| { |
| "type": "act", |
| "n_obs_steps": 1, |
| "normalization_mapping": { |
| "VISUAL": "MEAN_STD", |
| "STATE": "MIN_MAX", |
| "ACTION": "MIN_MAX" |
| }, |
| "input_features": { |
| "observation.state": { |
| "type": "STATE", |
| "shape": [6] |
| }, |
| "observation.images.front": { |
| "type": "VISUAL", |
| "shape": [3, 720, 1280] |
| } |
| }, |
| "output_features": { |
| "action": { |
| "type": "ACTION", |
| "shape": [6] |
| } |
| }, |
| "device": "cuda", |
| "use_amp": false, |
| "chunk_size": 100, |
| "n_action_steps": 100, |
| "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": 1, |
| "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, |
| "normalization_stats": { |
| "STATE": { |
| "type": "MIN_MAX", |
| "min": [-87.9917221069336, -99.32231903076172, -98.47122192382812, -99.39393615722656, -92.20779418945312, 1.2709029912948608], |
| "max": [94.9482421875, 100.0, 99.82014465332031, 100.0, 61.40259552001953, 72.9765853881836] |
| }, |
| "ACTION": { |
| "type": "MIN_MAX", |
| "min": [-87.84749603271484, -100.0, -99.90917205810547, -100.0, -92.48041534423828, 0.0], |
| "max": [95.5520248413086, 100.0, 100.0, 100.0, 61.723236083984375, 73.77326202392578] |
| } |
| } |
| } |
|
|
