{ "type": "sac", "n_obs_steps": 1, "normalization_mapping": { "VISUAL": "MEAN_STD", "STATE": "MIN_MAX", "ENV": "MIN_MAX", "ACTION": "MIN_MAX" }, "input_features": { "observation.images.front": { "type": "VISUAL", "shape": [ 3, 128, 128 ] }, "observation.images.wrist": { "type": "VISUAL", "shape": [ 3, 128, 128 ] }, "observation.state": { "type": "STATE", "shape": [ 18 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 3 ] } }, "device": "cuda", "use_amp": false, "push_to_hub": true, "repo_id": "yfynb1111/sac", "private": null, "tags": null, "license": null, "dataset_stats": { "observation.images.front": { "mean": [ 0.485, 0.456, 0.406 ], "std": [ 0.229, 0.224, 0.225 ] }, "observation.images.wrist": { "mean": [ 0.485, 0.456, 0.406 ], "std": [ 0.229, 0.224, 0.225 ] }, "observation.state": { "min": [ -0.6897139549255371, -1.1421763896942139, -0.5745007991790771, -2.97829008102417, -0.2710767090320587, 1.3246592283248901, -0.04057434946298599, -0.21261805295944214, -0.4548068344593048, -0.6540042757987976, -0.3644964098930359, -1.1057522296905518, -0.40768879652023315, -0.2220114767551422, 0.0, 0.19176171720027924, -0.3013063669204712, 0.00362197193317115 ], "max": [ 0.5107022523880005, 0.5516204237937927, 0.5620884299278259, -1.3330878019332886, 0.32758936285972595, 3.119610548019409, 1.8364211320877075, 0.25358933210372925, 0.36316126585006714, 0.14765967428684235, 0.49947625398635864, 0.144814133644104, 0.2820609211921692, 0.7382049560546875, 255.0, 0.6012658476829529, 0.3005995750427246, 0.5004003643989563 ] } }, "storage_device": "cpu", "vision_encoder_name": "helper2424/resnet10", "freeze_vision_encoder": true, "image_encoder_hidden_dim": 32, "shared_encoder": true, "num_discrete_actions": 3, "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": 0.97, "temperature_init": 0.01, "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": 2, "state_encoder_hidden_dim": 256, "latent_dim": 64, "target_entropy": null, "use_backup_entropy": true, "grad_clip_norm": 10.0, "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": 5.0, "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 }