Multi Agent Reinforcement

Multi-agent reinforcement learning (MARL) focuses on enabling multiple independent agents to learn optimal strategies within a shared environment, often to achieve a collective goal. Current research emphasizes improving training efficiency and scalability through techniques like sparse training, large neighborhood search, and leveraging large language models for high-level planning, as well as addressing challenges like robustness to uncertainty and efficient communication in decentralized settings. These advancements are significant for diverse applications, including robotics, economics, and resource management, by enabling the development of more efficient and adaptable multi-agent systems.

Papers

November 7, 2024

Think Smart, Act SMARL! Analyzing Probabilistic Logic Driven Safety in Multi-Agent Reinforcement Learning
Satchit Chatterji, Erman Acar
Reinforcement Learning Multi Agent Reinforcement Learning Policy Gradient Q Learning Safety Guarantee Multi Agent Reinforcement Safe Multi Agent Reinforcement Learning Model Based Safe Reinforcement Learning

October 18, 2024

MARLIN: Multi-Agent Reinforcement Learning Guided by Language-Based Inter-Robot Negotiation
Toby Godfrey, William Hunt, Mohammad D. Soorati
Reinforcement Learning Multi Agent Reinforcement Learning Multi Robot Multi Agent Reinforcement

October 5, 2024

YOLO-MARL: You Only LLM Once for Multi-agent Reinforcement Learning
Yuan Zhuang, Yi Shen, Zhili Zhang, Yuxiao Chen, Fei Miao
Multi Agent Reinforcement Learning Multi Agent Multi Agent Reinforcement Neural Network Policy Strategy Synthesis

September 28, 2024

Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
Pihe Hu, Shaolong Li, Zhuoran Li, Ling Pan, Longbo Huang
Multi Agent Multi Agent Reinforcement Dynamic Sparse Training Agent Training

August 21, 2024

Empirical Equilibria in Agent-based Economic systems with Learning agents
Kshama Dwarakanath, Svitlana Vyetrenko, Tucker Balch
Agent Based Simulation Learning Agent Multi Agent Reinforcement Multi Agent Market Empirical Game

July 27, 2024

Collaborative Adaptation for Recovery from Unforeseen Malfunctions in Discrete and Continuous MARL Domains
Yasin Findik, Hunter Hasenfus, Reza Azadeh
Multi Agent Reinforcement Learning Prompt Recovery Discrete Environment Multi Agent Reinforcement Collaborative Environment Agent Team Inter Agent Cooperative Multi Agent Learning

June 4, 2024

FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
Wenzhe Li, Zihan Ding, Seth Karten, Chi Jin
Reinforcement Learning New Benchmark Multi Agent Reinforcement Learning Multi Agent Reinforcement Cooperative Multi Agent System Game Dynamic

May 28, 2024

LNS2+RL: Combining Multi-agent Reinforcement Learning with Large Neighborhood Search in Multi-agent Path Finding
Yutong Wang, Tanishq Duhan, Jiaoyang Li, Guillaume Sartoretti
Multi Agent Reinforcement Learning Multi Agent Path Finding Multi Agent Reinforcement Priority Based Interactive Planning Large Neighborhood Search

May 13, 2024

Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client
Jun Xia, Yi Zhang, Yiyu Shi
Full Model Federated Learning Multi Agent Reinforcement Client Collaboration Artificial Intelligence of Thing Dual Approach Energy Constraint Heterogeneous Artificial Intelligence

April 23, 2024

Bi-CL: A Reinforcement Learning Framework for Robots Coordination Through Bi-level Optimization
Zechen Hu, Daigo Shishika, Xuesu Xiao, Xuan Wang
Reinforcement Learning Multi Robot System Multi Agent Reinforcement Multi Robot Coordination Reinforcement Learning Framework

April 3, 2024

MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search
Weizhe Chen, Sven Koenig, Bistra Dilkina
Multi Agent Deep Reinforcement Learning Cooperative Multi Agent Reinforcement Learning Multi Agent Challenge Centralized Training Multi Agent Reinforcement Neighborhood Search

