbc06ec72861a9ea60a66edd..0000000000000000000000000000000000000000 --- a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/config.yaml +++ /dev/null @@ -1,24 +0,0 @@ -general_cfg: - algo_name: QLearning - device: cpu - env_name: CliffWalking-v0 - eval_eps: 10 - eval_per_episode: 5 - load_checkpoint: true - load_path: Train_CliffWalking-v0_QLearning_20221128-144520 - max_steps: 100 - mode: test - new_step_api: true - render: true - save_fig: true - seed: 1 - show_fig: false - test_eps: 10 - train_eps: 300 - wrapper: envs.wrappers.CliffWalkingWapper -algo_cfg: - epsilon_decay: 300 - epsilon_end: 0.01 - epsilon_start: 0.95 - gamma: 0.99 - lr: 0.1 diff --git a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/logs/log.txt b/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/logs/log.txt deleted file mode 100644 index 4a7968b9e5d088b7998840f204da58d2afe612c7..0000000000000000000000000000000000000000 --- a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/logs/log.txt +++ /dev/null @@ -1,14 +0,0 @@ -2022-11-28 15:05:39 - r - INFO: - n_states: 48, n_actions: 4 -2022-11-28 15:05:39 - r - INFO: - Start testing! -2022-11-28 15:05:39 - r - INFO: - Env: CliffWalking-v0, Algorithm: QLearning, Device: cpu -2022-11-28 15:05:44 - r - INFO: - Episode: 1/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:45 - r - INFO: - Episode: 2/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:45 - r - INFO: - Episode: 3/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:46 - r - INFO: - Episode: 4/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:46 - r - INFO: - Episode: 5/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:46 - r - INFO: - Episode: 6/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:47 - r - INFO: - Episode: 7/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:47 - r - INFO: - Episode: 8/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:48 - r - INFO: - Episode: 9/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:48 - r - INFO: - Episode: 10/10, Reward: -13.000, Step: 13 -2022-11-28 15:05:48 - r - INFO: - Finish testing! diff --git a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/models/Qleaning_model.pkl b/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/models/Qleaning_model.pkl deleted file mode 100644 index 11b3246418fe8e689ff25f81da33205b94378416..0000000000000000000000000000000000000000 --- a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/models/Qleaning_model.pkl +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0a5088e21ba086ef3631d0381b7b57ec20f56261d403a159a6c8d0cae3d6ec63 -size 5999 diff --git a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/results/learning_curve.png b/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/results/learning_curve.png deleted file mode 100644 index c565c2a416cfb9116b0b3200fb6d0a5617472d76..0000000000000000000000000000000000000000 Binary files a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/results/learning_curve.png and /dev/null differ diff --git a/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/res.csv b/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/res.csv deleted file mode 100644 index 2d69fb8e7ddf3a69ca3e85cbc39fd580d2160ba5..0000000000000000000000000000000000000000 --- a/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/res.csv +++ /dev/null @@ -1,11 +0,0 @@ -episodes,rewards,steps -0,-13,13 -1,-13,13 -2,-13,13 -3,-13,13 -4,-13,13 -5,-13,13 -6,-13,13 -7,-13,13 -8,-13,13 -9,-13,13 diff --git a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/config.yaml b/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/config.yaml deleted file mode 100644 index aea7ad063e6aedffd91853a1dcc659229e6ec15e..0000000000000000000000000000000000000000 --- a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/config.yaml +++ /dev/null @@ -1,23 +0,0 @@ -general_cfg: - algo_name: QLearning - device: cpu - env_name: CliffWalking-v0 - eval_eps: 10 - eval_per_episode: 5 - load_checkpoint: false - load_path: Train_CartPole-v1_DQN_20221026-054757 - max_steps: 100 - mode: train - new_step_api: true - save_fig: true - seed: 1 - show_fig: false - test_eps: 10 - train_eps: 300 - wrapper: envs.wrappers.CliffWalkingWapper -algo_cfg: - epsilon_decay: 300 - epsilon_end: 0.01 - epsilon_start: 0.95 - gamma: 0.99 - lr: 0.1 diff --git a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/logs/log.txt b/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/logs/log.txt deleted file mode 100644 index b7991b770c307671d75d96851aba9c27779f1dfa..0000000000000000000000000000000000000000 --- a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/logs/log.txt +++ /dev/null @@ -1,342 +0,0 @@ -2022-11-28 14:45:22 - r - INFO: - n_states: 48, n_actions: 4 -2022-11-28 14:45:22 - r - INFO: - Start training! -2022-11-28 14:45:22 - r - INFO: - Env: CliffWalking-v0, Algorithm: QLearning, Device: cpu -2022-11-28 14:45:22 - r - INFO: - Episode: 1/300, Reward: -397.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 2/300, Reward: -1090.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 3/300, Reward: -694.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 4/300, Reward: -397.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 5/300, Reward: -496.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Current episode 5 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 6/300, Reward: -298.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 7/300, Reward: -199.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 8/300, Reward: -298.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 9/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 10/300, Reward: -199.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Current episode 10 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 11/300, Reward: -93.000, Step: 93 -2022-11-28 14:45:22 - r - INFO: - Episode: 12/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 13/300, Reward: -199.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 14/300, Reward: -199.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 15/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Current episode 15 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 16/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 17/300, Reward: -33.000, Step: 33 -2022-11-28 14:45:22 - r - INFO: - Episode: 18/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 19/300, Reward: -66.000, Step: 66 -2022-11-28 14:45:22 - r - INFO: - Episode: 20/300, Reward: -99.000, Step: 99 -2022-11-28 14:45:22 - r - INFO: - Current episode 20 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 21/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 22/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 23/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 24/300, Reward: -54.000, Step: 54 -2022-11-28 14:45:22 - r - INFO: - Episode: 25/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Current episode 25 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 26/300, Reward: -73.000, Step: 73 -2022-11-28 14:45:22 - r - INFO: - Episode: 27/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 28/300, Reward: -90.000, Step: 90 -2022-11-28 14:45:22 - r - INFO: - Episode: 29/300, Reward: -87.000, Step: 87 -2022-11-28 14:45:22 - r - INFO: - Episode: 30/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Current episode 30 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 31/300, Reward: -46.000, Step: 46 -2022-11-28 14:45:22 - r - INFO: - Episode: 32/300, Reward: -82.000, Step: 82 -2022-11-28 14:45:22 - r - INFO: - Episode: 33/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 34/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 35/300, Reward: -67.000, Step: 67 -2022-11-28 14:45:22 - r - INFO: - Current episode 35 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 36/300, Reward: -75.000, Step: 75 -2022-11-28 14:45:22 - r - INFO: - Episode: 37/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 38/300, Reward: -45.000, Step: 45 -2022-11-28 14:45:22 - r - INFO: - Episode: 39/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 40/300, Reward: -37.000, Step: 37 -2022-11-28 14:45:22 - r - INFO: - Current episode 40 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 41/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 42/300, Reward: -43.000, Step: 43 -2022-11-28 14:45:22 - r - INFO: - Episode: 43/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 44/300, Reward: -56.000, Step: 56 -2022-11-28 14:45:22 - r - INFO: - Episode: 45/300, Reward: -70.000, Step: 70 -2022-11-28 14:45:22 - r - INFO: - Current episode 45 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 46/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 47/300, Reward: -47.000, Step: 47 -2022-11-28 14:45:22 - r - INFO: - Episode: 48/300, Reward: -85.000, Step: 85 -2022-11-28 14:45:22 - r - INFO: - Episode: 49/300, Reward: -82.000, Step: 82 -2022-11-28 14:45:22 - r - INFO: - Episode: 50/300, Reward: -51.000, Step: 51 -2022-11-28 14:45:22 - r - INFO: - Current episode 50 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 51/300, Reward: -50.000, Step: 50 -2022-11-28 14:45:22 - r - INFO: - Episode: 52/300, Reward: -86.000, Step: 86 -2022-11-28 14:45:22 - r - INFO: - Episode: 53/300, Reward: -100.000, Step: 100 -2022-11-28 14:45:22 - r - INFO: - Episode: 54/300, Reward: -40.000, Step: 40 -2022-11-28 14:45:22 - r - INFO: - Episode: 55/300, Reward: -87.000, Step: 87 -2022-11-28 14:45:22 - r - INFO: - Current episode 55 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 56/300, Reward: -59.000, Step: 59 -2022-11-28 14:45:22 - r - INFO: - Episode: 57/300, Reward: -51.000, Step: 51 -2022-11-28 14:45:22 - r - INFO: - Episode: 58/300, Reward: -98.000, Step: 98 -2022-11-28 14:45:22 - r - INFO: - Episode: 59/300, Reward: -67.000, Step: 67 -2022-11-28 14:45:22 - r - INFO: - Episode: 60/300, Reward: -60.000, Step: 60 -2022-11-28 14:45:22 - r - INFO: - Current episode 60 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 61/300, Reward: -38.000, Step: 38 -2022-11-28 14:45:22 - r - INFO: - Episode: 62/300, Reward: -76.000, Step: 76 -2022-11-28 14:45:22 - r - INFO: - Episode: 63/300, Reward: -70.000, Step: 70 -2022-11-28 14:45:22 - r - INFO: - Episode: 64/300, Reward: -60.000, Step: 60 -2022-11-28 14:45:22 - r - INFO: - Episode: 65/300, Reward: -68.000, Step: 68 -2022-11-28 14:45:22 - r - INFO: - Current episode 65 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 66/300, Reward: -25.000, Step: 25 -2022-11-28 14:45:22 - r - INFO: - Episode: 67/300, Reward: -69.000, Step: 69 -2022-11-28 14:45:22 - r - INFO: - Episode: 68/300, Reward: -183.000, Step: 84 -2022-11-28 14:45:22 - r - INFO: - Episode: 69/300, Reward: -62.000, Step: 62 -2022-11-28 14:45:22 - r - INFO: - Episode: 70/300, Reward: -44.000, Step: 44 -2022-11-28 14:45:22 - r - INFO: - Current episode 70 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 71/300, Reward: -71.000, Step: 71 -2022-11-28 14:45:22 - r - INFO: - Episode: 72/300, Reward: -55.000, Step: 55 -2022-11-28 14:45:22 - r - INFO: - Episode: 73/300, Reward: -65.000, Step: 65 -2022-11-28 14:45:22 - r - INFO: - Episode: 74/300, Reward: -61.000, Step: 61 -2022-11-28 14:45:22 - r - INFO: - Episode: 75/300, Reward: -36.000, Step: 36 -2022-11-28 14:45:22 - r - INFO: - Current episode 75 has the best eval reward: -100.000 -2022-11-28 14:45:22 - r - INFO: - Episode: 76/300, Reward: -47.000, Step: 47 -2022-11-28 14:45:22 - r - INFO: - Episode: 77/300, Reward: -63.000, Step: 63 -2022-11-28 14:45:22 - r - INFO: - Episode: 78/300, Reward: -45.000, Step: 45 -2022-11-28 14:45:22 - r - INFO: - Episode: 79/300, Reward: -59.000, Step: 59 -2022-11-28 14:45:22 - r - INFO: - Episode: 80/300, Reward: -39.000, Step: 39 -2022-11-28 14:45:23 - r - INFO: - Current episode 80 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 81/300, Reward: -62.000, Step: 62 -2022-11-28 14:45:23 - r - INFO: - Episode: 82/300, Reward: -38.000, Step: 38 -2022-11-28 14:45:23 - r - INFO: - Episode: 83/300, Reward: -64.000, Step: 64 -2022-11-28 14:45:23 - r - INFO: - Episode: 84/300, Reward: -40.000, Step: 40 -2022-11-28 14:45:23 - r - INFO: - Episode: 85/300, Reward: -59.000, Step: 59 -2022-11-28 14:45:23 - r - INFO: - Current episode 85 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 86/300, Reward: -48.000, Step: 48 -2022-11-28 14:45:23 - r - INFO: - Episode: 87/300, Reward: -39.000, Step: 39 -2022-11-28 14:45:23 - r - INFO: - Episode: 88/300, Reward: -70.000, Step: 70 -2022-11-28 14:45:23 - r - INFO: - Episode: 89/300, Reward: -34.000, Step: 34 -2022-11-28 14:45:23 - r - INFO: - Episode: 90/300, Reward: -40.000, Step: 40 -2022-11-28 14:45:23 - r - INFO: - Current episode 90 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 91/300, Reward: -27.000, Step: 27 -2022-11-28 14:45:23 - r - INFO: - Episode: 92/300, Reward: -65.000, Step: 65 -2022-11-28 14:45:23 - r - INFO: - Episode: 93/300, Reward: -79.000, Step: 79 -2022-11-28 14:45:23 - r - INFO: - Episode: 94/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Episode: 95/300, Reward: -38.000, Step: 38 -2022-11-28 14:45:23 - r - INFO: - Current episode 95 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 96/300, Reward: -23.000, Step: 23 -2022-11-28 14:45:23 - r - INFO: - Episode: 97/300, Reward: -60.000, Step: 60 -2022-11-28 14:45:23 - r - INFO: - Episode: 98/300, Reward: -41.000, Step: 41 -2022-11-28 14:45:23 - r - INFO: - Episode: 99/300, Reward: -39.000, Step: 39 -2022-11-28 14:45:23 - r - INFO: - Episode: 100/300, Reward: -42.000, Step: 42 -2022-11-28 14:45:23 - r - INFO: - Current episode 100 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 101/300, Reward: -41.000, Step: 41 -2022-11-28 14:45:23 - r - INFO: - Episode: 102/300, Reward: -59.000, Step: 59 -2022-11-28 14:45:23 - r - INFO: - Episode: 103/300, Reward: -31.000, Step: 31 -2022-11-28 14:45:23 - r - INFO: - Episode: 104/300, Reward: -43.000, Step: 43 -2022-11-28 14:45:23 - r - INFO: - Episode: 105/300, Reward: -70.000, Step: 70 -2022-11-28 14:45:23 - r - INFO: - Current episode 105 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 106/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 107/300, Reward: -161.000, Step: 62 -2022-11-28 14:45:23 - r - INFO: - Episode: 108/300, Reward: -38.000, Step: 38 -2022-11-28 14:45:23 - r - INFO: - Episode: 109/300, Reward: -45.000, Step: 45 -2022-11-28 14:45:23 - r - INFO: - Episode: 110/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Current episode 110 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 111/300, Reward: -47.000, Step: 47 -2022-11-28 14:45:23 - r - INFO: - Episode: 112/300, Reward: -23.000, Step: 23 -2022-11-28 14:45:23 - r - INFO: - Episode: 113/300, Reward: -62.000, Step: 62 -2022-11-28 14:45:23 - r - INFO: - Episode: 114/300, Reward: -34.000, Step: 34 -2022-11-28 14:45:23 - r - INFO: - Episode: 115/300, Reward: -46.000, Step: 46 -2022-11-28 14:45:23 - r - INFO: - Current episode 115 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 116/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 117/300, Reward: -46.000, Step: 46 -2022-11-28 14:45:23 - r - INFO: - Episode: 118/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Episode: 119/300, Reward: -24.000, Step: 24 -2022-11-28 14:45:23 - r - INFO: - Episode: 120/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Current episode 120 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 121/300, Reward: -42.000, Step: 42 -2022-11-28 14:45:23 - r - INFO: - Episode: 122/300, Reward: -62.000, Step: 62 -2022-11-28 14:45:23 - r - INFO: - Episode: 123/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Episode: 124/300, Reward: -31.000, Step: 31 -2022-11-28 14:45:23 - r - INFO: - Episode: 125/300, Reward: -37.000, Step: 37 -2022-11-28 14:45:23 - r - INFO: - Current episode 125 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 126/300, Reward: -51.000, Step: 51 -2022-11-28 14:45:23 - r - INFO: - Episode: 127/300, Reward: -32.000, Step: 32 -2022-11-28 14:45:23 - r - INFO: - Episode: 128/300, Reward: -22.000, Step: 22 -2022-11-28 14:45:23 - r - INFO: - Episode: 129/300, Reward: -34.000, Step: 34 -2022-11-28 14:45:23 - r - INFO: - Episode: 130/300, Reward: -22.000, Step: 22 -2022-11-28 14:45:23 - r - INFO: - Current episode 130 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 131/300, Reward: -53.000, Step: 53 -2022-11-28 14:45:23 - r - INFO: - Episode: 132/300, Reward: -28.000, Step: 28 -2022-11-28 14:45:23 - r - INFO: - Episode: 133/300, Reward: -33.000, Step: 33 -2022-11-28 14:45:23 - r - INFO: - Episode: 134/300, Reward: -39.000, Step: 39 -2022-11-28 14:45:23 - r - INFO: - Episode: 135/300, Reward: -39.000, Step: 39 -2022-11-28 14:45:23 - r - INFO: - Current episode 135 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 136/300, Reward: -20.000, Step: 20 -2022-11-28 14:45:23 - r - INFO: - Episode: 137/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Episode: 138/300, Reward: -42.000, Step: 42 -2022-11-28 14:45:23 - r - INFO: - Episode: 139/300, Reward: -154.000, Step: 55 -2022-11-28 14:45:23 - r - INFO: - Episode: 140/300, Reward: -34.000, Step: 34 -2022-11-28 14:45:23 - r - INFO: - Current episode 140 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 141/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 142/300, Reward: -21.000, Step: 21 -2022-11-28 14:45:23 - r - INFO: - Episode: 143/300, Reward: -38.000, Step: 38 -2022-11-28 14:45:23 - r - INFO: - Episode: 144/300, Reward: -21.000, Step: 21 -2022-11-28 14:45:23 - r - INFO: - Episode: 145/300, Reward: -46.000, Step: 46 -2022-11-28 14:45:23 - r - INFO: - Current episode 145 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 146/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:23 - r - INFO: - Episode: 147/300, Reward: -37.000, Step: 37 -2022-11-28 14:45:23 - r - INFO: - Episode: 148/300, Reward: -27.000, Step: 27 -2022-11-28 14:45:23 - r - INFO: - Episode: 149/300, Reward: -39.000, Step: 39 -2022-11-28 14:45:23 - r - INFO: - Episode: 150/300, Reward: -18.000, Step: 18 -2022-11-28 14:45:23 - r - INFO: - Current episode 150 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 151/300, Reward: -34.000, Step: 34 -2022-11-28 14:45:23 - r - INFO: - Episode: 152/300, Reward: -25.000, Step: 25 -2022-11-28 14:45:23 - r - INFO: - Episode: 153/300, Reward: -32.000, Step: 32 -2022-11-28 14:45:23 - r - INFO: - Episode: 154/300, Reward: -40.000, Step: 40 -2022-11-28 14:45:23 - r - INFO: - Episode: 155/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Current episode 155 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 156/300, Reward: -36.000, Step: 36 -2022-11-28 14:45:23 - r - INFO: - Episode: 157/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 158/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Episode: 159/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 160/300, Reward: -22.000, Step: 22 -2022-11-28 14:45:23 - r - INFO: - Current episode 160 has the best eval reward: -100.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 161/300, Reward: -18.000, Step: 18 -2022-11-28 14:45:23 - r - INFO: - Episode: 162/300, Reward: -46.000, Step: 46 -2022-11-28 14:45:23 - r - INFO: - Episode: 163/300, Reward: -27.000, Step: 27 -2022-11-28 14:45:23 - r - INFO: - Episode: 164/300, Reward: -22.000, Step: 22 -2022-11-28 14:45:23 - r - INFO: - Episode: 165/300, Reward: -34.000, Step: 34 -2022-11-28 14:45:23 - r - INFO: - Current episode 165 has the best eval reward: -15.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 166/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:23 - r - INFO: - Episode: 167/300, Reward: -24.000, Step: 24 -2022-11-28 14:45:23 - r - INFO: - Episode: 168/300, Reward: -45.000, Step: 45 -2022-11-28 14:45:23 - r - INFO: - Episode: 169/300, Reward: -36.000, Step: 36 -2022-11-28 14:45:23 - r - INFO: - Episode: 170/300, Reward: -20.000, Step: 20 -2022-11-28 14:45:23 - r - INFO: - Episode: 171/300, Reward: -26.000, Step: 26 -2022-11-28 14:45:23 - r - INFO: - Episode: 172/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 173/300, Reward: -32.000, Step: 32 -2022-11-28 14:45:23 - r - INFO: - Episode: 174/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:23 - r - INFO: - Episode: 175/300, Reward: -31.000, Step: 31 -2022-11-28 14:45:23 - r - INFO: - Current episode 175 has the best eval reward: -15.