| { | |
| "type": "sac", | |
| "n_obs_steps": 1, | |
| "normalization_mapping": { | |
| "VISUAL": "MEAN_STD", | |
| "STATE": "MIN_MAX", | |
| "ENV": "MIN_MAX", | |
| "ACTION": "MIN_MAX" | |
| }, | |
| "input_features": { | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 6 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 6 | |
| ] | |
| } | |
| }, | |
| "device": "cpu", | |
| "use_amp": false, | |
| "push_to_hub": true, | |
| "repo_id": "bearlover365/multi_sac_smoke", | |
| "private": null, | |
| "tags": null, | |
| "license": null, | |
| "dataset_stats": { | |
| "observation.image": { | |
| "mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ] | |
| }, | |
| "observation.state": { | |
| "min": [ | |
| 0.0, | |
| 0.0 | |
| ], | |
| "max": [ | |
| 1.0, | |
| 1.0 | |
| ] | |
| }, | |
| "action": { | |
| "min": [ | |
| 0.0, | |
| 0.0, | |
| 0.0 | |
| ], | |
| "max": [ | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ] | |
| } | |
| }, | |
| "storage_device": "cpu", | |
| "vision_encoder_name": null, | |
| "freeze_vision_encoder": true, | |
| "image_encoder_hidden_dim": 32, | |
| "shared_encoder": true, | |
| "num_discrete_actions": null, | |
| "image_embedding_pooling_dim": 8, | |
| "online_steps": 1000000, | |
| "online_env_seed": 10000, | |
| "online_buffer_capacity": 100000, | |
| "offline_buffer_capacity": 100000, | |
| "async_prefetch": false, | |
| "online_step_before_learning": 100, | |
| "policy_update_freq": 1, | |
| "discount": 0.99, | |
| "temperature_init": 1.0, | |
| "num_critics": 2, | |
| "num_subsample_critics": null, | |
| "critic_lr": 0.0003, | |
| "actor_lr": 0.0003, | |
| "temperature_lr": 0.0003, | |
| "critic_target_update_weight": 0.005, | |
| "utd_ratio": 1, | |
| "state_encoder_hidden_dim": 256, | |
| "latent_dim": 256, | |
| "target_entropy": null, | |
| "use_backup_entropy": true, | |
| "grad_clip_norm": 40.0, | |
| "critic_network_kwargs": { | |
| "hidden_dims": [ | |
| 256, | |
| 256 | |
| ], | |
| "activate_final": true, | |
| "final_activation": null | |
| }, | |
| "actor_network_kwargs": { | |
| "hidden_dims": [ | |
| 256, | |
| 256 | |
| ], | |
| "activate_final": true | |
| }, | |
| "policy_kwargs": { | |
| "use_tanh_squash": true, | |
| "std_min": 1e-05, | |
| "std_max": 10.0, | |
| "init_final": 0.05 | |
| }, | |
| "discrete_critic_network_kwargs": { | |
| "hidden_dims": [ | |
| 256, | |
| 256 | |
| ], | |
| "activate_final": true, | |
| "final_activation": null | |
| }, | |
| "actor_learner_config": { | |
| "learner_host": "127.0.0.1", | |
| "learner_port": 50051, | |
| "policy_parameters_push_frequency": 4, | |
| "queue_get_timeout": 2 | |
| }, | |
| "concurrency": { | |
| "actor": "threads", | |
| "learner": "threads" | |
| }, | |
| "use_torch_compile": true | |
| } |