Cooperative MARL

MARL: Multi-Agent Reinforcement Learning

Cooperative MARL studies how multiple learning agents can achieve shared goals when each sees only part of the environment and may act independently. Common approaches include centralized training with decentralized execution, value factorization such as QMIX, actor-critic methods such as MAPPO, and graph-based communication or hierarchical control. Researchers evaluate coordination on benchmarks such as StarCraft Multi-Agent Challenge, Multi-Particle Environment, and Overcooked, as well as in robotics, traffic control, and resource allocation. A central challenge is making coordination scalable and robust to unfamiliar teammates, changing team sizes, communication failures, and tasks where high team reward may not reflect genuine cooperation.

Latest papers

247 papers32 papers in the last four weeks, up 10% on the four weeks before. 0.2% of all new papers.

A Game-Theoretic Spatio-Temporal Reinforcement Learning Framework for Collaborative Public Resource Allocation
Oct 30, 2025Songxin Lei, Qiongyan Wang, Yanchen Zhu +6Multi-Agent Coordination Reinforcement Learning
The Hong Kong University of Science and Technology (Guangzhou) · Peking University · Beijing Institute of Technology +1
Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
Sep 12, 2025Chirayu Nimonkar, Shlok Shah, Catherine Ji +1Multi-Agent Coordination RL Exploration
Princeton University
Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
Aug 8, 2025Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei +2Multi-Agent Collaboration Ad Hoc Teamwork
Collaborative Artificial Intelligence, University of Stuttgart, Stuttgart, Germany.
Efficient Generation of Diverse Cooperative Agents with World Models
Jun 9, 2025Yi Loo, Akshunn Trivedi, Malika MeghjaniCooperative MARL Zero-Shot Coordination
Singapore University of Technology and Design (SUTD)
ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
May 29, 2025Caroline Wang, Arrasy Rahman, Benjamin Nativi +4Multi-Agent Collaboration Ad Hoc Teamwork
Department of Computer Science The University of Texas at Austin · Visa AI · College of Computing and Data Science Nanyang Technological University +1
Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions
Apr 29, 2025Bhavini Jeloka, Yue Guan, Panagiotis TsiotrasMean-Field MARL Multi-Agent Reinforcement Learning
School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA, USA
A Generalist Hanabi Agent
Mar 17, 2025Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond +3RL for Game AI Cooperative MARL
Chandar Research Lab · Mila – Quebec AI Institute · Polytechnique Montréal +4

Oct 30, 2025J/K move · Enter open · S save

A Game-Theoretic Spatio-Temporal Reinforcement Learning Framework for Collaborative Public Resource Allocation

Songxin Lei, Qiongyan Wang, Yanchen Zhu, Hanyu Yao+5

The Hong Kong University of Science and Technology (Guangzhou) · Peking University · Beijing Institute of Technology+1

Multi-Agent Coordination Reinforcement Learning Potential Games Cooperative MARL

Open paper AskPDF arXiv

Public resource allocation involves distributing resources, including urban infrastructure, energy, and transportation, which are typically limited in capacity, to meet social demands. In real-world scenarios, resources are typically limited in capacity, which makes coordination among multiple resources essential. However, existing methods often optimize resource movements in an isolated manner and do not explicitly account for capacity-aware collaboration under spatio-temporal dynamics. To address this limitation, we introduce the Collaborative Public Resource Allocation (CPRA) problem, and propose a Game-Theoretic Spatio-Temporal Reinforcement Learning (GSTRL) framework to solve it. Our contributions are twofold: 1) We formulate CPRA as a potential game and construct the potential function based on the objective function of CPRA, laying a theoretical foundation for approximating the Nash equilibrium of this NP-hard problem; and 2) Our GSTRL framework effectively captures the spatio-temporal dynamics of the overall system. We evaluate GSTRL on two real-world datasets, where experiments show its superior performance. Our source codes are available at https://github.com/thunderlrr/GSTRL.