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 176/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:23 - r - INFO: - Episode: 177/300, Reward: -31.000, Step: 31 -2022-11-28 14:45:23 - r - INFO: - Episode: 178/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 179/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 180/300, Reward: -21.000, Step: 21 -2022-11-28 14:45:23 - r - INFO: - Episode: 181/300, Reward: -31.000, Step: 31 -2022-11-28 14:45:23 - r - INFO: - Episode: 182/300, Reward: -21.000, Step: 21 -2022-11-28 14:45:23 - r - INFO: - Episode: 183/300, Reward: -39.000, Step: 39 -2022-11-28 14:45:23 - r - INFO: - Episode: 184/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Episode: 185/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:23 - r - INFO: - Episode: 186/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:23 - r - INFO: - Episode: 187/300, Reward: -27.000, Step: 27 -2022-11-28 14:45:23 - r - INFO: - Episode: 188/300, Reward: -18.000, Step: 18 -2022-11-28 14:45:23 - r - INFO: - Episode: 189/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:23 - r - INFO: - Episode: 190/300, Reward: -24.000, Step: 24 -2022-11-28 14:45:23 - r - INFO: - Episode: 191/300, Reward: -28.000, Step: 28 -2022-11-28 14:45:23 - r - INFO: - Episode: 192/300, Reward: -36.000, Step: 36 -2022-11-28 14:45:23 - r - INFO: - Episode: 193/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:23 - r - INFO: - Episode: 194/300, Reward: -40.000, Step: 40 -2022-11-28 14:45:23 - r - INFO: - Episode: 195/300, Reward: -20.000, Step: 20 -2022-11-28 14:45:23 - r - INFO: - Episode: 196/300, Reward: -23.000, Step: 23 -2022-11-28 14:45:23 - r - INFO: - Episode: 197/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:23 - r - INFO: - Episode: 198/300, Reward: -28.000, Step: 28 -2022-11-28 14:45:23 - r - INFO: - Episode: 199/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:23 - r - INFO: - Episode: 200/300, Reward: -27.000, Step: 27 -2022-11-28 14:45:23 - r - INFO: - Episode: 201/300, Reward: -14.000, Step: 14 -2022-11-28 14:45:23 - r - INFO: - Episode: 202/300, Reward: -31.000, Step: 31 -2022-11-28 14:45:23 - r - INFO: - Episode: 203/300, Reward: -25.000, Step: 25 -2022-11-28 14:45:23 - r - INFO: - Episode: 204/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:23 - r - INFO: - Episode: 205/300, Reward: -36.000, Step: 36 -2022-11-28 14:45:23 - r - INFO: - Episode: 206/300, Reward: -29.000, Step: 29 -2022-11-28 14:45:23 - r - INFO: - Episode: 207/300, Reward: -20.000, Step: 20 -2022-11-28 14:45:23 - r - INFO: - Episode: 208/300, Reward: -23.000, Step: 23 -2022-11-28 14:45:23 - r - INFO: - Episode: 209/300, Reward: -14.000, Step: 14 -2022-11-28 14:45:23 - r - INFO: - Episode: 210/300, Reward: -28.000, Step: 28 -2022-11-28 14:45:23 - r - INFO: - Episode: 211/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:23 - r - INFO: - Episode: 212/300, Reward: -26.000, Step: 26 -2022-11-28 14:45:23 - r - INFO: - Episode: 213/300, Reward: -18.000, Step: 18 -2022-11-28 14:45:23 - r - INFO: - Episode: 214/300, Reward: -26.000, Step: 26 -2022-11-28 14:45:23 - r - INFO: - Episode: 215/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:23 - r - INFO: - Episode: 216/300, Reward: -23.000, Step: 23 -2022-11-28 14:45:23 - r - INFO: - Episode: 217/300, Reward: -20.000, Step: 20 -2022-11-28 14:45:23 - r - INFO: - Episode: 218/300, Reward: -48.000, Step: 48 -2022-11-28 14:45:23 - r - INFO: - Episode: 219/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:23 - r - INFO: - Episode: 220/300, Reward: -133.000, Step: 34 -2022-11-28 14:45:23 - r - INFO: - Episode: 221/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:23 - r - INFO: - Episode: 222/300, Reward: -20.000, Step: 20 -2022-11-28 14:45:23 - r - INFO: - Episode: 223/300, Reward: -18.000, Step: 18 -2022-11-28 14:45:23 - r - INFO: - Episode: 224/300, Reward: -35.000, Step: 35 -2022-11-28 14:45:23 - r - INFO: - Episode: 225/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:23 - r - INFO: - Current episode 225 has the best eval reward: -13.000 -2022-11-28 14:45:23 - r - INFO: - Episode: 226/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:23 - r - INFO: - Episode: 227/300, Reward: -16.000, Step: 16 -2022-11-28 14:45:23 - r - INFO: - Episode: 228/300, Reward: -25.000, Step: 25 -2022-11-28 14:45:23 - r - INFO: - Episode: 229/300, Reward: -25.000, Step: 25 -2022-11-28 14:45:23 - r - INFO: - Episode: 230/300, Reward: -26.000, Step: 26 -2022-11-28 14:45:24 - r - INFO: - Episode: 231/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:24 - r - INFO: - Episode: 232/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:24 - r - INFO: - Episode: 233/300, Reward: -27.000, Step: 27 -2022-11-28 14:45:24 - r - INFO: - Episode: 234/300, Reward: -30.000, Step: 30 -2022-11-28 14:45:24 - r - INFO: - Episode: 235/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:24 - r - INFO: - Episode: 236/300, Reward: -18.000, Step: 18 -2022-11-28 14:45:24 - r - INFO: - Episode: 237/300, Reward: -122.000, Step: 23 -2022-11-28 14:45:24 - r - INFO: - Episode: 238/300, Reward: -25.000, Step: 25 -2022-11-28 14:45:24 - r - INFO: - Episode: 239/300, Reward: -20.000, Step: 20 -2022-11-28 14:45:24 - r - INFO: - Episode: 240/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 241/300, Reward: -39.000, Step: 39 -2022-11-28 14:45:24 - r - INFO: - Episode: 242/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:24 - r - INFO: - Episode: 243/300, Reward: -14.000, Step: 14 -2022-11-28 14:45:24 - r - INFO: - Episode: 244/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 245/300, Reward: -22.000, Step: 22 -2022-11-28 14:45:24 - r - INFO: - Episode: 246/300, Reward: -31.000, Step: 31 -2022-11-28 14:45:24 - r - INFO: - Episode: 247/300, Reward: -20.000, Step: 20 -2022-11-28 14:45:24 - r - INFO: - Episode: 248/300, Reward: -28.000, Step: 28 -2022-11-28 14:45:24 - r - INFO: - Episode: 249/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 250/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:24 - r - INFO: - Episode: 251/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 252/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 253/300, Reward: -21.000, Step: 21 -2022-11-28 14:45:24 - r - INFO: - Episode: 254/300, Reward: -16.000, Step: 16 -2022-11-28 14:45:24 - r - INFO: - Episode: 255/300, Reward: -22.000, Step: 22 -2022-11-28 14:45:24 - r - INFO: - Episode: 256/300, Reward: -18.000, Step: 18 -2022-11-28 14:45:24 - r - INFO: - Episode: 257/300, Reward: -23.000, Step: 23 -2022-11-28 14:45:24 - r - INFO: - Episode: 258/300, Reward: -16.000, Step: 16 -2022-11-28 14:45:24 - r - INFO: - Episode: 259/300, Reward: -22.000, Step: 22 -2022-11-28 14:45:24 - r - INFO: - Episode: 260/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Current episode 260 has the best eval reward: -13.000 -2022-11-28 14:45:24 - r - INFO: - Episode: 261/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 262/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:24 - r - INFO: - Episode: 263/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:24 - r - INFO: - Episode: 264/300, Reward: -32.000, Step: 32 -2022-11-28 14:45:24 - r - INFO: - Episode: 265/300, Reward: -16.000, Step: 16 -2022-11-28 14:45:24 - r - INFO: - Episode: 266/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 267/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:24 - r - INFO: - Episode: 268/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 269/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 270/300, Reward: -28.000, Step: 28 -2022-11-28 14:45:24 - r - INFO: - Episode: 271/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 272/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 273/300, Reward: -16.000, Step: 16 -2022-11-28 14:45:24 - r - INFO: - Episode: 274/300, Reward: -128.000, Step: 29 -2022-11-28 14:45:24 - r - INFO: - Episode: 275/300, Reward: -32.000, Step: 32 -2022-11-28 14:45:24 - r - INFO: - Episode: 276/300, Reward: -24.000, Step: 24 -2022-11-28 14:45:24 - r - INFO: - Episode: 277/300, Reward: -26.000, Step: 26 -2022-11-28 14:45:24 - r - INFO: - Episode: 278/300, Reward: -14.000, Step: 14 -2022-11-28 14:45:24 - r - INFO: - Episode: 279/300, Reward: -25.000, Step: 25 -2022-11-28 14:45:24 - r - INFO: - Episode: 280/300, Reward: -22.000, Step: 22 -2022-11-28 14:45:24 - r - INFO: - Current episode 280 has the best eval reward: -13.000 -2022-11-28 14:45:24 - r - INFO: - Episode: 281/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 282/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 283/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 284/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 285/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 286/300, Reward: -16.000, Step: 16 -2022-11-28 14:45:24 - r - INFO: - Episode: 287/300, Reward: -21.000, Step: 21 -2022-11-28 14:45:24 - r - INFO: - Episode: 288/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:24 - r - INFO: - Episode: 289/300, Reward: -26.000, Step: 26 -2022-11-28 14:45:24 - r - INFO: - Episode: 290/300, Reward: -16.000, Step: 16 -2022-11-28 14:45:24 - r - INFO: - Current episode 290 has the best eval reward: -13.000 -2022-11-28 14:45:24 - r - INFO: - Episode: 291/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 292/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 293/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 294/300, Reward: -15.000, Step: 15 -2022-11-28 14:45:24 - r - INFO: - Episode: 295/300, Reward: -13.000, Step: 13 -2022-11-28 14:45:24 - r - INFO: - Episode: 296/300, Reward: -24.000, Step: 24 -2022-11-28 14:45:24 - r - INFO: - Episode: 297/300, Reward: -19.000, Step: 19 -2022-11-28 14:45:24 - r - INFO: - Episode: 298/300, Reward: -14.000, Step: 14 -2022-11-28 14:45:24 - r - INFO: - Episode: 299/300, Reward: -16.000, Step: 16 -2022-11-28 14:45:24 - r - INFO: - Episode: 300/300, Reward: -17.000, Step: 17 -2022-11-28 14:45:24 - r - INFO: - Finish training! diff --git a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/models/Qleaning_model.pkl b/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/models/Qleaning_model.pkl deleted file mode 100644 index 11b3246418fe8e689ff25f81da33205b94378416..0000000000000000000000000000000000000000 --- a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/models/Qleaning_model.pkl +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0a5088e21ba086ef3631d0381b7b57ec20f56261d403a159a6c8d0cae3d6ec63 -size 5999 diff --git a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/results/learning_curve.png b/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/results/learning_curve.png deleted file mode 100644 index 9a7d7b53cd632bf99f7c9b1335f1816c33df8bea..0000000000000000000000000000000000000000 Binary files a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/results/learning_curve.png and /dev/null differ diff --git a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/results/res.csv b/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/results/res.csv deleted file mode 100644 index 