| general_cfg: | |
| algo_name: MO-QLearning | |
| device: cpu | |
| env_name: deep-sea-treasure-v0 | |
| eval_eps: 10 | |
| eval_per_episode: 5 | |
| load_checkpoint: false | |
| load_path: tasks | |
| max_steps: 200 | |
| mode: train | |
| new_step_api: true | |
| render: false | |
| save_fig: true | |
| seed: 0 | |
| show_fig: false | |
| test_eps: 20 | |
| train_eps: 100 | |
| wrapper: null | |
| algo_cfg: | |
| epsilon_decay: 300 | |
| epsilon_end: 0.01 | |
| epsilon_start: 0.95 | |
| gamma: 0.9 | |
| lr: 0.1 | |
| weights: | |
| - 0.5 | |
| - 0.5 | |