ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learning
Read the original on arXiv AI →ADEPT is a reinforcement‑learning framework that first pre‑trains a dexterous policy on a generic object reposing task and then post‑trains downstream policies using this pretrained behavior as a prior. The approach avoids relearning basic skills for each new task, and employs a stable post‑training recipe—behavior‑cloning distillation, critic warm‑up, and conservative on‑policy updates—to preserve the pretrained capabilities. ADEPT’s joint‑space Geometric Fabric mediates between the policy and the robot, enabling zero‑shot sim‑to‑real transfer on a 23‑DoF Kuka‑Allegro and a 29‑DoF Flexiv‑Sharpa, where the robots solve long‑horizon tasks from challenging initial states at human‑level speed.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.