Multi-Agent Reinforcement Learning

Also known as MARL

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

373 papers47 papers in the last four weeks, up 81% on the four weeks before. 0.3% of all new papers.

Adaptive Punishment for Cooperation in Mixed-Motive Games
May 23, 2026Min Tang, Fanqi Kong, Linyuan Lü +1Evolutionary Game Theory Multi-Agent Reinforcement Learning
University of Science and Technology of China, Hefei, China · State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China
Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
May 23, 2026Yuheng Jing, Kai Li, Ziwen Zhang +8RL Benchmarks Multi-Agent Coordination
C2DL, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · University of Science and Technology of China +5
Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaboration
May 23, 2026Adnan Ahmad, Bahareh Nakisa, Mohammad Naim RastgooHierarchical RL Multi-Agent Collaboration
aSchoold of Information Technology, Deakin University, 75 Pidgons Rd, Waurn Ponds, 3216, VIC, Australia · bFaculty of Information Technology, Monash University, Wellington Rd, Clayton, 3800, VIC, Australia
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
May 22, 2026Yifan Zeng, Yiran Wu, Yaolun Zhang +4Multi-Agent LLM Systems LLM Agent Workflow Optimization
1Oregon State University · 2Pennsylvania State University · 3Adobe Inc. +1
One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents
May 22, 2026Yoosung HongReinforcement Learning Game-Playing Agents
Independent Researcher
ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
May 22, 2026Elie Abboud, Oren GalMulti-Agent System Optimization Sparse-Reward RL
Department of Marine Technologies University of Haifa
Self-Play Reinforcement Learning under Imperfect Information in Big 2
May 21, 2026Aalok PatwaGame-Playing Agents Self-Play RL
University of Pennsylvania
Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
May 21, 2026Ismail Geles, Leonard Bauersfeld, Markus Wulfmeier +1Aerial Robotics Multi-Agent Coordination
Robotics and Perception Group, University of Zurich, Zurich, Switzerland · Google DeepMind, London, United Kingdom
Incentive-Aligned Vehicle-to-Vehicle Energy Trading via Nash-Integrated Multi-Agent Reinforcement Learning
May 21, 2026Yujin Lin, Yue Yang, Hao WangMulti-Agent Coordination Automated Negotiation
Department of Data Science and AI, Faculty of IT, Monash University, Australia · Monash Energy Institute, Monash University, Australia
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
May 20, 2026Alexi Canesse, Benoît Goupil, Jesse Read +1Decentralized MARL Multi-Agent Communication
École polytechnique (LIX), CNRS, Institut Polytechnique de Paris, Palaiseau, France
Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX
May 20, 2026Soichiro Nishimori, Shinri Okano, Keigo Habara +3RL Benchmarks Game-Playing Agents
The University of Tokyo, Tokyo, Japan. · Nara Institute of Science and Technology, Nara, Japan. · Independent Researcher. +5
Memory-Induced Supra-Competitive Outcomes Between Deep Reinforcement Learning Agents in Optimal Trade Execution
May 19, 2026Christos Spyridon Koulouris, Carlo CampajolaAlgorithmic Collusion Memory-Augmented Agents
Institute of Finance and Technology, University College London, Gower Street WC1E 6BT London, United Kingdom · UZH Blockchain Center, Andreasstrasse 15, 8050 Zürich, Switzerland
GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning
May 19, 2026Zhiyuan Fan, Gabriele FarinaReinforcement Learning Self-Play RL
MIT
Differentiable Model Predictive Safety for Heterogeneous Mobility at Urban Intersections
May 19, 2026Wenzhe Song, Hao ZhangMulti-Agent Coordination Intelligent Transportation Systems
School of Business Stevens Institute of Technology Hoboken, 07030, USA · Department of Mechanical Engineering Carnegie Mellon University Pittsburgh, 15213, USA
Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints
May 18, 2026Jiayu Li, Enpei Zhang, Dawei Zhou +2Sequential MARL Sequential Decision Making
Stern School of Business · New York University · Department of Computer Science +2
When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State
May 18, 2026Peiying Zhu, Sidi ChangPartially Observable RL Dynamic Pricing
Blossom AI San Francisco, USA · Blossom AI Labs Tokyo, Japan
Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty
May 18, 2026Prakash Aryan, Kaushik Raghupathruni, Timo Kehrer +1Pedestrian Behavior Modeling Human Behavior Simulation
University of Bern, Bern, Switzerland. · AI4I, The Italian Institute of Artificial Intelligence, Turin, Italy.
The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection
May 18, 2026Benedict Russell, Chin-wing Leung, Paolo TurriniSocial Dilemmas Policy Gradient
Mathematics Institute Warwick University · Department of Computer Science Warwick University
Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
May 18, 2026Sunwoo Lee, Mingu Kang, Yonghyeon Jo +1Adversarial Training Multi-Agent Coordination
Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea
Shared Backbone PPO for Multi-UAV Communication Coverage with Connection Preservation
May 18, 2026Z. JiangMulti-Robot Systems Proximal Policy Optimization
Zhejiang University
Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehicles
May 16, 2026Jianye Xu, Bassam AlrifaeeReward Shaping Control Barrier Functions
Department of Computer Science, RWTH Aachen University, Germany · Department of Aerospace Engineering, University of the Bundeswehr Munich, Germany
NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
May 16, 2026Haoran Lu, Luyang Fang, Wenxuan Zhong +1Multi-Agent LLM Systems Multi-Agent Coordination
Department of Statistics, University of Georgia, Athens, GA 30602
Distributed Zeroth-Order Policy Gradient for Networked Multi-agent Reinforcement Learning from Human Feedback
May 15, 2026Pengcheng Dai, He Wang, Dongming Wang +2Policy Gradient Decentralized MARL
Singapore University of Technology and Design, Singapore 487372, Singapore · Southeast University, Nanjing 211189, China · University of California, Riverside, CA 92521, USA +2
Task-Semantic Graph-Driven Distributed Agent Networking for Underwater Target Tracking
May 15, 2026Shengchao Zhu, Guangjie Han, Chuan Lin +1Underwater Robotics Decentralized MARL
College of Computer Science and Software Engineering, Hohai University, Nanjing 210098, China · College of Information Science and Engineering, Hohai University, Changzhou 210013, China · Software College, Northeastern University, Shenyang 110819, China
Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic
May 14, 2026Leo Muxing Wang, Pengkun Yang, Lili SuFederated RL Actor-Critic Methods
Northeastern University · Tsinghua University
Quantum Advantage in Multi Agent Reinforcement Learning
May 14, 2026Simranjeet Singh Dahia, Claudia SzaboDecentralized MARL Quantum RL
Adelaide University, Australia
MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning
May 14, 2026Yaolun Zhang, Yujie Zhao, Nan Wang +6Multi-Agent System Optimization Multi-Agent Orchestration
1Oregon State University · 5AG2AI, Inc. · 2UCSD +2
MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving
May 13, 2026Rajeev Yasarla, Deepti Hegde, Hsin-Pai Cheng +9End-to-End Autonomous Driving Vision-Language-Action Models
Qualcomm AI Research · Qualcomm Technologies, Inc
Dual Hierarchical Dialogue Policy Learning for Legal Inquisitive Conversational Agents
May 13, 2026Xubo Lin, Zezhi Deng, Shihao Wang +2Hierarchical RL Conversational Agents
Georgetown University · Singapore Management University
MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters
May 13, 2026H. Moore, S. Qi, D. Milojicic +2LLM Serving LLM Inference
Colorado State University Fort Collins, CO, USA · Hewlett Packard Labs Milpitas, CA, USA

May 23, 2026J/K move · Enter open · S save

Adaptive Punishment for Cooperation in Mixed-Motive Games

Min Tang, Fanqi Kong, Linyuan Lü, Xue Feng

University of Science and Technology of China, Hefei, China · State Key Laboratory of General Artificial Intelligence, BIGAI, Beijing, China

Evolutionary Game Theory Multi-Agent Reinforcement Learning

Open paper AskPDF arXiv

Mixed-motive scenarios are ubiquitous in real-world multi-agent interactions, where self-interested agents often defect for immediate rewards, overlooking the potential of altruistic cooperation to improve long-term gains and collective welfare. Peer punishment can deter defection, but as costly second-order altruism, its persistent imposition may undermine the punisher's interests. Existing approaches often struggle to effectively implement punishment to promote cooperation. To balance the efficacy and cost of punishment, we propose Adaptive Punishment for Cooperation (APC), a distributed method that determines punishment intensity based on both a dynamic punishment probability and the severity of defection. This dynamic probability substantially reduces costly and ineffective punishment while also promotes cooperation. To accurately assess defection and its severity, we use a defection awareness module, whose learning is guided by game reward. Theoretical analysis and empirical results show APC performs effectively in iterated public goods game. Empirically, APC also significantly outperforms existing baselines across sequential social dilemmas, learning rational and effective punishment policies that foster cooperation by strategically deterring defection.