Stretch ICRA Run D
Private research checkpoint for the Hello Robot Stretch cup-serving policy experiments.
- Experiment arm: Run D
- Base architecture: NVIDIA GR00T N1.6-3B
- Training data: GT60 + augmented60 with inherited GT labels (120 episodes)
- Final training step: 90,705
- Cameras: head + gripper
- Action horizon: 16
Oracle/inherited-GT policy arm.
Files
This repository contains policy inference weights and the matching processor/statistics/configuration files. DeepSpeed optimizer and RNG states are intentionally excluded.
Use the included statistics.json (or processor/statistics.json, depending on the archived checkpoint layout) and processor configuration with the weights. The exact training configuration is retained under experiment_cfg/.
Intended use
Research and reproducibility only. Validate robot limits, preprocessing, normalization, and emergency-stop behavior before physical deployment.
- Downloads last month
- 5