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

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

Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning
Oct 26, 2026Qiyue Xia, J. Michael HerrmannMulti-Objective Reinforcement Learning Multi-Agent Reinforcement Learning
School of Informatics, University of Edinburgh, Edinburgh, United Kingdom
Belief-Conditioned Multi-Agent Actor Critic for Decentralized LLM Collaboration
Oct 26, 2026Tianle Chen, Shuo Liu, Christopher AmatoMulti-Agent LLM Systems Multi-Agent Reinforcement Learning
Khoury College of Computer Sciences, Northeastern University, Boston, MA, 02215, USA
BE-CTDE: Blockchain-Enabled Multi-Agent Reinforcement Learning with Anomaly Detection and Token Economics
Oct 25, 2026Chih-Wei Huang, Hsin-Chieh Lee, Yun-Chen Yu +3Multi-Agent Reinforcement Learning Adversarial MARL
Department of Communication Engineering, National Central University, Taoyuan City 320317, Taiwan · Interdisciplinary Research Center for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran 31261, Saudi Arabia · School of Computing, Queen’s University, Kingston, ON K7L 2N8, Canada +1
SpecMAGIC: Specification-Guided Multi-Task Generalization in Multi-Agent Reinforcement Learning
Oct 21, 2026Zijian Guo, İlker Işık, H. M. Sabbir Ahmad +1Multi-Agent Reinforcement Learning Multi-Agent Coordination
Division of Systems Engineering, Boston University · Department of Electrical and Computer Engineering, Boston University
JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in Seconds
Oct 20, 2026Daniele Montagnani, Andrea Coletta, Antonietta Mira +1Multi-Agent Reinforcement Learning Reinforcement Learning
Università di Pavia Italy · USI Lugano Switzerland · Banca d’Italia† Italy +1
Is Anyone Enforcing the Cartel? What Reinforcement Learning Teaches LLM Agents in Markets
Oct 20, 2026Hieu Tran, Hong YuAlgorithmic Collusion RL for LLM Agents
University of Massachusetts Amherst · University of Massachusetts Lowell
Vulnerability Analysis for Safe Multi-Agent Reinforcement
Oct 19, 2026Taozheng Zhu, Shixiong Jiang, Fanxin KongAdversarial Attacks Adversarial MARL
University of Notre Dame, Notre Dame, Indiana, USA
Cooperation Without Shared Rewards via Reciprocal Q-Augmentation
Oct 17, 2026Francesco Morri, Adel Abusitta, Quentin Cappart +1Multi-Agent Reinforcement Learning Cooperative MARL
Polytechnique Montréal Montréal, Canada · Polytechnique Montréal, Mila Montréal, Canada · UCLouvain Louvain-la-Neuve, Belgium +1
Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems
Oct 15, 2026Omar Adalat, Edwin Hamel-De le Court, Francesco BelardinelliReinforcement Learning Multi-Agent Reinforcement Learning
Imperial College London London, United Kingdom · University of Manchester Manchester, United Kingdom
Learning Rewards in Strategic Games
Oct 15, 2026Antoine Bergerault, Cyrille Kone, Giorgia RamponiReinforcement Learning Multi-Agent Reinforcement Learning
ALPI Lab, University of Zurich
Constrained Multi-Agent Reinforcement Learning in Imagination
Oct 15, 2026Raz Shmueli, Shahaf S. ShperbergConstrained MARL Multi-Agent Reinforcement Learning
Ben-Gurion University of the Negev, Beer-Sheva, Israel
Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies
Oct 14, 2026Sajad Marvi, Julian Schmidt, Alessandro Canevaro +2Uncertainty-Aware Exploration Autonomous Driving Planning
Mercedes-Benz AG, Germany. · Department of Computer Science, University of Freiburg, Germany.
Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning
Oct 13, 2026Svar Rajankumar Patel, Kshitij JerathBehavioral Diversity in RL Cooperative MARL
Department of Computer Science, University of Massachusetts Lowell, Lowell, Massachusetts, USA · Department of Mechanical and Industrial Engineering, University of Massachusetts Lowell, Lowell, Massachusetts, USA
CALM: Decentralized Control of Cooperative Aerial Manipulation with Multi-Agent Reinforcement Learning
Oct 13, 2026Jiaxi Huo, Petre Ricioppo, Fausto Francesco LizzioAerial Manipulation Decentralized MARL
Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Torino, Italy
When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability
Oct 13, 2026Marcel Petran, Stefan EdelkampOpponent Modeling Multi-Agent Reinforcement Learning
Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic
Reinforcement Learning for Large-Scale Lifelong Multi-Agent Path Finding with Shared Spatial Fields
Oct 13, 2026Jean Seong Bjorn ChoeMulti-Agent Path Finding Multi-Agent Planning
Independent Researcher
SIGN-MAPPO: State-Intent-Aware Graph Multi-Agent Reinforcement Learning for Cooperative Driving under Imperfect V2X
Oct 11, 2026Zide Fan, Jiahui Yuan, Kaixin Zhang +3Multi-Agent Coordination Cooperative MARL
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China · Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences and the School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences
Do Rollups Self-Organize? Multi-Agent Reinforcement Learning in the EIP-4844 Blob Fee Market
Oct 11, 2026Alessio BriniEmergent Behavior in Multi-Agent Systems Multi-Agent Reinforcement Learning
Pratt School of Engineering, Duke University, Durham, NC, USA
MARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL
Oct 10, 2026Ulixes Tariq Hawili, Subramanian Ramamoorthy, Yoann Altmann +1RL Benchmarks Multi-Agent Reinforcement Learning
School of Engineering, University of Edinburgh, Edinburgh, United Kingdom · School of Informatics, University of Edinburgh, Edinburgh, United Kingdom · School of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh, United Kingdom
MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS
Oct 9, 2026Tom Philipp Backert, Mohammad D. Soorati, Javad GhofraniML Reproducibility Multi-Agent Reinforcement Learning
University of Lübeck, Lübeck, Germany · University of Southampton, Southampton, UK · Bonn-Rhein-Sieg University of Applied Sciences, Sankt Augustin, Germany
SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
Oct 9, 2026Hongrui Zheng, Aditya Singh, Rahul MangharamConstrained MARL Multi-Agent Reinforcement Learning
University of Pennsylvania, Philadelphia, USA
Spatial Pattern Formation from Multi-Agent Learning in Public Goods Dilemmas
Oct 8, 2026Yefei Zhang, Yuxuan ZhaoEmergent Behavior in Multi-Agent Systems Multi-Agent Reinforcement Learning
Department of Mathematics University of Illinois Urbana-Champaign Urbana, IL 61801, USA
Continual Graph Multi-Agent Reinforcement Learning
Oct 7, 2026Tommaso Marzi, Ahmed Hendawy, Jan Peters +3Multi-Agent Reinforcement Learning Continual RL
IDSIA USI-SUPSI, Università della Svizzera italiana, Lugano, Switzerland · Technical University of Darmstadt, Darmstadt, Germany · Robotics Institute Germany (RIG) +4
Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks
Oct 7, 2026Bernardo A. C. Pereira, Marcos Carvalho, Fatih Temiz +5Edge Computing Multi-Agent Reinforcement Learning
Universidade Federal de Minas Gerais, Brazil · School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada · University of Antwerp - imec, IDLab - Faculty of Applied Engineering, Belgium
The Deceptive Bandit Problem: Exploratory Coupling and the Fragility of Multi-Agent Learning
Oct 6, 2026Michael Tang, Mahmoud Abdelgalil, Jorge I. PovedaMulti-Agent Bandits Bandit Learning
Electrical and Computer Engineering Department at the University of California, San Diego, La Jolla, CA, USA · Mechanical and Aerospace Engineering Department at the University at Buffalo, State University of New York, Buffalo, NY, USA
Learning to Report Unsafe Tasks in a Multi-Agent Game
Oct 6, 2026Avyay M. Casheekar, Hariganesh TangiralaAI Agent Safety Multi-Agent Systems
University of Michigan Law School Ann Arbor, USA · School of Computing National University of Singapore Singapore, Singapore
Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA
Oct 6, 2026Jordy KietoGame-Playing Agents Model-Based RL
Self-Referenced Social Preferences: Cooperation without Observing Others Rewards
Oct 6, 2026Mohamed Ayman Mohamed, Harshil Kotamreddy, Marcos Menon JoseCooperative MARL Multi-Agent Reinforcement Learning
Amazon, Vancouver, Canada · Nvidia, Santa Clara, United States · Itaú Unibanco, São Paulo, Brazil
Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models
Oct 6, 2026Fernando Martinez, Tao Li, Yingdong Lu +1Sequential MARL Action-Conditioned World Models
Department of Computer and Information Sciences, Fordham University, New York, NY, 10023, USA · Department of Systems Engineering, City University of Hong Kong, Hong Kong SAR, 999077, China · IBM Research, Yorktown Heights, NY, 10598, USA
BluffJAX: Adversarial Imperfect Information Games in JAX
Oct 6, 2026Aryaman Reddi, Jan Peters, Carlo D'EramoImperfect-Information Games RL Benchmarks
Department of Computer Science, TU Darmstadt, Germany · Hessian Center for Artificial Intelligence (Hessian.ai), Germany · German Research Center for AI (DFKI), Systems AI for Robot Learning, Germany +1

