MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning
This addresses non-stationarity in decentralized cooperative MARL, offering a minimalist solution with theoretical guarantees, though it appears incremental as it builds on independent Q-learning with minimal changes.
The paper tackles the non-stationarity problem in fully decentralized multi-agent reinforcement learning by proposing MA2QL, where agents take turns updating Q-functions, and proves convergence to a Nash equilibrium with empirical results showing it consistently outperforms independent Q-learning on cooperative tasks.
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 $\varepsilon$-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.