| { | |
| "n_obs_steps": 1, | |
| "chunk_size": 100, | |
| "n_action_steps": 100, | |
| "input_shapes": { | |
| "observation.images.top": [ | |
| 3, | |
| 480, | |
| 640 | |
| ], | |
| "observation.state": [ | |
| 14 | |
| ] | |
| }, | |
| "output_shapes": { | |
| "action": [ | |
| 14 | |
| ] | |
| }, | |
| "input_normalization_modes": { | |
| "observation.images.top": "mean_std", | |
| "observation.state": "mean_std" | |
| }, | |
| "output_normalization_modes": { | |
| "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": 1, | |
| "use_vae": true, | |
| "latent_dim": 32, | |
| "n_vae_encoder_layers": 4, | |
| "use_temporal_aggregation": false, | |
| "dropout": 0.1, | |
| "kl_weight": 10.0 | |
| } |