協調運動制御のための部分同変強化学習フレームワーク
Subequivariant Reinforcement Learning Framework for Coordinated Motion Control
物理の部分同変原理を利用し、関節間の複雑な依存関係を考慮した強化学習アーキテクチャCoordiGraphを提案。多様な環境での実験で汎化性能とサンプル効率が向上することを示した。
著者: Haoyu Wang, Xiaoyu Tan, Xihe Qiu, Chao Qu
分類: cs.RO, cs.AI
原文アブストラクト
Effective coordination is crucial for motion control with reinforcement learning, especially as the complexity of agents and their motions increases. However, many existing methods struggle to account for the intricate dependencies between joints. We introduce CoordiGraph, a novel architecture that leverages subequivariant principles from physics to enhance coordination of motion control with reinforcement learning. This method embeds the principles of equivariance as inherent patterns in the learning process under gravity influence, which aids in modeling the nuanced relationships between joints vital for motion control. Through extensive experimentation with sophisticated agents in diverse environments, we highlight the merits of our approach. Compared to current leading methods, CoordiGraph notably enhances generalization and sample efficiency.
