Multi-Agent Reinforcement Learning

Also known as MARL

Overview

Multi-agent reinforcement learning studies how multiple decision-makers learn when each agent’s actions affect both the environment and other agents, across cooperative, competitive, and mixed-motive settings. Common approaches include centralized training with decentralized execution, independent or shared actor-critic policies, value factorization such as QMIX, self-play and game-solving methods, and graph-based communication or hierarchical policies. Researchers test these methods in benchmarks such as SMAC, MPE, Overcooked, and multi-agent MuJoCo, and apply them to robotics, traffic, wireless networks, energy systems, and language-agent workflows. A central challenge is scaling coordination and credit assignment while keeping learning stable under non-stationarity and policies robust, safe, and fair with unfamiliar partners and conditions.

Latest papers

CardsList

402 papers32 papers in the last four weeks, down 41% on the four weeks before. 0.2% of all new papers.

  1. Is Anyone Enforcing the Cartel? What Reinforcement Learning Teaches LLM Agents in Markets

    Oct 20, 2026Hieu Tran, Hong YuAlgorithmic CollusionRL for LLM Agents

  2. Vulnerability Analysis for Safe Multi-Agent Reinforcement Learning

    Oct 19, 2026Taozheng Zhu, Shixiong Jiang, Fanxin KongSafe MARLAdversarial Attacks

  3. Cooperation Without Shared Rewards via Reciprocal Q-Augmentation

    Oct 17, 2026Francesco Morri, Adel Abusitta, Quentin Cappart +1Multi-Agent Reinforcement LearningCooperative MARL

  4. Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems

    Oct 15, 2026Omar Adalat, Edwin Hamel-De le Court, Francesco BelardinelliReinforcement LearningMulti-Agent Reinforcement Learning

  5. Learning Rewards in Strategic Games

    Oct 15, 2026Antoine Bergerault, Cyrille Kone, Giorgia RamponiReinforcement LearningMulti-Agent Reinforcement Learning

  6. Constrained Multi-Agent Reinforcement Learning in Imagination

    Oct 15, 2026Raz Shmueli, Shahaf S. ShperbergConstrained MARLMulti-Agent Reinforcement Learning

  7. Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies

    Oct 14, 2026Sajad Marvi, Julian Schmidt, Alessandro Canevaro +2Uncertainty-Aware ExplorationAutonomous Driving Planning

  8. Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning

    Oct 13, 2026Svar Rajankumar Patel, Kshitij JerathBehavioral Diversity in RLCooperative MARL

  9. CALM: Decentralized Control of Cooperative Aerial Manipulation with Multi-Agent Reinforcement Learning

    Oct 13, 2026Jiaxi Huo, Petre Ricioppo, Fausto Francesco LizzioAerial ManipulationDecentralized MARL

  10. When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability

    Oct 13, 2026Marcel Petran, Stefan EdelkampOpponent ModelingMulti-Agent Reinforcement Learning

  11. SIGN-MAPPO: State-Intent-Aware Graph Multi-Agent Reinforcement Learning for Cooperative Driving under Imperfect V2X

    Oct 11, 2026Zide Fan, Jiahui Yuan, Kaixin Zhang +3graph-based multi-agent reinforcement learningMulti-Agent Coordination

  12. MARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL

    Oct 10, 2026Ulixes Tariq Hawili, Subramanian Ramamoorthy, Yoann Altmann +1RL BenchmarksMulti-Agent Reinforcement Learning

  13. MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS

    Oct 9, 2026Tom Philipp Backert, Mohammad D. Soorati, Javad GhofraniML ReproducibilityMulti-Agent Reinforcement Learning

  14. SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning

    Oct 9, 2026Hongrui Zheng, Aditya Singh, Rahul MangharamSafe MARLConstrained MARL

  15. Spatial Pattern Formation from Multi-Agent Learning in Public Goods Dilemmas

    Oct 8, 2026Yefei Zhang, Yuxuan ZhaoEmergent Behavior in Multi-Agent SystemsMulti-Agent Reinforcement Learning

  16. Continual Graph Multi-Agent Reinforcement Learning

    Oct 7, 2026Tommaso Marzi, Ahmed Hendawy, Jan Peters +3graph-based multi-agent reinforcement learningMulti-Agent Reinforcement Learning

  17. Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks

    Oct 7, 2026Bernardo A. C. Pereira, Marcos Carvalho, Fatih Temiz +5Edge ComputingMulti-Agent Reinforcement Learning

  18. The Deceptive Bandit Problem: Exploratory Coupling and the Fragility of Multi-Agent Learning

    Oct 6, 2026Michael Tang, Mahmoud Abdelgalil, Jorge I. PovedaMulti-Agent BanditsBandit Learning

  19. Learning to Report Unsafe Tasks in a Multi-Agent Game

    Oct 6, 2026Avyay M. Casheekar, Hariganesh TangiralaAI Agent SafetyMulti-Agent Systems

  20. Self-Referenced Social Preferences: Cooperation without Observing Others Rewards

    Oct 6, 2026Mohamed Ayman Mohamed, Harshil Kotamreddy, Marcos Menon JoseCooperative MARLMulti-Agent Reinforcement Learning

  21. Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models

    Oct 6, 2026Fernando Martinez, Tao Li, Yingdong Lu +1Sequential MARLAction-Conditioned World Models

  22. BluffJAX: Adversarial Imperfect Information Games in JAX

    Oct 6, 2026Aryaman Reddi, Jan Peters, Carlo D'EramoImperfect-Information GamesRL Benchmarks

  23. Cooperating with Future Collaborators: Multi-Agent RL under Staggered Participation

    Oct 6, 2026Jianglin Qiao, Siyi Hu, Thien Hoang Nguyen +2Multi-Agent Reinforcement LearningCooperative MARL

  24. Foundation Model-Aided Multi-Agent Reinforcement Learning for Wireless Random Access Network Optimization

    Oct 6, 2026Myeung Suk Oh, Zhiyao Zhang, Alvaro Velasquez +2Wireless Resource AllocationDecentralized MARL

  25. Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning

    Oct 5, 2026Xiaoyang Cao, Jingqi Li, Zhe Fu +1Game TheoryConstrained MARL

  26. Strategic Multi-Agent Learning for Interpretable Action Valuation of All Players in Football

    Oct 5, 2026Kenjiro Ide, Taiga Someya, Kohei Kawaguchi +1Sequential Decision MakingInterpretability in RL