gsc579's picture
Test_CartPole-v1_A2C
85cfc10
raw
history blame
18.3 kB
2023-06-24 15:30:29 - SimpleLog - INFO: - General Configs:
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
2023-06-24 15:30:29 - SimpleLog - INFO: - Name Value Type
2023-06-24 15:30:29 - SimpleLog - INFO: - env_name gym <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - algo_name A2C <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - mode test <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - device cpu <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - seed 1 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - max_episode 100 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - max_step 200 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
2023-06-24 15:30:29 - SimpleLog - INFO: - mp_backend single <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - n_workers 2 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - n_learners 1 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
2023-06-24 15:30:29 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
2023-06-24 15:30:29 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - model_save_fre 10 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
2023-06-24 15:30:29 - SimpleLog - INFO: - load_path Train_CartPole-v1_A2C_20230623-223515 <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - load_model_step best <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
2023-06-24 15:30:29 - SimpleLog - INFO: - Algo Configs:
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
2023-06-24 15:30:29 - SimpleLog - INFO: - Name Value Type
2023-06-24 15:30:29 - SimpleLog - INFO: - independ_actor 1 <class 'bool'>
2023-06-24 15:30:29 - SimpleLog - INFO: - share_optimizer 0 <class 'bool'>
2023-06-24 15:30:29 - SimpleLog - INFO: - action_type discrete <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - gamma 0.98 <class 'float'>
2023-06-24 15:30:29 - SimpleLog - INFO: - k_epochs 4 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
2023-06-24 15:30:29 - SimpleLog - INFO: - actor_lr 0.001 <class 'float'>
2023-06-24 15:30:29 - SimpleLog - INFO: - critic_lr 0.01 <class 'float'>
2023-06-24 15:30:29 - SimpleLog - INFO: - critic_loss_coef 0.5 <class 'float'>
2023-06-24 15:30:29 - SimpleLog - INFO: - entropy_coef 0.01 <class 'float'>
2023-06-24 15:30:29 - SimpleLog - INFO: - buffer_type ONPOLICY_QUE <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - batch_size 256 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - sgd_batch_size 128 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - actor_hidden_dim 256 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - critic_hidden_dim 256 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - min_policy 0 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'>
2023-06-24 15:30:29 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [128], 'activation': 'relu'}] <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [128], 'activation': 'relu'}] <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
2023-06-24 15:30:29 - SimpleLog - INFO: - Env Configs:
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
2023-06-24 15:30:29 - SimpleLog - INFO: - Name Value Type
2023-06-24 15:30:29 - SimpleLog - INFO: - id CartPole-v1 <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - render_mode None <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - wrapper None <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
2023-06-24 15:30:29 - SimpleLog - INFO: - ================================================================================
2023-06-24 15:30:29 - SimpleLog - INFO: - Start testing!
2023-06-24 15:30:29 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward 200.000 in 200 steps
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 1 finished episode 2 with reward 200.000 in 200 steps
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward 200.000 in 200 steps
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward 200.000 in 200 steps
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 200.000 in 200 steps
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward 200.000 in 200 steps
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward 200.000 in 200 steps
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 0 finished episode 8 with reward 200.000 in 200 steps
2023-06-24 15:30:30 - SimpleLog - INFO: - Interactor 1 finished episode 9 with reward 200.000 in 200 steps
2023-06-24 15:30:31 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward 200.000 in 200 steps
2023-06-24 15:30:31 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward 200.000 in 200 steps
2023-06-24 15:30:31 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward 200.000 in 200 steps
2023-06-24 15:30:31 - SimpleLog - INFO: - update_step: 10, online_eval_reward: 200.000
2023-06-24 15:30:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
2023-06-24 15:30:31 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward 200.000 in 200 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward 200.000 in 200 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward 200.000 in 200 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 1 finished episode 16 with reward 200.000 in 200 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 17 with reward 200.000 in 200 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 18 with reward 18.000 in 18 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 19 with reward 200.000 in 200 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward 200.000 in 200 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 1 finished episode 21 with reward 200.000 in 200 steps
2023-06-24 15:30:32 - SimpleLog - INFO: - Interactor 0 finished episode 22 with reward 200.000 in 200 steps
2023-06-24 15:30:33 - SimpleLog - INFO: - Interactor 1 finished episode 23 with reward 200.000 in 200 steps
2023-06-24 15:30:33 - SimpleLog - INFO: - Interactor 0 finished episode 24 with reward 200.000 in 200 steps
2023-06-24 15:30:33 - SimpleLog - INFO: - Interactor 1 finished episode 25 with reward 200.000 in 200 steps
2023-06-24 15:30:33 - SimpleLog - INFO: - update_step: 20, online_eval_reward: 200.000
2023-06-24 15:30:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 26 with reward 200.000 in 200 steps
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 1 finished episode 27 with reward 200.000 in 200 steps
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward 200.000 in 200 steps
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward 200.000 in 200 steps
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 30 with reward 200.000 in 200 steps
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 1 finished episode 31 with reward 200.000 in 200 steps
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 32 with reward 200.000 in 200 steps
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 1 finished episode 33 with reward 200.000 in 200 steps
2023-06-24 15:30:34 - SimpleLog - INFO: - Interactor 0 finished episode 34 with reward 200.000 in 200 steps
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 1 finished episode 35 with reward 200.000 in 200 steps
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 0 finished episode 36 with reward 200.000 in 200 steps
