johnjim0816's picture
update CartPole-v1 NoisyDQN
54d82df
raw
history blame
3.82 kB
2022-12-04 00:36:59 - r - INFO: - Hyperparameters:
2022-12-04 00:36:59 - r - INFO: - ================================================================================
2022-12-04 00:36:59 - r - INFO: - Name Value Type
2022-12-04 00:36:59 - r - INFO: - env_name CartPole-v1 <class 'str'>
2022-12-04 00:36:59 - r - INFO: - new_step_api 1 <class 'bool'>
2022-12-04 00:36:59 - r - INFO: - wrapper None <class 'str'>
2022-12-04 00:36:59 - r - INFO: - render 0 <class 'bool'>
2022-12-04 00:36:59 - r - INFO: - algo_name A2C <class 'str'>
2022-12-04 00:36:59 - r - INFO: - mode test <class 'str'>
2022-12-04 00:36:59 - r - INFO: - seed 1 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - device cpu <class 'str'>
2022-12-04 00:36:59 - r - INFO: - train_eps 1000 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - test_eps 10 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - eval_eps 10 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - eval_per_episode 5 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - max_steps 200 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - load_checkpoint 1 <class 'bool'>
2022-12-04 00:36:59 - r - INFO: - load_path Train_CartPole-v1_A2C_20221204-003439 <class 'str'>
2022-12-04 00:36:59 - r - INFO: - show_fig 0 <class 'bool'>
2022-12-04 00:36:59 - r - INFO: - save_fig 1 <class 'bool'>
2022-12-04 00:36:59 - r - INFO: - continuous 0 <class 'bool'>
2022-12-04 00:36:59 - r - INFO: - gamma 0.99 <class 'float'>
2022-12-04 00:36:59 - r - INFO: - actor_lr 0.0003 <class 'float'>
2022-12-04 00:36:59 - r - INFO: - critic_lr 0.001 <class 'float'>
2022-12-04 00:36:59 - r - INFO: - actor_hidden_dim 256 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - critic_hidden_dim 256 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - entropy_coef 0.001 <class 'float'>
2022-12-04 00:36:59 - r - INFO: - update_freq 20 <class 'int'>
2022-12-04 00:36:59 - r - INFO: - ================================================================================
2022-12-04 00:37:00 - r - INFO: - n_states: 4, n_actions: 2
2022-12-04 00:37:00 - r - INFO: - Start testing!
2022-12-04 00:37:00 - r - INFO: - Env: CartPole-v1, Algorithm: A2C, Device: cpu
2022-12-04 00:37:00 - r - INFO: - Episode: 1/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 2/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 3/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 4/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 5/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 6/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 7/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 8/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 9/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Episode: 10/10, Reward: 200.000, Step: 200
2022-12-04 00:37:00 - r - INFO: - Finish testing!