Oct 26, 2026J/K move · Enter open · S save

Preference-Guided Cooperation in Multi-Objective Multi-Agent Reinforcement Learning

Qiyue Xia, J. Michael Herrmann

School of Informatics, University of Edinburgh, Edinburgh, United Kingdom

Multi-Objective Reinforcement Learning Multi-Agent Reinforcement Learning Cooperative MARL

Open paper AskPDF arXiv

Multi-objective multi-agent reinforcement learning (MOMARL) addresses agent coordination and objective trade-offs simultaneously while optimising overall system performance. Existing work tends to treat multi-agent cooperation and multi-objective optimisation as largely independent components of a learning problem, which amounts to an exorbitant complexity except in trivial cases. We study here whether the structure provided by multiple objectives can itself be exploited to facilitate cooperation, rather than being treated as an additional optimisation challenge. We formulate MOMARL at both the team and individual levels and introduce objective-wise counterfactual credit assignment to evaluate each agent's contribution across the team objectives. We propose Meta-Gradient Informed Multi-Objective Multi-Agent Reinforcement Learning (MIRL), with static (MIRL-S) and dynamic (MIRL-D) variants. By incorporating meta-gradient information, MIRL enables agents to learn how to prioritise objectives individually while collectively optimising the system-level objective, allowing the multi-objective structure to directly guide cooperation. Experiments on a multi-objective multiple particle environment show that our methods improve Pareto-front quality over baselines, with the dynamic variant achieving the strongest performance.