6e5550faa60c3fd0b9aed2945e73ed281a843f5e..0000000000000000000000000000000000000000 --- a/CliffWalking-v0/Train_CliffWalking-v0_QLearning_20221128-144520/results/res.csv +++ /dev/null @@ -1,301 +0,0 @@ -episodes,rewards,steps -0,-397,100 -1,-1090,100 -2,-694,100 -3,-397,100 -4,-496,100 -5,-298,100 -6,-199,100 -7,-298,100 -8,-100,100 -9,-199,100 -10,-93,93 -11,-100,100 -12,-199,100 -13,-199,100 -14,-100,100 -15,-100,100 -16,-33,33 -17,-100,100 -18,-66,66 -19,-99,99 -20,-100,100 -21,-100,100 -22,-100,100 -23,-54,54 -24,-100,100 -25,-73,73 -26,-100,100 -27,-90,90 -28,-87,87 -29,-100,100 -30,-46,46 -31,-82,82 -32,-100,100 -33,-100,100 -34,-67,67 -35,-75,75 -36,-100,100 -37,-45,45 -38,-100,100 -39,-37,37 -40,-100,100 -41,-43,43 -42,-100,100 -43,-56,56 -44,-70,70 -45,-100,100 -46,-47,47 -47,-85,85 -48,-82,82 -49,-51,51 -50,-50,50 -51,-86,86 -52,-100,100 -53,-40,40 -54,-87,87 -55,-59,59 -56,-51,51 -57,-98,98 -58,-67,67 -59,-60,60 -60,-38,38 -61,-76,76 -62,-70,70 -63,-60,60 -64,-68,68 -65,-25,25 -66,-69,69 -67,-183,84 -68,-62,62 -69,-44,44 -70,-71,71 -71,-55,55 -72,-65,65 -73,-61,61 -74,-36,36 -75,-47,47 -76,-63,63 -77,-45,45 -78,-59,59 -79,-39,39 -80,-62,62 -81,-38,38 -82,-64,64 -83,-40,40 -84,-59,59 -85,-48,48 -86,-39,39 -87,-70,70 -88,-34,34 -89,-40,40 -90,-27,27 -91,-65,65 -92,-79,79 -93,-30,30 -94,-38,38 -95,-23,23 -96,-60,60 -97,-41,41 -98,-39,39 -99,-42,42 -100,-41,41 -101,-59,59 -102,-31,31 -103,-43,43 -104,-70,70 -105,-29,29 -106,-161,62 -107,-38,38 -108,-45,45 -109,-29,29 -110,-47,47 -111,-23,23 -112,-62,62 -113,-34,34 -114,-46,46 -115,-29,29 -116,-46,46 -117,-30,30 -118,-24,24 -119,-30,30 -120,-42,42 -121,-62,62 -122,-30,30 -123,-31,31 -124,-37,37 -125,-51,51 -126,-32,32 -127,-22,22 -128,-34,34 -129,-22,22 -130,-53,53 -131,-28,28 -132,-33,33 -133,-39,39 -134,-39,39 -135,-20,20 -136,-30,30 -137,-42,42 -138,-154,55 -139,-34,34 -140,-29,29 -141,-21,21 -142,-38,38 -143,-21,21 -144,-46,46 -145,-19,19 -146,-37,37 -147,-27,27 -148,-39,39 -149,-18,18 -150,-34,34 -151,-25,25 -152,-32,32 -153,-40,40 -154,-30,30 -155,-36,36 -156,-29,29 -157,-30,30 -158,-29,29 -159,-22,22 -160,-18,18 -161,-46,46 -162,-27,27 -163,-22,22 -164,-34,34 -165,-15,15 -166,-24,24 -167,-45,45 -168,-36,36 -169,-20,20 -170,-26,26 -171,-29,29 -172,-32,32 -173,-17,17 -174,-31,31 -175,-15,15 -176,-31,31 -177,-29,29 -178,-29,29 -179,-21,21 -180,-31,31 -181,-21,21 -182,-39,39 -183,-30,30 -184,-13,13 -185,-30,30 -186,-27,27 -187,-18,18 -188,-17,17 -189,-24,24 -190,-28,28 -191,-36,36 -192,-15,15 -193,-40,40 -194,-20,20 -195,-23,23 -196,-17,17 -197,-28,28 -198,-15,15 -199,-27,27 -200,-14,14 -201,-31,31 -202,-25,25 -203,-19,19 -204,-36,36 -205,-29,29 -206,-20,20 -207,-23,23 -208,-14,14 -209,-28,28 -210,-19,19 -211,-26,26 -212,-18,18 -213,-26,26 -214,-19,19 -215,-23,23 -216,-20,20 -217,-48,48 -218,-13,13 -219,-133,34 -220,-17,17 -221,-20,20 -222,-18,18 -223,-35,35 -224,-17,17 -225,-13,13 -226,-16,16 -227,-25,25 -228,-25,25 -229,-26,26 -230,-19,19 -231,-17,17 -232,-27,27 -233,-30,30 -234,-17,17 -235,-18,18 -236,-122,23 -237,-25,25 -238,-20,20 -239,-13,13 -240,-39,39 -241,-17,17 -242,-14,14 -243,-15,15 -244,-22,22 -245,-31,31 -246,-20,20 -247,-28,28 -248,-15,15 -249,-19,19 -250,-15,15 -251,-13,13 -252,-21,21 -253,-16,16 -254,-22,22 -255,-18,18 -256,-23,23 -257,-16,16 -258,-22,22 -259,-13,13 -260,-13,13 -261,-19,19 -262,-17,17 -263,-32,32 -264,-16,16 -265,-15,15 -266,-17,17 -267,-13,13 -268,-15,15 -269,-28,28 -270,-15,15 -271,-13,13 -272,-16,16 -273,-128,29 -274,-32,32 -275,-24,24 -276,-26,26 -277,-14,14 -278,-25,25 -279,-22,22 -280,-13,13 -281,-15,15 -282,-15,15 -283,-13,13 -284,-13,13 -285,-16,16 -286,-21,21 -287,-19,19 -288,-26,26 -289,-16,16 -290,-13,13 -291,-13,13 -292,-13,13 -293,-15,15 -294,-13,13 -295,-24,24 -296,-19,19 -297,-14,14 -298,-16,16 -299,-17,17 diff --git a/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/config.yaml b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/config.yaml similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/config.yaml rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/config.yaml diff --git a/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/logs/log.txt b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/logs/log.txt similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/logs/log.txt rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/logs/log.txt diff --git a/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/modelsDynaQ_model.pkl b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/modelsDynaQ_model.pkl similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/modelsDynaQ_model.pkl rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/modelsDynaQ_model.pkl diff --git a/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/results/learning_curve.png b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/results/learning_curve.png similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/results/learning_curve.png rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/results/learning_curve.png diff --git a/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/results/res.csv b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/results/res.csv similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/results/res.csv rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_DynaQ_20221210-095944/results/res.csv diff --git a/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/config.yaml b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/config.yaml similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/config.yaml rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/config.yaml diff --git a/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/logs/log.txt b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/logs/log.txt similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/logs/log.txt rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/logs/log.txt diff --git a/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/models/checkpoint.pkl b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/models/checkpoint.pkl similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/models/checkpoint.pkl rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/models/checkpoint.pkl diff --git a/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/learning_curve.png b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/learning_curve.png similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/learning_curve.png rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/learning_curve.png diff --git a/CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/results/res.csv b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/res.csv similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_QLearning_20221128-150537/results/res.csv rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/results/res.csv diff --git a/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/tb_logs/events.out.tfevents.1678464930.DESKTOP-H34HQIQ.51560.0 b/ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/tb_logs/events.out.tfevents.1678464930.DESKTOP-H34HQIQ.51560.0 similarity index 100% rename from CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/tb_logs/events.out.tfevents.1678464930.DESKTOP-H34HQIQ.51560.0 rename to ToyText/CliffWalking-v0/Test_CliffWalking-v0_Sarsa_20230311-001530/tb_logs/events.out.tfevents.1678464930.DESKTOP-H34HQIQ.51560.0 diff --git a/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/config.yaml b/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cc8f2fb8b22e3a1cd44a0ec467b4fa0e0f20348a --- /dev/null +++ b/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/config.yaml @@ -0,0 +1,32 @@ +general_cfg: + algo_name: QLearning + collect_traj: false + device: cpu + env_name: gym + load_checkpoint: true + load_model_step: 12000 + load_path: Train_single_CliffWalking-v0_QLearning_20230519-005837 + max_episode: 10 + max_step: 100 + mode: test + model_save_fre: 500 + mp_backend: single + n_learners: 1 + n_workers: 1 + online_eval: false + online_eval_episode: 10 + seed: 1 + share_buffer: true +algo_cfg: + epsilon_decay: 300 + epsilon_end: 0.01 + epsilon_start: 0.95 + gamma: 0.99 + lr: 0.1 +env_cfg: + id: CliffWalking-v0 + ignore_params: + - wrapper + - ignore_params + render_mode: null + wrapper: null diff --git a/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/logs/log.txt b/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..9f5541f66d8e2ad284699f13bab19de989dc83c7 --- /dev/null +++ b/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/logs/log.txt @@ -0,0 +1,52 @@ +2023-05-19 00:59:51 - SimpleLog - INFO: - General Configs: +2023-05-19 00:59:51 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:59:51 - SimpleLog - INFO: - Name Value Type +2023-05-19 00:59:51 - SimpleLog - INFO: - env_name gym +2023-05-19 00:59:51 - SimpleLog - INFO: - algo_name QLearning +2023-05-19 00:59:51 - SimpleLog - INFO: - mode test +2023-05-19 00:59:51 - SimpleLog - INFO: - device cpu +2023-05-19 00:59:51 - SimpleLog - INFO: - seed 1 +2023-05-19 00:59:51 - SimpleLog - INFO: - max_episode 10 +2023-05-19 00:59:51 - SimpleLog - INFO: - max_step 100 +2023-05-19 00:59:51 - SimpleLog - INFO: - collect_traj 0 +2023-05-19 00:59:51 - SimpleLog - INFO: - mp_backend single +2023-05-19 00:59:51 - SimpleLog - INFO: - n_workers 1 +2023-05-19 00:59:51 - SimpleLog - INFO: - n_learners 1 +2023-05-19 00:59:51 - SimpleLog - INFO: - share_buffer 1 +2023-05-19 00:59:51 - SimpleLog - INFO: - online_eval 0 +2023-05-19 00:59:51 - SimpleLog - INFO: - online_eval_episode 10 +2023-05-19 00:59:51 - SimpleLog - INFO: - model_save_fre 500 +2023-05-19 00:59:51 - SimpleLog - INFO: - load_checkpoint 1 +2023-05-19 00:59:51 - SimpleLog - INFO: - load_path Train_single_CliffWalking-v0_QLearning_20230519-005837 +2023-05-19 00:59:51 - SimpleLog - INFO: - load_model_step 12000 +2023-05-19 00:59:51 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:59:51 - SimpleLog - INFO: - Algo Configs: +2023-05-19 00:59:51 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:59:51 - SimpleLog - INFO: - Name Value Type +2023-05-19 00:59:51 - SimpleLog - INFO: - epsilon_start 0.95 +2023-05-19 00:59:51 - SimpleLog - INFO: - epsilon_end 0.01 +2023-05-19 00:59:51 - SimpleLog - INFO: - epsilon_decay 300 +2023-05-19 00:59:51 - SimpleLog - INFO: - gamma 0.99 +2023-05-19 00:59:51 - SimpleLog - INFO: - lr 0.1 +2023-05-19 00:59:51 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:59:51 - SimpleLog - INFO: - Env Configs: +2023-05-19 00:59:51 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:59:51 - SimpleLog - INFO: - Name Value Type +2023-05-19 00:59:51 - SimpleLog - INFO: - id CliffWalking-v0 +2023-05-19 00:59:51 - SimpleLog - INFO: - render_mode None +2023-05-19 00:59:51 - SimpleLog - INFO: - wrapper None +2023-05-19 00:59:51 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-19 00:59:51 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:59:51 - SimpleLog - INFO: - obs_space: Discrete(48), n_actions: Discrete(4) +2023-05-19 00:59:51 - SimpleLog - INFO: - Start testing! +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 0, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 1, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 2, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 3, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 4, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 5, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 6, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 7, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 8, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - episode: 9, ep_reward: -13, ep_step: 13 +2023-05-19 00:59:51 - SimpleLog - INFO: - Finish testing! total time consumed: 0.02s diff --git a/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/tb_logs/interact/events.out.tfevents.1684429191.DESKTOP-H34HQIQ.94200.0 b/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/tb_logs/interact/events.out.tfevents.1684429191.DESKTOP-H34HQIQ.94200.0 new file mode 100644 index 0000000000000000000000000000000000000000..c5abba9e0ee71018c3cad5954e99211bc1df27ac --- /dev/null +++ b/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/tb_logs/interact/events.out.tfevents.1684429191.DESKTOP-H34HQIQ.94200.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715f68373647ab2fa023781cd81d1c6abed325f8f63359a5572827a8794835cc +size 750 diff --git a/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/tb_logs/model/events.out.tfevents.1684429191.DESKTOP-H34HQIQ.94200.1 b/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/tb_logs/model/events.out.tfevents.1684429191.DESKTOP-H34HQIQ.94200.1 new file mode 100644 index 0000000000000000000000000000000000000000..8f3ef4190f0b11de722285fd8996123ef5619b1a --- /dev/null +++ b/ToyText/CliffWalking-v0/Test_single_CliffWalking-v0_QLearning_20230519-005951/tb_logs/model/events.out.tfevents.1684429191.DESKTOP-H34HQIQ.94200.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48523c05279b11aaebb4f245670d2d649b949be219aa05dfcc99c7bc3048c9b2 +size 40 diff --git a/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/config.yaml b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/config.yaml similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/config.yaml rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/config.yaml diff --git a/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/logs/log.txt b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/logs/log.txt similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/logs/log.txt rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/logs/log.txt diff --git a/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/modelsDynaQ_model.pkl b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/modelsDynaQ_model.pkl similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/modelsDynaQ_model.pkl rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/modelsDynaQ_model.pkl diff --git a/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/results/learning_curve.png b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/results/learning_curve.png similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/results/learning_curve.png rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/results/learning_curve.png diff --git a/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/results/res.csv b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/results/res.csv similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/results/res.csv rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_DynaQ_20221210-095808/results/res.csv diff --git a/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/config.yaml b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/config.yaml similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/config.yaml rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/config.yaml diff --git a/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/logs/log.txt b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/logs/log.txt similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/logs/log.txt rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/logs/log.txt diff --git a/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/models/checkpoint.pkl b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/models/checkpoint.pkl similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/models/checkpoint.pkl rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/models/checkpoint.pkl diff --git a/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/results/learning_curve.png b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/results/learning_curve.png similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/results/learning_curve.png rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/results/learning_curve.png diff --git a/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/results/res.csv b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/results/res.csv similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/results/res.csv rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/results/res.csv diff --git a/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/tb_logs/events.out.tfevents.1678464904.DESKTOP-H34HQIQ.27128.0 b/ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/tb_logs/events.out.tfevents.1678464904.DESKTOP-H34HQIQ.27128.0 similarity index 100% rename from CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/tb_logs/events.out.tfevents.1678464904.DESKTOP-H34HQIQ.27128.0 rename to ToyText/CliffWalking-v0/Train_CliffWalking-v0_Sarsa_20230311-001504/tb_logs/events.out.tfevents.1678464904.DESKTOP-H34HQIQ.27128.0 diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/config.yaml b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2044a69e1b9240cc1b88fba79052d64c8711a0de --- /dev/null +++ b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/config.yaml @@ -0,0 +1,32 @@ +general_cfg: + algo_name: QLearning + collect_traj: false + device: cpu + env_name: gym + load_checkpoint: false + load_model_step: best + load_path: Train_single_CartPole-v1_DQN_20230515-211721 + max_episode: 300 + max_step: 100 + mode: train + model_save_fre: 500 + mp_backend: single + n_learners: 1 + n_workers: 1 + online_eval: false + online_eval_episode: 10 + seed: 1 + share_buffer: true +algo_cfg: + epsilon_decay: 300 + epsilon_end: 0.01 + epsilon_start: 0.95 + gamma: 0.99 + lr: 0.1 +env_cfg: + id: CliffWalking-v0 + ignore_params: + - wrapper + - ignore_params + render_mode: null + wrapper: null diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/logs/log.txt b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/logs/log.txt new file mode 100644 index 0000000000000000000000000000000000000000..442acd3330c4641859c08610b52597ec1bcf9314 --- /dev/null +++ b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/logs/log.txt @@ -0,0 +1,342 @@ +2023-05-19 00:58:37 - SimpleLog - INFO: - General Configs: +2023-05-19 00:58:37 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:58:37 - SimpleLog - INFO: - Name Value Type +2023-05-19 00:58:37 - SimpleLog - INFO: - env_name gym +2023-05-19 00:58:37 - SimpleLog - INFO: - algo_name QLearning +2023-05-19 00:58:37 - SimpleLog - INFO: - mode train +2023-05-19 00:58:37 - SimpleLog - INFO: - device cpu +2023-05-19 00:58:37 - SimpleLog - INFO: - seed 1 +2023-05-19 00:58:37 - SimpleLog - INFO: - max_episode 300 +2023-05-19 00:58:37 - SimpleLog - INFO: - max_step 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - collect_traj 0 +2023-05-19 00:58:37 - SimpleLog - INFO: - mp_backend single +2023-05-19 00:58:37 - SimpleLog - INFO: - n_workers 1 +2023-05-19 00:58:37 - SimpleLog - INFO: - n_learners 1 +2023-05-19 00:58:37 - SimpleLog - INFO: - share_buffer 1 +2023-05-19 00:58:37 - SimpleLog - INFO: - online_eval 0 +2023-05-19 00:58:37 - SimpleLog - INFO: - online_eval_episode 10 +2023-05-19 00:58:37 - SimpleLog - INFO: - model_save_fre 500 +2023-05-19 00:58:37 - SimpleLog - INFO: - load_checkpoint 0 +2023-05-19 00:58:37 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_DQN_20230515-211721 +2023-05-19 00:58:37 - SimpleLog - INFO: - load_model_step best +2023-05-19 00:58:37 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:58:37 - SimpleLog - INFO: - Algo Configs: +2023-05-19 00:58:37 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:58:37 - SimpleLog - INFO: - Name Value Type +2023-05-19 00:58:37 - SimpleLog - INFO: - epsilon_start 0.95 +2023-05-19 00:58:37 - SimpleLog - INFO: - epsilon_end 0.01 +2023-05-19 00:58:37 - SimpleLog - INFO: - epsilon_decay 300 +2023-05-19 00:58:37 - SimpleLog - INFO: - gamma 0.99 +2023-05-19 00:58:37 - SimpleLog - INFO: - lr 0.1 +2023-05-19 00:58:37 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:58:37 - SimpleLog - INFO: - Env Configs: +2023-05-19 00:58:37 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:58:37 - SimpleLog - INFO: - Name Value Type +2023-05-19 00:58:37 - SimpleLog - INFO: - id CliffWalking-v0 +2023-05-19 00:58:37 - SimpleLog - INFO: - render_mode None +2023-05-19 00:58:37 - SimpleLog - INFO: - wrapper None +2023-05-19 00:58:37 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] +2023-05-19 00:58:37 - SimpleLog - INFO: - ================================================================================ +2023-05-19 00:58:37 - SimpleLog - INFO: - obs_space: Discrete(48), n_actions: Discrete(4) +2023-05-19 00:58:37 - SimpleLog - INFO: - Start training! +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 0, ep_reward: -397, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 1, ep_reward: -1090, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 2, ep_reward: -694, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 3, ep_reward: -397, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 4, ep_reward: -496, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 