Off-Beat Multi-Agent Reinforcement Learning

TL;DR

This paper introduces LeGEM, a novel episodic memory framework for multi-agent reinforcement learning in environments with off-beat actions, improving coordination and sample efficiency.

Contribution

It develops a new algorithmic framework and a memory scheme to handle off-beat actions and temporal credit assignment in MARL, which were previously unaddressed.

Findings

LeGEM significantly improves multi-agent coordination.

LeGEM achieves leading performance in various scenarios.

LeGEM enhances sample efficiency in MARL.

Abstract

We investigate model-free multi-agent reinforcement learning (MARL) in environments where off-beat actions are prevalent, i.e., all actions have pre-set execution durations. During execution durations, the environment changes are influenced by, but not synchronised with, action execution. Such a setting is ubiquitous in many real-world problems. However, most MARL methods assume actions are executed immediately after inference, which is often unrealistic and can lead to catastrophic failure for multi-agent coordination with off-beat actions. In order to fill this gap, we develop an algorithmic framework for MARL with off-beat actions. We then propose a novel episodic memory, LeGEM, for model-free MARL algorithms. LeGEM builds agents' episodic memories by utilizing agents' individual experiences. It boosts multi-agent learning by addressing the challenging temporal credit assignment problem raised by the off-beat actions via our novel reward redistribution scheme, alleviating the issue of non-Markovian reward. We evaluate LeGEM on various multi-agent scenarios with off-beat actions, including Stag-Hunter Game, Quarry Game, Afforestation Game, and StarCraft II micromanagement tasks. Empirical results show that LeGEM significantly boosts multi-agent coordination and achieves leading performance and improved sample efficiency.