| 2022-11-28 15:58:53 - r - INFO: - Hyperparameters: | |
| 2022-11-28 15:58:53 - r - INFO: - ================================================================================ | |
| 2022-11-28 15:58:53 - r - INFO: - Name Value Type | |
| 2022-11-28 15:58:53 - r - INFO: - env_name Racetrack-v0 <class 'str'> | |
| 2022-11-28 15:58:53 - r - INFO: - new_step_api 1 <class 'bool'> | |
| 2022-11-28 15:58:53 - r - INFO: - wrapper None <class 'str'> | |
| 2022-11-28 15:58:53 - r - INFO: - render 1 <class 'bool'> | |
| 2022-11-28 15:58:53 - r - INFO: - algo_name QLearning <class 'str'> | |
| 2022-11-28 15:58:53 - r - INFO: - mode test <class 'str'> | |
| 2022-11-28 15:58:53 - r - INFO: - seed 10 <class 'int'> | |
| 2022-11-28 15:58:53 - r - INFO: - device cpu <class 'str'> | |
| 2022-11-28 15:58:53 - r - INFO: - train_eps 400 <class 'int'> | |
| 2022-11-28 15:58:53 - r - INFO: - test_eps 20 <class 'int'> | |
| 2022-11-28 15:58:53 - r - INFO: - eval_eps 10 <class 'int'> | |
| 2022-11-28 15:58:53 - r - INFO: - eval_per_episode 5 <class 'int'> | |
| 2022-11-28 15:58:53 - r - INFO: - max_steps 200 <class 'int'> | |
| 2022-11-28 15:58:53 - r - INFO: - load_checkpoint 1 <class 'bool'> | |
| 2022-11-28 15:58:53 - r - INFO: - load_path Train_Racetrack-v0_QLearning_20221128-154935 <class 'str'> | |
| 2022-11-28 15:58:53 - r - INFO: - show_fig 0 <class 'bool'> | |
| 2022-11-28 15:58:53 - r - INFO: - save_fig 1 <class 'bool'> | |
| 2022-11-28 15:58:53 - r - INFO: - render_mode human <class 'str'> | |
| 2022-11-28 15:58:53 - r - INFO: - epsilon_start 0.95 <class 'float'> | |
| 2022-11-28 15:58:53 - r - INFO: - epsilon_end 0.01 <class 'float'> | |
| 2022-11-28 15:58:53 - r - INFO: - epsilon_decay 300 <class 'int'> | |
| 2022-11-28 15:58:53 - r - INFO: - gamma 0.9 <class 'float'> | |
| 2022-11-28 15:58:53 - r - INFO: - lr 0.1 <class 'float'> | |
| 2022-11-28 15:58:53 - r - INFO: - ================================================================================ | |
| 2022-11-28 15:58:54 - r - INFO: - n_states: 4, n_actions: 9 | |
| 2022-11-28 15:58:54 - r - INFO: - Start testing! | |
| 2022-11-28 15:58:54 - r - INFO: - Env: Racetrack-v0, Algorithm: QLearning, Device: cpu | |
| 2022-11-28 15:58:56 - r - INFO: - Episode: 1/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:58:56 - r - INFO: - Episode: 2/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:58:59 - r - INFO: - Episode: 3/20, Reward: -13.000, Step: 13 | |
| 2022-11-28 15:59:00 - r - INFO: - Episode: 4/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:01 - r - INFO: - Episode: 5/20, Reward: 3.000, Step: 7 | |
| 2022-11-28 15:59:03 - r - INFO: - Episode: 6/20, Reward: -13.000, Step: 13 | |
| 2022-11-28 15:59:04 - r - INFO: - Episode: 7/20, Reward: 2.000, Step: 8 | |
| 2022-11-28 15:59:06 - r - INFO: - Episode: 8/20, Reward: -12.000, Step: 12 | |
| 2022-11-28 15:59:07 - r - INFO: - Episode: 9/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:08 - r - INFO: - Episode: 10/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:09 - r - INFO: - Episode: 11/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:10 - r - INFO: - Episode: 12/20, Reward: 3.000, Step: 7 | |
| 2022-11-28 15:59:11 - r - INFO: - Episode: 13/20, Reward: 2.000, Step: 8 | |
| 2022-11-28 15:59:12 - r - INFO: - Episode: 14/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:13 - r - INFO: - Episode: 15/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:14 - r - INFO: - Episode: 16/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:15 - r - INFO: - Episode: 17/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:16 - r - INFO: - Episode: 18/20, Reward: 4.000, Step: 6 | |
| 2022-11-28 15:59:18 - r - INFO: - Episode: 19/20, Reward: 1.000, Step: 9 | |
| 2022-11-28 15:59:19 - r - INFO: - Episode: 20/20, Reward: 3.000, Step: 7 | |
| 2022-11-28 15:59:19 - r - INFO: - Finish testing! | |