Work

Subequivariant Reinforcement Learning Framework for Coordinated Motion Control

Year: 2024

Type: conference-paper

Abstract: 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.

Source: Proceedings - IEEE International Conference on Robotics and Automation/Proceedings

DOI: 10.1109/icra57147.2024.10610563

Authors: Haoyu Wang, Xiaoyu Tan, Xihe Qiu, Chao Qu

Institution: Shanghai University of Engineering Science

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Natural Science Foundation of Shanghai, National Natural Science Foundation of China

Awards: 面向睡眠呼吸障碍患者全流程辅助诊断算法应用研究, G4862170252