2022-12-03 14:34:30 - r - INFO: - Hyperparameters: 2022-12-03 14:34:30 - r - INFO: - ================================================================================ 2022-12-03 14:34:30 - r - INFO: - Name Value Type 2022-12-03 14:34:30 - r - INFO: - env_name CartPole-v1 2022-12-03 14:34:30 - r - INFO: - new_step_api 1 2022-12-03 14:34:30 - r - INFO: - wrapper None 2022-12-03 14:34:30 - r - INFO: - render 0 2022-12-03 14:34:30 - r - INFO: - algo_name REINFORCE 2022-12-03 14:34:30 - r - INFO: - mode test 2022-12-03 14:34:30 - r - INFO: - seed 1 2022-12-03 14:34:30 - r - INFO: - device cpu 2022-12-03 14:34:30 - r - INFO: - train_eps 200 2022-12-03 14:34:30 - r - INFO: - test_eps 10 2022-12-03 14:34:30 - r - INFO: - eval_eps 10 2022-12-03 14:34:30 - r - INFO: - eval_per_episode 5 2022-12-03 14:34:30 - r - INFO: - max_steps 200 2022-12-03 14:34:30 - r - INFO: - load_checkpoint 1 2022-12-03 14:34:30 - r - INFO: - load_path Train_CartPole-v1_REINFORCE_20221203-143307 2022-12-03 14:34:30 - r - INFO: - show_fig 0 2022-12-03 14:34:30 - r - INFO: - save_fig 1 2022-12-03 14:34:30 - r - INFO: - lr 0.01 2022-12-03 14:34:30 - r - INFO: - gamma 0.99 2022-12-03 14:34:30 - r - INFO: - hidden_dim 36 2022-12-03 14:34:30 - r - INFO: - update_freq 200 2022-12-03 14:34:30 - r - INFO: - ================================================================================ 2022-12-03 14:34:31 - r - INFO: - n_states: 4, n_actions: 2 2022-12-03 14:34:31 - r - INFO: - Start testing! 2022-12-03 14:34:31 - r - INFO: - Env: CartPole-v1, Algorithm: REINFORCE, Device: cpu 2022-12-03 14:34:31 - r - INFO: - Episode: 1/10, Reward: 200.000, Step: 200 2022-12-03 14:34:31 - r - INFO: - Episode: 2/10, Reward: 200.000, Step: 200 2022-12-03 14:34:31 - r - INFO: - Episode: 3/10, Reward: 200.000, Step: 200 2022-12-03 14:34:31 - r - INFO: - Episode: 4/10, Reward: 200.000, Step: 200 2022-12-03 14:34:31 - r - INFO: - Episode: 5/10, Reward: 200.000, Step: 200 2022-12-03 14:34:31 - r - INFO: - Episode: 6/10, Reward: 200.000, Step: 200 2022-12-03 14:34:31 - r - INFO: - Episode: 7/10, Reward: 200.000, Step: 200 2022-12-03 14:34:32 - r - INFO: - Episode: 8/10, Reward: 200.000, Step: 200 2022-12-03 14:34:32 - r - INFO: - Episode: 9/10, Reward: 200.000, Step: 200 2022-12-03 14:34:32 - r - INFO: - Episode: 10/10, Reward: 200.000, Step: 200 2022-12-03 14:34:32 - r - INFO: - Finish testing!