5, ep_reward: -298, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 6, ep_reward: -199, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 7, ep_reward: -298, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 8, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 9, ep_reward: -199, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 10, ep_reward: -93, ep_step: 93 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 11, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 12, ep_reward: -199, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 13, ep_reward: -199, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 14, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 15, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 16, ep_reward: -33, ep_step: 33 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 17, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 18, ep_reward: -66, ep_step: 66 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 19, ep_reward: -99, ep_step: 99 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 20, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 21, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 22, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 23, ep_reward: -54, ep_step: 54 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 24, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 25, ep_reward: -73, ep_step: 73 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 26, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 27, ep_reward: -90, ep_step: 90 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 28, ep_reward: -87, ep_step: 87 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 29, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 30, ep_reward: -46, ep_step: 46 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 31, ep_reward: -82, ep_step: 82 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 32, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 33, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 34, ep_reward: -67, ep_step: 67 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 35, ep_reward: -75, ep_step: 75 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 36, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 37, ep_reward: -45, ep_step: 45 +2023-05-19 00:58:37 - SimpleLog - INFO: - episode: 38, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 39, ep_reward: -37, ep_step: 37 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 40, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 41, ep_reward: -43, ep_step: 43 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 42, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 43, ep_reward: -56, ep_step: 56 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 44, ep_reward: -70, ep_step: 70 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 45, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 46, ep_reward: -47, ep_step: 47 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 47, ep_reward: -85, ep_step: 85 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 48, ep_reward: -82, ep_step: 82 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 49, ep_reward: -51, ep_step: 51 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 50, ep_reward: -50, ep_step: 50 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 51, ep_reward: -86, ep_step: 86 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 52, ep_reward: -100, ep_step: 100 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 53, ep_reward: -40, ep_step: 40 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 54, ep_reward: -87, ep_step: 87 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 55, ep_reward: -59, ep_step: 59 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 56, ep_reward: -51, ep_step: 51 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 57, ep_reward: -98, ep_step: 98 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 58, ep_reward: -67, ep_step: 67 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 59, ep_reward: -60, ep_step: 60 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 60, ep_reward: -38, ep_step: 38 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 61, ep_reward: -76, ep_step: 76 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 62, ep_reward: -70, ep_step: 70 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 63, ep_reward: -60, ep_step: 60 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 64, ep_reward: -68, ep_step: 68 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 65, ep_reward: -25, ep_step: 25 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 66, ep_reward: -69, ep_step: 69 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 67, ep_reward: -183, ep_step: 84 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 68, ep_reward: -62, ep_step: 62 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 69, ep_reward: -44, ep_step: 44 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 70, ep_reward: -71, ep_step: 71 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 71, ep_reward: -55, ep_step: 55 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 72, ep_reward: -65, ep_step: 65 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 73, ep_reward: -61, ep_step: 61 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 74, ep_reward: -36, ep_step: 36 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 75, ep_reward: -47, ep_step: 47 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 76, ep_reward: -63, ep_step: 63 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 77, ep_reward: -45, ep_step: 45 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 78, ep_reward: -59, ep_step: 59 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 79, ep_reward: -39, ep_step: 39 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 80, ep_reward: -62, ep_step: 62 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 81, ep_reward: -38, ep_step: 38 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 82, ep_reward: -64, ep_step: 64 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 83, ep_reward: -40, ep_step: 40 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 84, ep_reward: -59, ep_step: 59 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 85, ep_reward: -48, ep_step: 48 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 86, ep_reward: -39, ep_step: 39 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 87, ep_reward: -70, ep_step: 70 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 88, ep_reward: -34, ep_step: 34 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 89, ep_reward: -40, ep_step: 40 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 90, ep_reward: -27, ep_step: 27 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 91, ep_reward: -65, ep_step: 65 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 92, ep_reward: -79, ep_step: 79 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 93, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 94, ep_reward: -38, ep_step: 38 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 95, ep_reward: -23, ep_step: 23 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 96, ep_reward: -60, ep_step: 60 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 97, ep_reward: -41, ep_step: 41 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 98, ep_reward: -39, ep_step: 39 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 99, ep_reward: -42, ep_step: 42 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 100, ep_reward: -41, ep_step: 41 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 101, ep_reward: -59, ep_step: 59 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 102, ep_reward: -31, ep_step: 31 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 103, ep_reward: -43, ep_step: 43 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 104, ep_reward: -70, ep_step: 70 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 105, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:38 - SimpleLog - INFO: - episode: 106, ep_reward: -161, ep_step: 62 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 107, ep_reward: -38, ep_step: 38 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 108, ep_reward: -45, ep_step: 45 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 109, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 110, ep_reward: -47, ep_step: 47 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 111, ep_reward: -23, ep_step: 23 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 112, ep_reward: -62, ep_step: 62 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 113, ep_reward: -34, ep_step: 34 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 114, ep_reward: -46, ep_step: 46 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 115, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 116, ep_reward: -46, ep_step: 46 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 117, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 118, ep_reward: -24, ep_step: 24 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 119, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 120, ep_reward: -42, ep_step: 42 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 121, ep_reward: -62, ep_step: 62 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 122, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 123, ep_reward: -31, ep_step: 31 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 124, ep_reward: -37, ep_step: 37 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 125, ep_reward: -51, ep_step: 51 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 126, ep_reward: -32, ep_step: 32 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 127, ep_reward: -22, ep_step: 22 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 128, ep_reward: -34, ep_step: 34 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 129, ep_reward: -22, ep_step: 22 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 130, ep_reward: -53, ep_step: 53 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 131, ep_reward: -28, ep_step: 28 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 132, ep_reward: -33, ep_step: 33 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 133, ep_reward: -39, ep_step: 39 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 134, ep_reward: -39, ep_step: 39 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 