johnjim0816's picture
update CartPole-v1 NoisyDQN
54d82df
raw
history blame
3.97 kB
2023-01-11 13:25:42 - r - INFO: - Hyperparameters:
2023-01-11 13:25:42 - r - INFO: - ================================================================================
2023-01-11 13:25:42 - r - INFO: - Name Value Type
2023-01-11 13:25:42 - r - INFO: - env_name CartPole-v1 <class 'str'>
2023-01-11 13:25:42 - r - INFO: - new_step_api 1 <class 'bool'>
2023-01-11 13:25:42 - r - INFO: - wrapper None <class 'str'>
2023-01-11 13:25:42 - r - INFO: - render 0 <class 'bool'>
2023-01-11 13:25:42 - r - INFO: - algo_name A3C <class 'str'>
2023-01-11 13:25:42 - r - INFO: - mode train <class 'str'>
2023-01-11 13:25:42 - r - INFO: - seed 1 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - device cpu <class 'str'>
2023-01-11 13:25:42 - r - INFO: - train_eps 1000 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - test_eps 10 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - eval_eps 10 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - eval_per_episode 5 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - max_steps 200 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - load_checkpoint 0 <class 'bool'>
2023-01-11 13:25:42 - r - INFO: - load_path Train_CartPole-v1_DQN_20221026-054757 <class 'str'>
2023-01-11 13:25:42 - r - INFO: - show_fig 0 <class 'bool'>
2023-01-11 13:25:42 - r - INFO: - save_fig 1 <class 'bool'>
2023-01-11 13:25:42 - r - INFO: - n_workers 10 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - gamma 0.99 <class 'float'>
2023-01-11 13:25:42 - r - INFO: - actor_lr 0.0003 <class 'float'>
2023-01-11 13:25:42 - r - INFO: - critic_lr 0.001 <class 'float'>
2023-01-11 13:25:42 - r - INFO: - actor_hidden_dim 256 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - critic_hidden_dim 256 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - entropy_coef 0.001 <class 'float'>
2023-01-11 13:25:42 - r - INFO: - update_freq 20 <class 'int'>
2023-01-11 13:25:42 - r - INFO: - continuous 0 <class 'bool'>
2023-01-11 13:25:42 - r - INFO: - task_dir /Users/jj/Desktop/rl-tutorials/joyrl/tasks/Train_CartPole-v1_A3C_20230111-132542 <class 'str'>
2023-01-11 13:25:42 - r - INFO: - model_dir /Users/jj/Desktop/rl-tutorials/joyrl/tasks/Train_CartPole-v1_A3C_20230111-132542/models <class 'str'>
2023-01-11 13:25:42 - r - INFO: - res_dir /Users/jj/Desktop/rl-tutorials/joyrl/tasks/Train_CartPole-v1_A3C_20230111-132542/results <class 'str'>
2023-01-11 13:25:42 - r - INFO: - log_dir /Users/jj/Desktop/rl-tutorials/joyrl/tasks/Train_CartPole-v1_A3C_20230111-132542/logs <class 'str'>
2023-01-11 13:25:42 - r - INFO: - traj_dir /Users/jj/Desktop/rl-tutorials/joyrl/tasks/Train_CartPole-v1_A3C_20230111-132542/traj <class 'str'>
2023-01-11 13:25:42 - r - INFO: - ================================================================================
2023-01-11 13:25:42 - r - INFO: - n_states: 4, n_actions: 2
2023-01-11 13:25:43 - r - INFO: - Start training!
2023-01-11 13:25:43 - r - INFO: - Env: CartPole-v1, Algorithm: A3C, Device: cpu
2023-01-11 13:26:03 - r - INFO: - Finish training!