arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.15100cs.ROcs.AI
收藏

用于协调运动控制的次等变强化学习框架

Subequivariant Reinforcement Learning Framework for Coordinated Motion Control

Shanghai University of Engineering Science(上海工程技术大学);INF Technology (Shanghai) Co., Ltd(INF科技(上海)有限公司)

Haoyu Wang, Xiaoyu Tan, Xihe Qiu, Chao Qu

AI总结:

本文提出CoordiGraph架构,利用次等变原理将等变性嵌入重力影响下的强化学习过程,以建模关节依赖关系,从而显著提升复杂智能体运动控制的泛化能力和样本效率。

摘要:

有效的协调对于强化学习的运动控制至关重要,尤其是当智能体及其运动的复杂性增加时。然而,许多现有方法难以解释关节之间的复杂依赖关系。我们引入了CoordiGraph,这是一种新颖的架构,它利用物理学中的次等变原理来增强强化学习对运动控制的协调。该方法将等变性原理作为重力影响下学习过程的固有模式嵌入,这有助于建模对运动控制至关重要的关节间的细微关系。通过在不同环境中对复杂智能体进行广泛实验,我们突显了该方法的优势。与当前领先方法相比,CoordiGraph显著提升了泛化能力和样本效率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