adding configuration gripper index and threshold

This commit is contained in:
Maximellerbach
2026-05-29 14:11:51 +02:00
parent 8e82b2bd1a
commit 6f82adddc1
3 changed files with 29 additions and 11 deletions

View File

@@ -74,6 +74,10 @@ Key parameters in `VLAJEPAConfig`:
| `num_inference_timesteps` | 4 | Euler integration steps for action denoising |
| `freeze_qwen` | `False` | Freeze the Qwen3-VL backbone and only train the action head |
| `reinit_modules` | `None` | Key prefixes allowed to be randomly re-initialised on load (for cross-embodiment transfer, see [Fine-tuning on a different embodiment](#fine-tuning-on-a-different-embodiment)) |
| `gripper_dim` | 6 | Index of the gripper dimension in the action vector (e.g. 6 for a 7-DoF arm with gripper as the last joint) |
| `gripper_threshold` | 0.5 | Threshold used by `pre_snap_gripper_action` and `binarize_gripper_action` to binarize the gripper dimension |
| `pre_snap_gripper_action` | `True` | Snap the gripper dim to {0, 1} before unnormalization. Set to `False` for robots without a binary gripper |
| `binarize_gripper_action` | `True` | Binarize the gripper dim to {-1, 1} after unnormalization. Set to `False` for robots without a binary gripper |
---