Geometric Regularity with Robot Intrinsic Symmetry in Reinforcement Learning

Shengchao Yan, Yuan Zhang, Baohe Zhang, Joschka Boedecker, Wolfram Burgard

Keywords: geometric regularity, robot learning, multi-agent reinforcement learning, robot control

TL;DR: Geometric Regularity with Robot Intrinsic Symmetry in Robot Learning explores the incorporation of robot symmetry structures into deep learning architectures for improved performance in robot control tasks.

Abstract: Geometric regularity, which leverages data symmetry, has been successfully incorporated into deep learning architectures such as CNNs, RNNs, GNNs, and Transformers. While this concept has been widely applied in robotics to address the curse of dimensionality when learning from high-dimensional data, the inherent reflectional and rotational symmetry of robot structures has not been adequately explored. Drawing inspiration from cooperative multi-agent reinforcement learning, we introduce novel network structures for deep learning algorithms that explicitly capture this geometric regularity. Moreover, we investigate the relationship between the geometric prior and the concept of Parameter Sharing in multi-agent reinforcement learning. Through experiments conducted on various challenging continuous control tasks, we demonstrate the significant potential of the proposed geometric regularity in enhancing robot learning capabilities.