johnjim0816
update DDPG Pendulum-v1
56029d5
2023-05-27 12:07:39 - SimpleLog - INFO: - General Configs:
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type
2023-05-27 12:07:39 - SimpleLog - INFO: - env_name gym <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - algo_name DDPG <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - mode test <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - device cuda <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - seed 10 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - max_episode 10 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - max_step 200 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
2023-05-27 12:07:39 - SimpleLog - INFO: - mp_backend single <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - n_workers 4 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - n_learners 1 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
2023-05-27 12:07:39 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
2023-05-27 12:07:39 - SimpleLog - INFO: - online_eval_episode 20 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - model_save_fre 2000 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
2023-05-27 12:07:39 - SimpleLog - INFO: - load_path Train_ray_Pendulum-v1_DDPG_20230527-001715 <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - load_model_step best <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
2023-05-27 12:07:39 - SimpleLog - INFO: - Algo Configs:
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type
2023-05-27 12:07:39 - SimpleLog - INFO: - action_type dpg <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - buffer_size 8000 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - batch_size 128 <class 'int'>
2023-05-27 12:07:39 - SimpleLog - INFO: - gamma 0.99 <class 'float'>
2023-05-27 12:07:39 - SimpleLog - INFO: - policy_loss_weight 0.002 <class 'float'>
2023-05-27 12:07:39 - SimpleLog - INFO: - critic_lr 0.001 <class 'float'>
2023-05-27 12:07:39 - SimpleLog - INFO: - actor_lr 0.0001 <class 'float'>
2023-05-27 12:07:39 - SimpleLog - INFO: - tau 0.001 <class 'float'>
2023-05-27 12:07:39 - SimpleLog - INFO: - value_min -inf <class 'float'>
2023-05-27 12:07:39 - SimpleLog - INFO: - value_max inf <class 'float'>
2023-05-27 12:07:39 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
2023-05-27 12:07:39 - SimpleLog - INFO: - Env Configs:
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
2023-05-27 12:07:39 - SimpleLog - INFO: - Name Value Type
2023-05-27 12:07:39 - SimpleLog - INFO: - id Pendulum-v1 <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - render_mode rgb_array <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - wrapper None <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
2023-05-27 12:07:39 - SimpleLog - INFO: - ================================================================================
2023-05-27 12:07:39 - SimpleLog - INFO: - obs_space: Box([-1. -1. -8.], [1. 1. 8.], (3,), float32), n_actions: Box(-2.0, 2.0, (1,), float32)
2023-05-27 12:07:40 - SimpleLog - INFO: - Start testing!
2023-05-27 12:07:42 - SimpleLog - INFO: - episode: 0, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:46 - SimpleLog - INFO: - episode: 1, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:46 - SimpleLog - INFO: - episode: 2, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:47 - SimpleLog - INFO: - episode: 3, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:48 - SimpleLog - INFO: - episode: 4, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:48 - SimpleLog - INFO: - episode: 5, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:49 - SimpleLog - INFO: - episode: 6, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:50 - SimpleLog - INFO: - episode: 7, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:51 - SimpleLog - INFO: - episode: 8, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:52 - SimpleLog - INFO: - episode: 9, ep_reward: -253.906, ep_step: 200
2023-05-27 12:07:52 - SimpleLog - INFO: - Finish testing! total time consumed: 12.58s