Article

ADEPT: Accelerating Dexterous Manipulation via Reinforcement Learning Pre-Training and Post-Training

ADEPT is a large-scale reinforcement learning framework that first pre-trains a dexterous policy on a generic object-reposing task, then post-trains downstream policies with this prior, enabling long-horizon tasks to be solved directly from raw visual-tactile perception across high-DoF embodiments. To prevent naive fine-tuning from degrading zero-shot reposing ability, the authors propose a stable post-training scheme combining behavior-cloning distillation, critic warm-up, and conservative on-policy updates, and introduce a joint-space Geometric Fabric that coordinates the policy with the robot.

Part of the event: ADEPT: Pretraining and Post-Training Reinforcement Learning Accelerates Dexterous Manipulation

This page provides a summary and source link only.