johnjim0816
add all benchmarks
62e03a2
raw
history blame
5.46 kB
2023-03-29 23:48:02 - r - INFO: - Hyperparameters:
2023-03-29 23:48:02 - r - INFO: - ================================================================================
2023-03-29 23:48:02 - r - INFO: - Name Value Type
2023-03-29 23:48:02 - r - INFO: - env_name deep-sea-treasure-v0 <class 'str'>
2023-03-29 23:48:02 - r - INFO: - new_step_api 1 <class 'bool'>
2023-03-29 23:48:02 - r - INFO: - wrapper None <class 'str'>
2023-03-29 23:48:02 - r - INFO: - render 0 <class 'bool'>
2023-03-29 23:48:02 - r - INFO: - algo_name MO-QLearning <class 'str'>
2023-03-29 23:48:02 - r - INFO: - mode test <class 'str'>
2023-03-29 23:48:02 - r - INFO: - seed 0 <class 'int'>
2023-03-29 23:48:02 - r - INFO: - device cpu <class 'str'>
2023-03-29 23:48:02 - r - INFO: - train_eps 100 <class 'int'>
2023-03-29 23:48:02 - r - INFO: - test_eps 20 <class 'int'>
2023-03-29 23:48:02 - r - INFO: - eval_eps 10 <class 'int'>
2023-03-29 23:48:02 - r - INFO: - eval_per_episode 5 <class 'int'>
2023-03-29 23:48:02 - r - INFO: - max_steps 200 <class 'int'>
2023-03-29 23:48:02 - r - INFO: - load_checkpoint 0 <class 'bool'>
2023-03-29 23:48:02 - r - INFO: - load_path tasks <class 'str'>
2023-03-29 23:48:02 - r - INFO: - show_fig 0 <class 'bool'>
2023-03-29 23:48:02 - r - INFO: - save_fig 1 <class 'bool'>
2023-03-29 23:48:02 - r - INFO: - epsilon_start 0.95 <class 'float'>
2023-03-29 23:48:02 - r - INFO: - epsilon_end 0.01 <class 'float'>
2023-03-29 23:48:02 - r - INFO: - epsilon_decay 300 <class 'int'>
2023-03-29 23:48:02 - r - INFO: - gamma 0.9 <class 'float'>
2023-03-29 23:48:02 - r - INFO: - lr 0.1 <class 'float'>
2023-03-29 23:48:02 - r - INFO: - weights [0.5, 0.5] <class 'str'>
2023-03-29 23:48:02 - r - INFO: - task_dir E:\LAMDA\ongoing work\joyrl\joyrl-offline/tasks/Test_deep-sea-treasure-v0_MO-QLearning_20230329-234802 <class 'str'>
2023-03-29 23:48:02 - r - INFO: - res_dir E:\LAMDA\ongoing work\joyrl\joyrl-offline/tasks/Test_deep-sea-treasure-v0_MO-QLearning_20230329-234802/results <class 'str'>
2023-03-29 23:48:02 - r - INFO: - log_dir E:\LAMDA\ongoing work\joyrl\joyrl-offline/tasks/Test_deep-sea-treasure-v0_MO-QLearning_20230329-234802/logs <class 'str'>
2023-03-29 23:48:02 - r - INFO: - traj_dir E:\LAMDA\ongoing work\joyrl\joyrl-offline/tasks/Test_deep-sea-treasure-v0_MO-QLearning_20230329-234802/traj <class 'str'>
2023-03-29 23:48:02 - r - INFO: - tb_dir E:\LAMDA\ongoing work\joyrl\joyrl-offline/tasks/Test_deep-sea-treasure-v0_MO-QLearning_20230329-234802/tb_logs <class 'str'>
2023-03-29 23:48:02 - r - INFO: - ================================================================================
2023-03-29 23:48:02 - r - INFO: - n_states: 2, n_actions: 4
2023-03-29 23:48:02 - r - INFO: - Start testing!
2023-03-29 23:48:02 - r - INFO: - Env: deep-sea-treasure-v0, Algorithm: MO-QLearning, Device: cpu
2023-03-29 23:48:02 - r - INFO: - Episode: 1/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 2/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 3/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 4/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 5/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 6/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 7/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 8/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 9/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 10/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 11/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 12/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 13/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 14/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 15/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 16/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 17/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 18/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 19/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Episode: 20/20, Reward: 0.000,-200.000, Step: 200
2023-03-29 23:48:02 - r - INFO: - Finish testing!