MARL Algorithm

Multi-agent reinforcement learning (MARL) focuses on training multiple agents to cooperate or compete within a shared environment, aiming to optimize collective or individual performance. Current research emphasizes addressing challenges like non-stationarity (agents changing the environment for each other), improving safety and robustness through methods such as bilevel optimization and certified policy smoothing, and enhancing coordination and communication, including the exploration of emergent communication and hierarchical strategies. These advancements are crucial for deploying MARL in real-world applications like autonomous driving and robotics, where safe and efficient multi-agent collaboration is essential.

Papers

October 3, 2024

Breaking the mold: The challenge of large scale MARL specialization
Stefan Juang, Hugh Cao, Arielle Zhou, Ruochen Liu, Nevin L. Zhang, Elvis Liu
Challenge Task Multi Agent Learning Multiagent System Agent Performance MARL Algorithm

September 18, 2024

XP-MARL: Auxiliary Prioritization in Multi-Agent Reinforcement Learning to Address Non-Stationarity
Jianye Xu, Omar Sobhy, Bassam Alrifaee
Multi Agent Reinforcement Learning Priority User Non Stationarity Scheduling Policy MARL Algorithm Auxiliary Objective

September 9, 2024

Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors
Jiaqi Liu, Peng Hang, Xiaoxiang Na, Chao Huang, Jian Sun
Reinforcement Learning Autonomous Vehicle Multi Agent Reinforcement Learning Unsignalized Intersection MARL Algorithm Collaborative Decision Multi Agent Deep Deterministic Policy Connected and Automated Vehicle Hierarchical Game

May 28, 2024

Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving
Zhi Zheng, Shangding Gu
Autonomous Driving Bilevel Optimization MARL Algorithm Safe Multi Agent Reinforcement Learning

May 17, 2024

LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions
Chuanneng Sun, Songjun Huang, Dario Pompili
Reinforcement Learning Multi Agent Reinforcement Learning Future Direction MARL Algorithm

April 4, 2024

Laser Learning Environment: A new environment for coordination-critical multi-agent tasks
Yannick Molinghen, Raphaël Avalos, Mark Van Achter, Ann Nowé, Tom Lenaerts
Q Learning Multi Agent Coordination Zero Sum Markov Game Learning Environment MARL Algorithm New Environment Multi Agent Reinforcement Learning Environment

February 12, 2024

Mixed Q-Functionals: Advancing Value-Based Methods in Cooperative MARL with Continuous Action Domains
Yasin Findik, S. Reza Ahmadzadeh
Multi Agent Action Space Q Function MARL Algorithm Value Based

September 12, 2023

Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networks
Marwa Chafii, Salmane Naoumi, Reda Alami, Ebtesam Almazrouei, Mehdi Bennis, Merouane Debbah
Multi Agent Reinforcement Learning Emergent Communication Autonomous Decision Making MARL Algorithm Future Wireless Network

April 28, 2023

From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL
Dapeng Li, Zhiwei Xu, Bin Zhang, Guoliang Fan
New Paradigm Centralized Training Learning Paradigm Decentralized Execution MARL Algorithm Cooperative Learning Explicit Communication Tacit Knowledge

December 22, 2022

Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning
Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino, Gaojie Jin, Qiang Ni
Cooperative Multi Agent Reinforcement Learning Single Agent Robustness Certification MARL Algorithm

December 14, 2022

Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning
Majd Ibrahim, Ammar Fayad
Cooperative Multi Agent Reinforcement Learning Agent Behavior Latent Concept MARL Algorithm StarCraft II

November 29, 2022

Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learning
Daniel Tabas, Ahmed S. Zamzam, Baosen Zhang
Multi Agent Reinforcement Learning Primal Dual Multiagent System MARL Algorithm Multi Agent Actor Critic

August 26, 2022

CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning
Vasu Sharma, Prasoon Goyal, Kaixiang Lin, Govind Thattai, Qiaozi Gao, Gaurav S. Sukhatme
Multi Agent Reinforcement Learning Long Term Cooperation Multimodal Benchmark MARL Algorithm Heterogeneous Multi Agent Reinforcement Learning Cooperative Multi Agent Learning

August 23, 2022

Entropy Enhanced Multi-Agent Coordination Based on Hierarchical Graph Learning for Continuous Action Space
Yining Chen, Ke Wang, Guanghua Song, Xiaohong Jiang
Action Space Multi Agent Coordination Stable Entropy Large Scale Multi Agent MARL Algorithm

July 5, 2022

The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions
Mingyu Kim, Jihwan Oh, Yongsik Lee, Joonkee Kim, Seonghwan Kim, Song Chong, Se-Young Yun
LeArning Abstract Multi Agent Reinforcement Learning Reward Function Multi Agent Challenge MARL Algorithm StarCraft II Multi Stage Task

July 1, 2022

Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Miguel Suau, Jinke He, Mustafa Mert Çelikok, Matthijs T. J. Spaan, Frans A. Oliehoek
Reinforcement Learning Simulation Study Interactive Simulation Large Scale Multi Agent MARL Algorithm Simultaneous Learning Networked System

May 19, 2022

Sparse Adversarial Attack in Multi-agent Reinforcement Learning
Yizheng Hu, Zhihua Zhang
Adversarial Attack Multi Agent Reinforcement Learning Cooperative Multi Agent Reinforcement Learning MARL Algorithm Single Agent RL Sparse Adversarial Attack

May 11, 2022

Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning
Shuhan Qi, Shuhao Zhang, Xiaohan Hou, Jiajia Zhang, Xuan Wang, Jing Xiao
New Framework High Efficiency Multi Agent Reinforcement Learning Single Agent Reinforcement Learning MARL Algorithm Real Time Strategy

April 17, 2022

Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning
Jun Guo, Yonghong Chen, Yihang Hao, Zixin Yin, Yin Yu, Simin Li
Native Robustness MARL Algorithm Systematic Testing

February 7, 2022

Attacking c-MARL More Effectively: A Data Driven Approach
Nhan H. Pham, Lam M. Nguyen, Jie Chen, Hoang Thanh Lam, Subhro Das, Tsui-Wei Weng
Adversarial Attack Adversarial Perturbation Data Driven Approach MARL Algorithm Model Attack Agent Selection

MARL Algorithm

Papers

Breaking the mold: The challenge of large scale MARL specialization

XP-MARL: Auxiliary Prioritization in Multi-Agent Reinforcement Learning to Address Non-Stationarity

Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors

Safe Multi-Agent Reinforcement Learning with Bilevel Optimization in Autonomous Driving

LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions

Laser Learning Environment: A new environment for coordination-critical multi-agent tasks

Mixed Q-Functionals: Advancing Value-Based Methods in Cooperative MARL with Continuous Action Domains

Emergent Communication in Multi-Agent Reinforcement Learning for Future Wireless Networks

From Explicit Communication to Tacit Cooperation:A Novel Paradigm for Cooperative MARL

Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning

Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning

Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learning

CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning

Entropy Enhanced Multi-Agent Coordination Based on Hierarchical Graph Learning for Continuous Action Space

The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions

Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems

Sparse Adversarial Attack in Multi-agent Reinforcement Learning

Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning

Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning

Attacking c-MARL More Effectively: A Data Driven Approach