johnjim0816's picture
update CartPole-v1 NoisyDQN
54d82df
raw
history blame
7.32 kB
2023-05-17 13:48:53 - SimpleLog - INFO: - General Configs:
2023-05-17 13:48:53 - SimpleLog - INFO: - ================================================================================
2023-05-17 13:48:53 - SimpleLog - INFO: - Name Value Type
2023-05-17 13:48:53 - SimpleLog - INFO: - env_name gym <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - algo_name PPO <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - mode test <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - device cpu <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - seed 1 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - max_episode 10 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - max_step 200 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
2023-05-17 13:48:53 - SimpleLog - INFO: - mp_backend single <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - n_workers 2 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
2023-05-17 13:48:53 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - model_save_fre 10 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
2023-05-17 13:48:53 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_PPO_20230517-134440 <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - load_model_step best <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - ================================================================================
2023-05-17 13:48:53 - SimpleLog - INFO: - Algo Configs:
2023-05-17 13:48:53 - SimpleLog - INFO: - ================================================================================
2023-05-17 13:48:53 - SimpleLog - INFO: - Name Value Type
2023-05-17 13:48:53 - SimpleLog - INFO: - independ_actor 1 <class 'bool'>
2023-05-17 13:48:53 - SimpleLog - INFO: - share_optimizer 0 <class 'bool'>
2023-05-17 13:48:53 - SimpleLog - INFO: - ppo_type clip <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - eps_clip 0.2 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - kl_target 0.1 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - kl_lambda 0.5 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - kl_beta 1.5 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - kl_alpha 2 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - continuous 0 <class 'bool'>
2023-05-17 13:48:53 - SimpleLog - INFO: - gamma 0.99 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - k_epochs 4 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - actor_lr 0.0003 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - critic_lr 0.001 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - critic_loss_coef 0.5 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - entropy_coef 0.01 <class 'float'>
2023-05-17 13:48:53 - SimpleLog - INFO: - batch_size 256 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - sgd_batch_size 128 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - actor_hidden_dim 256 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - critic_hidden_dim 256 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - min_policy 0 <class 'int'>
2023-05-17 13:48:53 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_dim': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_dim': [256], 'activation': 'relu'}] <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_dim': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_dim': [256], 'activation': 'relu'}] <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - buffer_type ONPOLICY_QUE <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - ================================================================================
2023-05-17 13:48:53 - SimpleLog - INFO: - Env Configs:
2023-05-17 13:48:53 - SimpleLog - INFO: - ================================================================================
2023-05-17 13:48:53 - SimpleLog - INFO: - Name Value Type
2023-05-17 13:48:53 - SimpleLog - INFO: - id CartPole-v1 <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - render_mode None <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - wrapper None <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
2023-05-17 13:48:53 - SimpleLog - INFO: - ================================================================================
2023-05-17 13:48:53 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2)
2023-05-17 13:48:53 - SimpleLog - INFO: - Start testing!
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 0, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 1, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 2, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 3, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 4, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 5, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 6, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 7, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 8, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - episode: 9, ep_reward: 200.0, ep_step: 200
2023-05-17 13:48:54 - SimpleLog - INFO: - Finish testing! total time consumed: 0.50s