johnjim0816's picture
update CartPole-v1 NoisyDQN
54d82df
raw
history blame
5.19 kB
2023-04-09 16:01:45 - r - INFO: - Hyperparameters:
2023-04-09 16:01:45 - r - INFO: - ================================================================================
2023-04-09 16:01:45 - r - INFO: - Name Value Type
2023-04-09 16:01:45 - r - INFO: - env_name CartPole-v1 <class 'str'>
2023-04-09 16:01:45 - r - INFO: - new_step_api 1 <class 'bool'>
2023-04-09 16:01:45 - r - INFO: - wrapper None <class 'str'>
2023-04-09 16:01:45 - r - INFO: - render 0 <class 'bool'>
2023-04-09 16:01:45 - r - INFO: - render_mode human <class 'str'>
2023-04-09 16:01:45 - r - INFO: - algo_name CQL <class 'str'>
2023-04-09 16:01:45 - r - INFO: - mode test <class 'str'>
2023-04-09 16:01:45 - r - INFO: - mp_backend mp <class 'str'>
2023-04-09 16:01:45 - r - INFO: - seed 1 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - device cpu <class 'str'>
2023-04-09 16:01:45 - r - INFO: - train_eps 300 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - test_eps 10 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - eval_eps 10 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - eval_per_episode 5 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - max_steps 200 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - load_checkpoint 1 <class 'bool'>
2023-04-09 16:01:45 - r - INFO: - load_path Train_CartPole-v1_CQL_20230408-183652 <class 'str'>
2023-04-09 16:01:45 - r - INFO: - show_fig 1 <class 'bool'>
2023-04-09 16:01:45 - r - INFO: - save_fig 1 <class 'bool'>
2023-04-09 16:01:45 - r - INFO: - epsilon_start 0.95 <class 'float'>
2023-04-09 16:01:45 - r - INFO: - epsilon_end 0.01 <class 'float'>
2023-04-09 16:01:45 - r - INFO: - epsilon_decay 500 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - gamma 0.99 <class 'float'>
2023-04-09 16:01:45 - r - INFO: - tau 0.001 <class 'float'>
2023-04-09 16:01:45 - r - INFO: - lr 0.001 <class 'float'>
2023-04-09 16:01:45 - r - INFO: - buffer_size 100000 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - batch_size 64 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - target_update 4 <class 'int'>
2023-04-09 16:01:45 - r - INFO: - value_layers [{'activation': 'relu', 'layer_dim': ['n_states', 256], 'layer_type': 'linear'}, {'activation': 'relu', 'layer_dim': [256, 256], 'layer_type': 'linear'}, {'activation': 'none', 'layer_dim': [256, 'n_actions'], 'layer_type': 'linear'}] <class 'str'>
2023-04-09 16:01:45 - r - INFO: - task_dir D:\MyDoc\joyrl\joyrl-offline/tasks/Test_CartPole-v1_CQL_20230409-160145 <class 'str'>
2023-04-09 16:01:45 - r - INFO: - res_dir D:\MyDoc\joyrl\joyrl-offline/tasks/Test_CartPole-v1_CQL_20230409-160145/results <class 'str'>
2023-04-09 16:01:45 - r - INFO: - log_dir D:\MyDoc\joyrl\joyrl-offline/tasks/Test_CartPole-v1_CQL_20230409-160145/logs <class 'str'>
2023-04-09 16:01:45 - r - INFO: - traj_dir D:\MyDoc\joyrl\joyrl-offline/tasks/Test_CartPole-v1_CQL_20230409-160145/traj <class 'str'>
2023-04-09 16:01:45 - r - INFO: - video_dir D:\MyDoc\joyrl\joyrl-offline/tasks/Test_CartPole-v1_CQL_20230409-160145/videos <class 'str'>
2023-04-09 16:01:45 - r - INFO: - ================================================================================
2023-04-09 16:01:45 - r - INFO: - n_states: 4, n_actions: 2
2023-04-09 16:01:45 - r - INFO: - Start testing!
2023-04-09 16:01:45 - r - INFO: - Env: CartPole-v1, Algorithm: CQL, Device: cpu
2023-04-09 16:01:45 - r - INFO: - Episode: 1/10, Reward: 200.000, Step: 200
2023-04-09 16:01:45 - r - INFO: - Episode: 2/10, Reward: 200.000, Step: 200
2023-04-09 16:01:45 - r - INFO: - Episode: 3/10, Reward: 200.000, Step: 200
2023-04-09 16:01:45 - r - INFO: - Episode: 4/10, Reward: 200.000, Step: 200
2023-04-09 16:01:46 - r - INFO: - Episode: 5/10, Reward: 200.000, Step: 200
2023-04-09 16:01:46 - r - INFO: - Episode: 6/10, Reward: 200.000, Step: 200
2023-04-09 16:01:46 - r - INFO: - Episode: 7/10, Reward: 200.000, Step: 200
2023-04-09 16:01:46 - r - INFO: - Episode: 8/10, Reward: 200.000, Step: 200
2023-04-09 16:01:46 - r - INFO: - Episode: 9/10, Reward: 200.000, Step: 200
2023-04-09 16:01:46 - r - INFO: - Episode: 10/10, Reward: 200.000, Step: 200
2023-04-09 16:01:46 - r - INFO: - Finish testing!