| general_cfg: | |
| adversarial_batch_size: 128 | |
| adversarial_epochs: 5 | |
| algo_name: GAIL | |
| batch_size: 2048 | |
| device: cuda | |
| discount: 0.99 | |
| env_name: CartPole-v1 | |
| eval_eps: 10 | |
| eval_per_episode: 5 | |
| hidden_dim: 32 | |
| imitation_replay_size: 4 | |
| load_checkpoint: false | |
| load_path: Collect_CartPole-v1_PPO_20221206-173222 | |
| lr: 0.001 | |
| max_steps: 200 | |
| mode: train | |
| new_step_api: true | |
| num_workers: 8 | |
| ppo_epochs: 5 | |
| r1_reg_coeff: 1 | |
| render: false | |
| save_fig: true | |
| seed: 1 | |
| show_fig: false | |
| test_eps: 10 | |
| train_eps: 1500 | |
| wrapper: null | |
| algo_cfg: | |
| actor_hidden_dim: 256 | |
| actor_lr: 0.0003 | |
| batch_size: 2048 | |
| critic_hidden_dim: 256 | |
| critic_lr: 0.0003 | |
| entropy_coef: 0.01 | |
| eps_clip: 0.2 | |
| gamma: 0.99 | |
| k_epochs: 4 | |
| update_freq: 2048 | |