| general_cfg: | |
| algo_name: DynaQ | |
| device: cpu | |
| env_name: CliffWalking-v0 | |
| eval_eps: 10 | |
| eval_per_episode: 5 | |
| load_checkpoint: false | |
| load_path: Train_CliffWalking-v0_DynaQ_20221210-095208 | |
| max_steps: 100 | |
| mode: train | |
| new_step_api: true | |
| render: false | |
| save_fig: true | |
| seed: 1 | |
| show_fig: false | |
| test_eps: 10 | |
| train_eps: 100 | |
| wrapper: envs.wrappers.CliffWalkingWapper | |
| algo_cfg: | |
| epsilon_decay: 300 | |
| epsilon_end: 0.01 | |
| epsilon_start: 0.95 | |
| exploration_type: e-greedy | |
| gamma: 0.99 | |
| lr: 0.1 | |
| n_planning: 10 | |