Off-Beat Multi-Agent Reinforcement Learning
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.
Cite
@article{arxiv.2205.13718,
title = {Off-Beat Multi-Agent Reinforcement Learning},
author = {Wei Qiu and Weixun Wang and Rundong Wang and Bo An and Yujing Hu and Svetlana Obraztsova and Zinovi Rabinovich and Jianye Hao and Yingfeng Chen and Changjie Fan},
journal= {arXiv preprint arXiv:2205.13718},
year = {2022}
}
Comments
Fix typos