| 2022-11-28 15:46:29 - r - INFO: - Hyperparameters: | |
| 2022-11-28 15:46:29 - r - INFO: - ================================================================================ | |
| 2022-11-28 15:46:29 - r - INFO: - Name Value Type | |
| 2022-11-28 15:46:29 - r - INFO: - env_name FrozenLakeNoSlippery-v1 <class 'str'> | |
| 2022-11-28 15:46:29 - r - INFO: - new_step_api 1 <class 'bool'> | |
| 2022-11-28 15:46:29 - r - INFO: - wrapper None <class 'str'> | |
| 2022-11-28 15:46:29 - r - INFO: - render 1 <class 'bool'> | |
| 2022-11-28 15:46:29 - r - INFO: - algo_name QLearning <class 'str'> | |
| 2022-11-28 15:46:29 - r - INFO: - mode test <class 'str'> | |
| 2022-11-28 15:46:29 - r - INFO: - seed 10 <class 'int'> | |
| 2022-11-28 15:46:29 - r - INFO: - device cpu <class 'str'> | |
| 2022-11-28 15:46:29 - r - INFO: - train_eps 800 <class 'int'> | |
| 2022-11-28 15:46:29 - r - INFO: - test_eps 10 <class 'int'> | |
| 2022-11-28 15:46:29 - r - INFO: - eval_eps 10 <class 'int'> | |
| 2022-11-28 15:46:29 - r - INFO: - eval_per_episode 5 <class 'int'> | |
| 2022-11-28 15:46:29 - r - INFO: - max_steps 200 <class 'int'> | |
| 2022-11-28 15:46:29 - r - INFO: - load_checkpoint 1 <class 'bool'> | |
| 2022-11-28 15:46:29 - r - INFO: - load_path Train_FrozenLakeNoSlippery-v1_QLearning_20221128-152949 <class 'str'> | |
| 2022-11-28 15:46:29 - r - INFO: - show_fig 0 <class 'bool'> | |
| 2022-11-28 15:46:29 - r - INFO: - save_fig 1 <class 'bool'> | |
| 2022-11-28 15:46:29 - r - INFO: - render_mode human <class 'str'> | |
| 2022-11-28 15:46:29 - r - INFO: - epsilon_start 0.7 <class 'float'> | |
| 2022-11-28 15:46:29 - r - INFO: - epsilon_end 0.1 <class 'float'> | |
| 2022-11-28 15:46:29 - r - INFO: - epsilon_decay 2000 <class 'int'> | |
| 2022-11-28 15:46:29 - r - INFO: - gamma 0.95 <class 'float'> | |
| 2022-11-28 15:46:29 - r - INFO: - lr 0.9 <class 'float'> | |
| 2022-11-28 15:46:29 - r - INFO: - ================================================================================ | |
| 2022-11-28 15:46:30 - r - INFO: - n_states: 16, n_actions: 4 | |
| 2022-11-28 15:46:30 - r - INFO: - Start testing! | |
| 2022-11-28 15:46:30 - r - INFO: - Env: FrozenLakeNoSlippery-v1, Algorithm: QLearning, Device: cpu | |
| 2022-11-28 15:46:33 - r - INFO: - Episode: 1/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:35 - r - INFO: - Episode: 2/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:37 - r - INFO: - Episode: 3/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:39 - r - INFO: - Episode: 4/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:40 - r - INFO: - Episode: 5/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:42 - r - INFO: - Episode: 6/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:44 - r - INFO: - Episode: 7/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:46 - r - INFO: - Episode: 8/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:47 - r - INFO: - Episode: 9/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:49 - r - INFO: - Episode: 10/10, Reward: 1.000, Step: 6 | |
| 2022-11-28 15:46:49 - r - INFO: - Finish testing! | |