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward 200.000 in 200 steps
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward 200.000 in 200 steps
2023-06-24 15:30:35 - SimpleLog - INFO: - Interactor 1 finished episode 39 with reward 200.000 in 200 steps
2023-06-24 15:30:35 - SimpleLog - INFO: - update_step: 30, online_eval_reward: 200.000
2023-06-24 15:30:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 0 finished episode 40 with reward 200.000 in 200 steps
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 1 finished episode 41 with reward 200.000 in 200 steps
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 0 finished episode 42 with reward 200.000 in 200 steps
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 1 finished episode 43 with reward 200.000 in 200 steps
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 0 finished episode 44 with reward 200.000 in 200 steps
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 1 finished episode 45 with reward 200.000 in 200 steps
2023-06-24 15:30:36 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward 200.000 in 200 steps
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward 200.000 in 200 steps
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 0 finished episode 48 with reward 200.000 in 200 steps
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 1 finished episode 49 with reward 200.000 in 200 steps
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 0 finished episode 50 with reward 200.000 in 200 steps
2023-06-24 15:30:37 - SimpleLog - INFO: - Interactor 1 finished episode 51 with reward 200.000 in 200 steps
2023-06-24 15:30:38 - SimpleLog - INFO: - update_step: 40, online_eval_reward: 200.000
2023-06-24 15:30:38 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 0 finished episode 52 with reward 200.000 in 200 steps
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 1 finished episode 53 with reward 198.000 in 198 steps
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 0 finished episode 54 with reward 200.000 in 200 steps
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward 200.000 in 200 steps
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward 200.000 in 200 steps
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 1 finished episode 57 with reward 200.000 in 200 steps
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 0 finished episode 58 with reward 200.000 in 200 steps
2023-06-24 15:30:38 - SimpleLog - INFO: - Interactor 1 finished episode 59 with reward 200.000 in 200 steps
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 0 finished episode 60 with reward 200.000 in 200 steps
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 1 finished episode 61 with reward 200.000 in 200 steps
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 0 finished episode 62 with reward 200.000 in 200 steps
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward 200.000 in 200 steps
2023-06-24 15:30:39 - SimpleLog - INFO: - Interactor 1 finished episode 64 with reward 200.000 in 200 steps
2023-06-24 15:30:40 - SimpleLog - INFO: - update_step: 50, online_eval_reward: 200.000
2023-06-24 15:30:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 0 finished episode 65 with reward 200.000 in 200 steps
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 0 finished episode 66 with reward 200.000 in 200 steps
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 1 finished episode 67 with reward 200.000 in 200 steps
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 0 finished episode 68 with reward 200.000 in 200 steps
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 1 finished episode 69 with reward 200.000 in 200 steps
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 0 finished episode 70 with reward 200.000 in 200 steps
2023-06-24 15:30:40 - SimpleLog - INFO: - Interactor 1 finished episode 71 with reward 200.000 in 200 steps
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 0 finished episode 72 with reward 200.000 in 200 steps
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 0 finished episode 73 with reward 200.000 in 200 steps
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward 200.000 in 200 steps
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 1 finished episode 75 with reward 200.000 in 200 steps
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 0 finished episode 76 with reward 200.000 in 200 steps
2023-06-24 15:30:41 - SimpleLog - INFO: - Interactor 1 finished episode 77 with reward 200.000 in 200 steps
2023-06-24 15:30:42 - SimpleLog - INFO: - update_step: 60, online_eval_reward: 200.000
2023-06-24 15:30:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 0 finished episode 78 with reward 200.000 in 200 steps
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 1 finished episode 79 with reward 200.000 in 200 steps
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 0 finished episode 80 with reward 200.000 in 200 steps
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 1 finished episode 81 with reward 200.000 in 200 steps
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 0 finished episode 82 with reward 200.000 in 200 steps
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward 200.000 in 200 steps
2023-06-24 15:30:42 - SimpleLog - INFO: - Interactor 1 finished episode 84 with reward 200.000 in 200 steps
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 1 finished episode 85 with reward 200.000 in 200 steps
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 0 finished episode 86 with reward 200.000 in 200 steps
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 1 finished episode 87 with reward 200.000 in 200 steps
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 0 finished episode 88 with reward 200.000 in 200 steps
2023-06-24 15:30:43 - SimpleLog - INFO: - Interactor 1 finished episode 89 with reward 200.000 in 200 steps
2023-06-24 15:30:44 - SimpleLog - INFO: - update_step: 70, online_eval_reward: 200.000
2023-06-24 15:30:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 90 with reward 200.000 in 200 steps
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 1 finished episode 91 with reward 200.000 in 200 steps
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 1 finished episode 92 with reward 200.000 in 200 steps
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 93 with reward 200.000 in 200 steps
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 94 with reward 200.000 in 200 steps
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 95 with reward 11.000 in 11 steps
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 1 finished episode 96 with reward 200.000 in 200 steps
2023-06-24 15:30:44 - SimpleLog - INFO: - Interactor 0 finished episode 97 with reward 200.000 in 200 steps
2023-06-24 15:30:45 - SimpleLog - INFO: - Interactor 1 finished episode 98 with reward 200.000 in 200 steps
2023-06-24 15:30:45 - SimpleLog - INFO: - Interactor 0 finished episode 99 with reward 200.000 in 200 steps
2023-06-24 15:30:45 - SimpleLog - INFO: - Interactor 1 finished episode 100 with reward 200.000 in 200 steps
2023-06-24 15:30:45 - SimpleLog - INFO: - Finish testing! Time cost: 15.808 s