MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning
Abstract
Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the non-stationarity problem in the simplest and fundamental way and propose multi-agent alternate Q-learning (MA2QL), where agents take turns updating their Q-functions by Q-learning. MA2QL is a minimalist approach to fully decentralized cooperative MARL but is theoretically grounded. We prove that when each agent guarantees -convergence at each turn, their joint policy converges to a Nash equilibrium. In practice, MA2QL only requires minimal changes to independent Q-learning (IQL). We empirically evaluate MA2QL on a variety of cooperative multi-agent tasks. Results show MA2QL consistently outperforms IQL, which verifies the effectiveness of MA2QL, despite such minimal changes.
Cite
@article{arxiv.2209.08244,
title = {MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning},
author = {Kefan Su and Siyuan Zhou and Jiechuan Jiang and Chuang Gan and Xiangjun Wang and Zongqing Lu},
journal= {arXiv preprint arXiv:2209.08244},
year = {2023}
}
Comments
18 pages