Multi Agent Deep Reinforcement Learning

Multi-agent deep reinforcement learning (MADRL) focuses on training multiple AI agents to collaborate or compete within a shared environment, aiming to optimize collective performance through learning. Current research emphasizes developing efficient algorithms like MADDPG and variations of Q-learning, often incorporating transformer networks for improved feature representation and handling complex interactions, and exploring different training paradigms such as centralized training with decentralized execution. This field is significant for its potential to solve complex real-world problems across diverse domains, including autonomous driving, robotics, network optimization, and resource management, by enabling more robust and adaptable systems.

Papers

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 29, 2024

A Learning-based Incentive Mechanism for Mobile AIGC Service in Decentralized Internet of Vehicles
Jiani Fan, Minrui Xu, Ziyao Liu, Huanyi Ye, Chaojie Gu, Dusit Niyato, Kwok-Yan Lam
Generated Content Multi Agent Deep Reinforcement Learning Vehicle Plan Incentive Compatibility Decentralized Graph Roadside Unit Mobile Artificial Intelligence Generated Content

March 16, 2024

A Scalable and Parallelizable Digital Twin Framework for Sustainable Sim2Real Transition of Multi-Agent Reinforcement Learning Systems
Chinmay Vilas Samak, Tanmay Vilas Samak, Venkat Krovi
Multi Agent Reinforcement Learning Digital Twin Multi Agent Deep Reinforcement Learning Sim2real Strategy Cooperative Vehicle

February 27, 2024

Multi-Agent Deep Reinforcement Learning for Distributed Satellite Routing
Federico Lozano-Cuadra, Beatriz Soret
Offline Reinforcement Learning Multi Agent Deep Reinforcement Learning Optimal Path Optimal Route

February 12, 2024

MAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning
Ayesha Siddika Nipu, Siming Liu, Anthony Harris
Multi Agent Multi Agent Deep Reinforcement Learning Multi Agent Challenge Influence Diagram

February 6, 2024

Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning
Maxime Toquebiau, Nicolas Bredeche, Faïz Benamar, Jae-Yun Jun
Multi Agent Deep Reinforcement Learning Intrinsic Motivation

February 4, 2024

Interference-Aware Emergent Random Access Protocol for Downlink LEO Satellite Networks
Chang-Yong Lim, Jihong Park, Jinho Choi, Ju-Hyung Lee, Daesub Oh, Heewook Kim
Multi Agent Deep Reinforcement Learning Emergent Communication Multiple Access Low Earth Orbit Satellite Protocol Learning

January 23, 2024

January 21, 2024

MADRL-based UAVs Trajectory Design with Anti-Collision Mechanism in Vehicular Networks
Leonardo Spampinato, Enrico Testi, Chiara Buratti, Riccardo Marini
Unmanned Aerial Vehicle Multi Agent Deep Reinforcement Learning Vehicular Network Multiple Unmanned Aerial Vehicle Collision Avoidance Capability

January 18, 2024

Cooperative Edge Caching Based on Elastic Federated and Multi-Agent Deep Reinforcement Learning in Next-Generation Network
Qiong Wu, Wenhua Wang, Pingyi Fan, Qiang Fan, Huiling Zhu, Khaled B. Letaief
Federated Prompt Cooperation Multi Agent Deep Reinforcement Learning Base Station Adversarial AutoEncoder Edge Caching Next Generation Network

January 9, 2024

Deep Reinforcement Multi-agent Learning framework for Information Gathering with Local Gaussian Processes for Water Monitoring
Samuel Yanes Luis, Dmitriy Shutin, Juan Marchal Gómez, Daniel Gutiérrez Reina, Sergio Toral Marín
Deep Reinforcement Learning Gaussian Process Multi Agent Deep Reinforcement Learning Autonomous Surface Vehicle Water Quality Information Acquisition Double Deep Q Learning

December 14, 2023

Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems
Heiko Hoppe, Tobias Enders, Quentin Cappart, Maximilian Schiffer
Multi Agent Deep Reinforcement Learning Demand Prediction Vehicle Dispatching Autonomous Mobility

December 11, 2023

Scalable Decentralized Cooperative Platoon using Multi-Agent Deep Reinforcement Learning
Ahmed Abdelrahman, Omar M. Shehata, Yarah Basyoni, Elsayed I. Morgan
Autonomous Vehicle Multi Agent Deep Reinforcement Learning Platoon Control Cooperative Autonomous Driving

December 8, 2023

Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning
Chris Hicks, Vasilios Mavroudis, Myles Foley, Thomas Davies, Kate Highnam, Tim Watson
Deep Reinforcement Learning Multi Agent Deep Reinforcement Learning Deep Reinforcement UAV Network Sophisticated Agent Bell and Whistle Network Resilience

November 27, 2023

Multi-Agent Reinforcement Learning for Power Control in Wireless Networks via Adaptive Graphs
Lorenzo Mario Amorosa, Marco Skocaj, Roberto Verdone, Deniz Gündüz
Multi Agent Reinforcement Learning Wireless Network Multi Agent Deep Reinforcement Learning Policy Parameterization Adaptive Graph Network Optimization Power Control

November 19, 2023

Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies
Feng Wang, M. Cenk Gursoy, Senem Velipasalar
Adversarial Attack Multi Agent Deep Reinforcement Learning Deep RL Multi Agent Policy Network Slicing Defense Strategy

October 26, 2023

October 16, 2023

Joint Optimization of Traffic Signal Control and Vehicle Routing in Signalized Road Networks using Multi-Agent Deep Reinforcement Learning
Xianyue Peng, Hang Gao, