限界を育てる：実世界強化学習によるロボット歩行の継続的改善
Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion
実世界での強化学習において、訓練中の探索を調整するポリシー正則化フレームワークAPRLを提案し、四足歩行ロボットが数分で歩行を学習し、その後も性能が飽和せず改善し続けることを示した。
著者: Laura Smith, Yunhao Cao, Sergey Levine
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Deep reinforcement learning (RL) can enable robots to autonomously acquire complex behaviors, such as legged locomotion. However, RL in the real world is complicated by constraints on efficiency, safety, and overall training stability, which limits its practical applicability. We present APRL, a policy regularization framework that modulates the robot's exploration over the course of training, striking a balance between flexible improvement potential and focused, efficient exploration. APRL enables a quadrupedal robot to efficiently learn to walk entirely in the real world within minutes and continue to improve with more training where prior work saturates in performance. We demonstrate that continued training with APRL results in a policy that is substantially more capable of navigating challenging situations and is able to adapt to changes in dynamics with continued training.