March 5, 2024

PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning
Ke Zhang, DanDan Zhu, Qiuhan Xu, Hao Zhou, Ce Zheng
Multi Agent Reinforcement Learning Early Stage Convergence Multiple Agent Multi Agent Challenge Parameter Sharing Multi Agent Reinforcement Soft QMIX

March 4, 2024

SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition
Wenjing Zhang, Wei Zhang
Multi Agent Reinforcement Learning Hierarchical Reinforcement Learning Multi Agent Reinforcement Subtask Assignment

February 13, 2024

Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning for Digital Twins
Eslam Eldeeb, Houssem Sifaou, Osvaldo Simeone, Mohammad Shehab, Hirley Alves
Multi Agent Reinforcement Learning Multi Agent System Digital Twin Quantile Regression Distributional Reinforcement Learning Multi Agent Reinforcement Conservative Q Learning Offline Safe Reinforcement Learning

February 8, 2024

Risk-Sensitive Multi-Agent Reinforcement Learning in Network Aggregative Markov Games
Hafez Ghaemi, Hamed Kebriaei, Alireza Ramezani Moghaddam, Majid Nili Ahamdabadi
Multi Agent Reinforcement Prospect Theory Risk Aversion Aggregative Game

December 15, 2023

Communication-Efficient Soft Actor-Critic Policy Collaboration via Regulated Segment Mixture
Xiaoxue Yu, Rongpeng Li, Chengchao Liang, Zhifeng Zhao
Multi Agent Reinforcement Learning Vehicle Plan Multi Agent Reinforcement Mixed Autonomy Traffic Maximum Entropy Reinforcement Learning Domain Mixture

December 3, 2023

BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
Matteo Bettini, Amanda Prorok, Vincent Moens
Multi Agent Reinforcement Learning Multi Agent Reinforcement Benchmarking Tool

October 12, 2023

Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning
Aakriti Agrawal, Rohith Aralikatti, Yanchao Sun, Furong Huang
Native Robustness Multi Agent Reinforcement Learning Multi Agent System Curriculum Learning Multi Agent Reinforcement Modal Uncertainty

August 27, 2023

MARL for Decentralized Electric Vehicle Charging Coordination with V2V Energy Exchange
Jiarong Fan, Hao Wang, Ariel Liebman
Multi Agent Reinforcement Learning Electric Vehicle Multi Agent Reinforcement Electric Vehicle Charging Vehicle 2 Vehicle Vehicle to Vehicle

June 20, 2023

IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL
Pascal Leroy, Pablo G. Morato, Jonathan Pisane, Athanasios Kolios, Damien Ernst
Multi Agent Reinforcement Learning Environment Feature Cooperative Multi Agent Reinforcement Learning Multi Agent Reinforcement Software Suite

Multi Agent Reinforcement

Papers

Think Smart, Act SMARL! Analyzing Probabilistic Logic Driven Safety in Multi-Agent Reinforcement Learning

MARLIN: Multi-Agent Reinforcement Learning Guided by Language-Based Inter-Robot Negotiation

YOLO-MARL: You Only LLM Once for Multi-agent Reinforcement Learning

Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training

Empirical Equilibria in Agent-based Economic systems with Learning agents

Collaborative Adaptation for Recovery from Unforeseen Malfunctions in Discrete and Continuous MARL Domains

FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning

LNS2+RL: Combining Multi-agent Reinforcement Learning with Large Neighborhood Search in Multi-agent Path Finding

Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client

Bi-CL: A Reinforcement Learning Framework for Robots Coordination Through Bi-level Optimization

MARL-LNS: Cooperative Multi-agent Reinforcement Learning via Large Neighborhoods Search

PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of Multi-Agent Reinforcement Learning

SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition

Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning for Digital Twins

Risk-Sensitive Multi-Agent Reinforcement Learning in Network Aggregative Markov Games

Communication-Efficient Soft Actor-Critic Policy Collaboration via Regulated Segment Mixture

BenchMARL: Benchmarking Multi-Agent Reinforcement Learning

Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning

MARL for Decentralized Electric Vehicle Charging Coordination with V2V Energy Exchange

IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL