| general_cfg: | |
| algo_name: SoftQ | |
| collect_traj: false | |
| device: cpu | |
| env_name: gym | |
| interact_summary_fre: 1 | |
| load_checkpoint: false | |
| load_model_step: best | |
| load_path: Train_CartPole-v1_SoftQ_20230702-191520 | |
| max_episode: 200 | |
| max_step: 200 | |
| mode: train | |
| model_save_fre: 500 | |
| model_summary_fre: 1 | |
| mp_backend: null | |
| n_learners: 1 | |
| n_workers: 2 | |
| online_eval: true | |
| online_eval_episode: 10 | |
| seed: 1 | |
| share_buffer: true | |
| algo_cfg: | |
| alpha: 4 | |
| batch_size: 128 | |
| buffer_size: 100000 | |
| buffer_type: REPLAY_QUE | |
| epsilon_decay: 500 | |
| epsilon_end: 0.01 | |
| epsilon_start: 0.95 | |
| gamma: 0.95 | |
| lr: 0.0001 | |
| n_steps_per_learn: 1 | |
| target_update: 4 | |
| value_layers: | |
| - activation: relu | |
| layer_size: | |
| - 256 | |
| layer_type: linear | |
| - activation: relu | |
| layer_size: | |
| - 256 | |
| layer_type: linear | |
| env_cfg: | |
| id: CartPole-v1 | |
| ignore_params: | |
| - wrapper | |
| - ignore_params | |
| render_mode: null | |
| wrapper: null | |