Pith. sign in

MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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 $\varepsilon$-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.

fields

cs.AI 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

CORD: Generalizable Cooperation via Role Diversity

cs.AI · 2025-01-04 · conditional · novelty 5.0

CORD improves zero-shot cooperation in multi-agent games by learning diverse, causally informed role assignments through an entropy-based objective.

citing papers explorer

Showing 1 of 1 citing paper.

  • CORD: Generalizable Cooperation via Role Diversity cs.AI · 2025-01-04 · conditional · none · ref 6 · internal anchor

    CORD improves zero-shot cooperation in multi-agent games by learning diverse, causally informed role assignments through an entropy-based objective.