135, ep_reward: -20, ep_step: 20 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 136, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 137, ep_reward: -42, ep_step: 42 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 138, ep_reward: -154, ep_step: 55 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 139, ep_reward: -34, ep_step: 34 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 140, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 141, ep_reward: -21, ep_step: 21 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 142, ep_reward: -38, ep_step: 38 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 143, ep_reward: -21, ep_step: 21 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 144, ep_reward: -46, ep_step: 46 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 145, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 146, ep_reward: -37, ep_step: 37 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 147, ep_reward: -27, ep_step: 27 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 148, ep_reward: -39, ep_step: 39 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 149, ep_reward: -18, ep_step: 18 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 150, ep_reward: -34, ep_step: 34 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 151, ep_reward: -25, ep_step: 25 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 152, ep_reward: -32, ep_step: 32 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 153, ep_reward: -40, ep_step: 40 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 154, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 155, ep_reward: -36, ep_step: 36 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 156, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 157, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 158, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 159, ep_reward: -22, ep_step: 22 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 160, ep_reward: -18, ep_step: 18 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 161, ep_reward: -46, ep_step: 46 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 162, ep_reward: -27, ep_step: 27 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 163, ep_reward: -22, ep_step: 22 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 164, ep_reward: -34, ep_step: 34 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 165, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 166, ep_reward: -24, ep_step: 24 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 167, ep_reward: -45, ep_step: 45 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 168, ep_reward: -36, ep_step: 36 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 169, ep_reward: -20, ep_step: 20 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 170, ep_reward: -26, ep_step: 26 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 171, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 172, ep_reward: -32, ep_step: 32 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 173, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 174, ep_reward: -31, ep_step: 31 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 175, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 176, ep_reward: -31, ep_step: 31 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 177, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 178, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 179, ep_reward: -21, ep_step: 21 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 180, ep_reward: -31, ep_step: 31 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 181, ep_reward: -21, ep_step: 21 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 182, ep_reward: -39, ep_step: 39 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 183, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 184, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 185, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 186, ep_reward: -27, ep_step: 27 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 187, ep_reward: -18, ep_step: 18 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 188, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 189, ep_reward: -24, ep_step: 24 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 190, ep_reward: -28, ep_step: 28 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 191, ep_reward: -36, ep_step: 36 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 192, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 193, ep_reward: -40, ep_step: 40 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 194, ep_reward: -20, ep_step: 20 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 195, ep_reward: -23, ep_step: 23 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 196, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 197, ep_reward: -28, ep_step: 28 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 198, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 199, ep_reward: -27, ep_step: 27 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 200, ep_reward: -14, ep_step: 14 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 201, ep_reward: -31, ep_step: 31 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 202, ep_reward: -25, ep_step: 25 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 203, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 204, ep_reward: -36, ep_step: 36 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 205, ep_reward: -29, ep_step: 29 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 206, ep_reward: -20, ep_step: 20 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 207, ep_reward: -23, ep_step: 23 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 208, ep_reward: -14, ep_step: 14 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 209, ep_reward: -28, ep_step: 28 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 210, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 211, ep_reward: -26, ep_step: 26 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 212, ep_reward: -18, ep_step: 18 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 213, ep_reward: -26, ep_step: 26 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 214, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 215, ep_reward: -23, ep_step: 23 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 216, ep_reward: -20, ep_step: 20 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 217, ep_reward: -48, ep_step: 48 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 218, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 219, ep_reward: -133, ep_step: 34 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 220, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 221, ep_reward: -20, ep_step: 20 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 222, ep_reward: -18, ep_step: 18 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 223, ep_reward: -35, ep_step: 35 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 224, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 225, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 226, ep_reward: -16, ep_step: 16 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 227, ep_reward: -25, ep_step: 25 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 228, ep_reward: -25, ep_step: 25 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 229, ep_reward: -26, ep_step: 26 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 230, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 231, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 232, ep_reward: -27, ep_step: 27 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 233, ep_reward: -30, ep_step: 30 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 234, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 235, ep_reward: -18, ep_step: 18 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 236, ep_reward: -122, ep_step: 23 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 237, ep_reward: -25, ep_step: 25 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 238, ep_reward: -20, ep_step: 20 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 239, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 240, ep_reward: -39, ep_step: 39 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 241, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:39 - SimpleLog - INFO: - episode: 242, ep_reward: -14, ep_step: 14 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 243, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 244, ep_reward: -22, ep_step: 22 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 245, ep_reward: -31, ep_step: 31 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 246, ep_reward: -20, ep_step: 20 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 247, ep_reward: -28, ep_step: 28 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 248, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 249, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 250, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 251, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 252, ep_reward: -21, ep_step: 21 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 253, ep_reward: -16, ep_step: 16 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 254, ep_reward: -22, ep_step: 22 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 255, ep_reward: -18, ep_step: 18 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 256, ep_reward: -23, ep_step: 23 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 257, ep_reward: -16, ep_step: 16 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 258, ep_reward: -22, ep_step: 22 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 259, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 260, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 261, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 262, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 263, ep_reward: -32, ep_step: 32 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 264, ep_reward: -16, ep_step: 16 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 265, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 266, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 267, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 268, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 269, ep_reward: -28, ep_step: 28 