Cooperative Multi Agent Reinforcement Learning

Cooperative multi-agent reinforcement learning (MARL) focuses on training multiple agents to collaborate effectively towards shared goals, a challenge amplified by the complexity of decentralized decision-making. Current research emphasizes centralized training for decentralized execution (CTDE), employing techniques like value function factorization (e.g., QMIX variants) and communication mechanisms (e.g., graph-based networks and attention mechanisms) to improve coordination and scalability. This field is significant for its potential to advance autonomous systems in diverse domains, including robotics, traffic control, and resource management, by enabling efficient and robust teamwork in complex environments. Addressing challenges like power imbalances, adversarial agents, and privacy concerns within these frameworks is a key focus of ongoing work.

Papers

June 14, 2023

Hierarchical Task Network Planning for Facilitating Cooperative Multi-Agent Reinforcement Learning
Xuechen Mu, Hankz Hankui Zhuo, Chen Chen, Kai Zhang, Chao Yu, Jianye Hao
Multi Agent Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Intrinsic Reward Hierarchical Knowledge Agent Exploration Hierarchical Task Network Planning

June 2, 2023

Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
Dingyang Chen, Qi Zhang
Actor Critic Cooperative Multi Agent Reinforcement Learning Markov Game Multi Agent Policy Softmax Policy

May 27, 2023

Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?
Yihe Zhou, Shunyu Liu, Yunpeng Qing, Kaixuan Chen, Tongya Zheng, Yanhao Huang, Jie Song, Mingli Song
Multi Agent Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Centralized Training Multi Agent Reinforcement Local Level Decentralized Execution

May 12, 2023

Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning
Qingpeng Zhao, Yuanyang Zhu, Zichuan Liu, Zhi Wang, Chunlin Chen
State Space Cooperative Multi Agent Reinforcement Learning State Representation Multi Head Attention Mechanism Value Decomposition Compact Latent

May 10, 2023

May 9, 2023

Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation
Lei Yuan, Feng Chen, Zhongzhang Zhang, Yang Yu
Reinforcement Learning Multi Agent Adaptive Importance Cooperative Multi Agent Reinforcement Learning Communication Learning Auxiliary Adversarial

April 18, 2023

Cooperative Multi-Agent Reinforcement Learning for Inventory Management
Madhav Khirwar, Karthik S. Gurumoorthy, Ankit Ajit Jain, Shantala Manchenahally
Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Supply Chain Inventory Management Agent Environment Interaction

April 4, 2023

Regularization of the policy updates for stabilizing Mean Field Games
Talal Algumaei, Ruben Solozabal, Reda Alami, Hakim Hacid, Merouane Debbah, Martin Takac
Deep Reinforcement Learning Proximal Policy Optimization Mean Field Cooperative Multi Agent Reinforcement Learning Mean Field Game Policy Update

March 19, 2023

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning
Yat Long Lo, Christian Schroeder de Witt, Samuel Sokota, Jakob Nicolaus Foerster, Shimon Whiteson
Multi Agent Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Agent Communication Resource Utilization Mutual Information Maximization Coordinated Behavior Spoken Term

March 16, 2023

SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning
Shuhan Qi, Shuhao Zhang, Qiang Wang, Jiajia Zhang, Jing Xiao, Xuan Wang
Cooperative Multi Agent Reinforcement Learning Intrinsic Reward State Action Space Value Decomposition

March 15, 2023

Muti-Agent Proximal Policy Optimization For Data Freshness in UAV-assisted Networks
Mouhamed Naby Ndiaye, El Houcine Bergou, Hajar El Hammouti
Reinforcement Learning Proximal Policy Optimization Policy Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Multi Agent Proximal Policy Optimization Data Quality Issue UAV Assisted

March 3, 2023

Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning
Jihwan Oh, Joonkee Kim, Minchan Jeong, Se-Young Yun
Multi Agent Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Distributional Reinforcement Learning Collaborative Exploration Optimistic Exploration

February 19, 2023

Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning
Cong Guan, Feng Chen, Lei Yuan, Zongzhang Zhang, Yang Yu
Cooperative Multi Agent Reinforcement Learning Online Service Communication Efficiency Multi Agent Communication Offline Multi Agent Reinforcement Learning Aggregated Representation Message Aggregation

February 14, 2023

February 12, 2023

MANSA: Learning Fast and Slow in Multi-Agent Systems
David Mguni, Haojun Chen, Taher Jafferjee, Jianhong Wang, Long Fei, Xidong Feng, Stephen McAleer, Feifei Tong, Jun Wang, Yaodong Yang
Multi Agent Reinforcement Learning Multi Agent System Cooperative Multi Agent Reinforcement Learning Multi Agent Challenge Multi Agent Network Level Based Foraging

February 8, 2023

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning
Volodymyr Tkachuk, Seyed Alireza Bakhtiari, Johannes Kirschner, Matej Jusup, Ilija Bogunovic, Csaba Szepesvári
Reinforcement Learning Financial Application Action Space Cooperative Multi Agent Reinforcement Learning Efficient Planning Global Reward Blow Up Algorithm

February 7, 2023

Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
Simin Li, Jun Guo, Jingqiao Xiu, Pu Feng, Xin Yu, Aishan Liu, Wenjun Wu, Xianglong Liu
Adversarial Attack Cooperative Multi Agent Reinforcement Learning Multi Agent Interaction Multi Agent MuJoCo Adversarial Influence

February 4, 2023

Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative Multi-Agent Reinforcement Learning
Zhiwei Xu, Bin Zhang, Dapeng Li, Guangchong Zhou, Zeren Zhang, Guoliang Fan
Cooperative Multi Agent Reinforcement Learning Self Awareness Value Decomposition

Cooperative Multi Agent Reinforcement Learning

Papers

Hierarchical Task Network Planning for Facilitating Cooperative Multi-Agent Reinforcement Learning

Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning

Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?

Boosting Value Decomposition via Unit-Wise Attentive State Representation for Cooperative Multi-Agent Reinforcement Learning

Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers

Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generation

Cooperative Multi-Agent Reinforcement Learning for Inventory Management

Regularization of the policy updates for stabilizing Mean Field Games

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning

SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning

Muti-Agent Proximal Policy Optimization For Data Freshness in UAV-assisted Networks

Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning

Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning

A Theory of Mind Approach as Test-Time Mitigation Against Emergent Adversarial Communication

Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning

MANSA: Learning Fast and Slow in Multi-Agent Systems

Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning

Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence

Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative Multi-Agent Reinforcement Learning