${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning

TL;DR

This paper introduces Euclidean symmetry-aware neural network architectures for cooperative multi-agent reinforcement learning, leading to improved performance and generalization in symmetric environments.

Contribution

It formally characterizes symmetries in Markov games and designs symmetric neural network architectures for actor-critic methods, enhancing MARL performance and generalization.

Findings

Superior performance on MARL benchmarks

Effective zero-shot and transfer learning in symmetric scenarios

Neural architectures with embedded symmetry constraints

Abstract

Identification and analysis of symmetrical patterns in the natural world have led to significant discoveries across various scientific fields, such as the formulation of gravitational laws in physics and advancements in the study of chemical structures. In this paper, we focus on exploiting Euclidean symmetries inherent in certain cooperative multi-agent reinforcement learning (MARL) problems and prevalent in many applications. We begin by formally characterizing a subclass of Markov games with a general notion of symmetries that admits the existence of symmetric optimal values and policies. Motivated by these properties, we design neural network architectures with symmetric constraints embedded as an inductive bias for multi-agent actor-critic methods. This inductive bias results in superior performance in various cooperative MARL benchmarks and impressive generalization capabilities such as zero-shot learning and transfer learning in unseen scenarios with repeated symmetric patterns. The code is available at: https://github.com/dchen48/E3AC.