REGRIND
yunhaif
Retargeting-guided reinforcement learning for dexterous manipulation.
What you can explore
Explore the retargeting stage and its connection to the Isaac Lab training pipeline.
Before you use it
The documented stack uses specific Isaac Lab and Isaac Sim versions. The default optimization path uses Mosek; the source describes a Clarabel alternative.
Original contributors
REGRIND authors and repository contributors
License / access: Code: MIT · data, models and dependencies may have separate terms
Keep exploring
SPIDER
Physics-based retargeting of human motion into robot trajectories across supported embodiments.
DexTrack
Dexterous manipulation through reinforcement learning that tracks human-derived hand–object motion.
Isaac Lab
GPU-oriented robot-learning framework with articulated-robot manipulation environments.
Editorial reference · checked 2026-09-22