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 270, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 271, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 272, ep_reward: -16, ep_step: 16 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 273, ep_reward: -128, ep_step: 29 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 274, ep_reward: -32, ep_step: 32 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 275, ep_reward: -24, ep_step: 24 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 276, ep_reward: -26, ep_step: 26 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 277, ep_reward: -14, ep_step: 14 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 278, ep_reward: -25, ep_step: 25 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 279, ep_reward: -22, ep_step: 22 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 280, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 281, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 282, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 283, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 284, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 285, ep_reward: -16, ep_step: 16 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 286, ep_reward: -21, ep_step: 21 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 287, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 288, ep_reward: -26, ep_step: 26 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 289, ep_reward: -16, ep_step: 16 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 290, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 291, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 292, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 293, ep_reward: -15, ep_step: 15 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 294, ep_reward: -13, ep_step: 13 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 295, ep_reward: -24, ep_step: 24 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 296, ep_reward: -19, ep_step: 19 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 297, ep_reward: -14, ep_step: 14 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 298, ep_reward: -16, ep_step: 16 +2023-05-19 00:58:40 - SimpleLog - INFO: - episode: 299, ep_reward: -17, ep_step: 17 +2023-05-19 00:58:40 - SimpleLog - INFO: - Finish training! total time consumed: 3.10s diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/1000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/1000 new file mode 100644 index 0000000000000000000000000000000000000000..fbc026dc6b4d8e21b228efc332c45c1879aaa0c6 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/1000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/10000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/10000 new file mode 100644 index 0000000000000000000000000000000000000000..e7e13ee2d4da5119ce9af7a105de2df2a987d237 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/10000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/10500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/10500 new file mode 100644 index 0000000000000000000000000000000000000000..5e93164c5542a65c0c318cfbea2532e6cf11d0c8 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/10500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/11000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/11000 new file mode 100644 index 0000000000000000000000000000000000000000..13854fcb086c8dc19ee2b4cf633fc979ad52ccde Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/11000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/11500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/11500 new file mode 100644 index 0000000000000000000000000000000000000000..4d5a3aab7d52a5e989556a475df5af9e861b2baf Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/11500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/12000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/12000 new file mode 100644 index 0000000000000000000000000000000000000000..a927cca72dfd2f37948d81c94cc5708f368b7ba1 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/12000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/1500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/1500 new file mode 100644 index 0000000000000000000000000000000000000000..54b205cd64e0b81363515a8e4a9ea74d6a31b1fb Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/1500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/2000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/2000 new file mode 100644 index 0000000000000000000000000000000000000000..d16bbfa3edeb847ef55b7f32913fd6815d1f8eaf Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/2000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/2500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/2500 new file mode 100644 index 0000000000000000000000000000000000000000..a765df91b1f7280caf14b76d65e5297ac46f0eb9 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/2500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/3000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/3000 new file mode 100644 index 0000000000000000000000000000000000000000..64a58e34cf0800ea55b193fddac78362bbd17b5e Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/3000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/3500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/3500 new file mode 100644 index 0000000000000000000000000000000000000000..b4eae4ddf4ae1d43b7002defc92bbc9f0ecdf47b Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/3500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/4000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/4000 new file mode 100644 index 0000000000000000000000000000000000000000..26c65f9c9bafaaee20d347aa000c9e562ed1d453 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/4000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/4500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/4500 new file mode 100644 index 0000000000000000000000000000000000000000..41d055a907a2b6e4665d055f9cd8b9d5161c013c Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/4500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/500 new file mode 100644 index 0000000000000000000000000000000000000000..3b6365745950c437fe1ad4849b195847f01f5f02 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/5000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/5000 new file mode 100644 index 0000000000000000000000000000000000000000..fd556aa21eeff97884b99a512e39b24a764f2de9 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/5000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/5500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/5500 new file mode 100644 index 0000000000000000000000000000000000000000..40e60098ecc24bbc213d47f0333ef237f3c76b32 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/5500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/6000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/6000 new file mode 100644 index 0000000000000000000000000000000000000000..a5b98ef69c88ab648a10ff98a6924b735646cd51 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/6000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/6500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/6500 new file mode 100644 index 0000000000000000000000000000000000000000..639b0fc4360965884ce307deeca3e4fcf56d2ea6 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/6500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/7000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/7000 new file mode 100644 index 0000000000000000000000000000000000000000..6b67b6a0d755c2ab3505b249469eeea62b1f8b5b Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/7000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/7500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/7500 new file mode 100644 index 0000000000000000000000000000000000000000..85c421d173407c52e204c5c59eb2de7c700a7bbd Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/7500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/8000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/8000 new file mode 100644 index 0000000000000000000000000000000000000000..e2edf37e490de28813c3e27a50750f8ec225cd5e Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/8000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/8500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/8500 new file mode 100644 index 0000000000000000000000000000000000000000..a01a3426433a1bcb6362c1acde3b77a0ea7cc91f Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/8500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/9000 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/9000 new file mode 100644 index 0000000000000000000000000000000000000000..2e75b6bc8df035370494cbf99103d0e8aa44263f Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/9000 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/9500 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/9500 new file mode 100644 index 0000000000000000000000000000000000000000..9cc623d1bd9845ad9d50fa53ee41cb16b7320647 Binary files /dev/null and b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/models/9500 differ diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/tb_logs/interact/events.out.tfevents.1684429117.DESKTOP-H34HQIQ.66128.0 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/tb_logs/interact/events.out.tfevents.1684429117.DESKTOP-H34HQIQ.66128.0 new file mode 100644 index 0000000000000000000000000000000000000000..c5a467e3ca02c873fb02a5cfcba2c06d0b1655b5 --- /dev/null +++ b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/tb_logs/interact/events.out.tfevents.1684429117.DESKTOP-H34HQIQ.66128.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6073ea422a1bad572f7b58625e0c45be5c19f81a9f7cba5e73dc93313af801 +size 31580 diff --git a/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/tb_logs/model/events.out.tfevents.1684429117.DESKTOP-H34HQIQ.66128.1 b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/tb_logs/model/events.out.tfevents.1684429117.DESKTOP-H34HQIQ.66128.1 new file mode 100644 index 0000000000000000000000000000000000000000..cbfa02066a4624160a65c478937b72cbb4f8d607 --- /dev/null +++ b/ToyText/CliffWalking-v0/Train_single_CliffWalking-v0_QLearning_20230519-005837/tb_logs/model/events.out.tfevents.1684429117.DESKTOP-H34HQIQ.66128.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba579d9e6571d4e818cb9d3a414f339775347074a0cf7b69fefa46c145af5339 +size 601780