| { |
| "type": "rewact", |
| "n_obs_steps": 1, |
| "input_features": { |
| "observation.state": { |
| "type": "STATE", |
| "shape": [ |
| 6 |
| ] |
| }, |
| "observation.images.top": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 576, |
| 1024 |
| ] |
| }, |
| "observation.images.front": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 576, |
| 1024 |
| ] |
| }, |
| "observation.images.wrist": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 720, |
| 1280 |
| ] |
| } |
| }, |
| "output_features": { |
| "action": { |
| "type": "ACTION", |
| "shape": [ |
| 6 |
| ] |
| } |
| }, |
| "device": "cuda", |
| "use_amp": false, |
| "use_peft": false, |
| "push_to_hub": true, |
| "repo_id": "villekuosmanen/armnetbench_tool_insert_rewact", |
| "private": null, |
| "tags": null, |
| "license": null, |
| "pretrained_path": null, |
| "chunk_size": 100, |
| "n_action_steps": 50, |
| "normalization_mapping": { |
| "VISUAL": "MEAN_STD", |
| "STATE": "MEAN_STD", |
| "ACTION": "MEAN_STD" |
| }, |
| "vision_backbone": "resnet18", |
| "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1", |
| "replace_final_stride_with_dilation": false, |
| "pre_norm": false, |
| "dim_model": 512, |
| "n_heads": 8, |
| "dim_feedforward": 3200, |
| "feedforward_activation": "relu", |
| "n_encoder_layers": 4, |
| "n_decoder_layers": 4, |
| "use_vae": true, |
| "latent_dim": 32, |
| "n_vae_encoder_layers": 4, |
| "temporal_ensemble_coeff": null, |
| "dropout": 0.1, |
| "kl_weight": 10.0, |
| "optimizer_lr": 1e-05, |
| "optimizer_weight_decay": 0.0001, |
| "optimizer_lr_backbone": 1e-05, |
| "use_reward_head": true, |
| "reward_loss_weight": 0.1, |
| "num_value_bins": 100, |
| "value_min": 0, |
| "value_max": 1, |
| "proprio_dropout": 0.5, |
| "vision_encoder_type": "resnet", |
| "freeze_vision_encoder": true, |
| "dinov3": null, |
| "vjepa2": null, |
| "sam3": null |
| } |
