対称性誘導メモリ拡張による効率的な歩行学習
Symmetry-Guided Memory Augmentation for Efficient Locomotion Learning
ロボットとタスクの対称性を利用して追加の訓練経験を生成し、さらにポリシーのメモリ状態にも変換を適用することで、脚式ロボットの強化学習を効率化するフレームワークを提案した。
著者: Kaixi Bao, Chenhao Li, Yarden As, Andreas Krause, Marco Hutter
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Training reinforcement learning (RL) policies for legged locomotion often requires extensive environment interactions, which are costly and time-consuming. We propose Symmetry-Guided Memory Augmentation (SGMA), a framework that improves training efficiency by combining structured experience augmentation with memory-based context inference. Our method leverages robot and task symmetries to generate additional, physically consistent training experiences without requiring extra interactions. To avoid the pitfalls of naive augmentation, we extend these transformations to the policy's memory states, enabling the agent to retain task-relevant context and adapt its behavior accordingly. We evaluate the approach on quadruped and humanoid robots in simulation, as well as on a real quadruped platform. Across diverse locomotion tasks involving joint failures and payload variations, our method achieves efficient policy training while maintaining robust performance, demonstrating a practical route toward data-efficient RL for legged robots.
