Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learning
원문 초록
In decentralized multi-agent reinforcement learning, agents learning in isolation can lead to relative over-generalization (RO), where optimal joint actions are undervalued in favor of suboptimal ones. This hinders effective coordination in cooperative tasks, as agents tend to choose actions that are individually rational but collectively suboptimal. To address this issue, we introduce MaxMax Q-Learning (MMQ), which employs an iterative process of sampling and evaluating potential next states, selecting those with maximal Q-values for learning. This approach refines approximations of ideal state transitions, aligning more closely with the optimal joint policy of collaborating agents. We provide theoretical analysis supporting MMQ's potential and present empirical evaluations across various environments susceptible to RO. Our results demonstrate that MMQ frequently outperforms existing baselines, exhibiting enhanced convergence and sample efficiency.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Robust Multi-Agent Reinforcement Learning with Model Uncertainty
Biological Pathway Guided Gene Selection Through Collaborative Reinforcement Learning
Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning
Multi-Agent Reinforcement Learning for Autonomous Multi-Satellite Earth Observation: A Realistic Case Study
Reinforcement Learning-Based Policy Optimisation For Heterogeneous Radio Access
Dynamic Reinsurance Treaty Bidding via Multi-Agent Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.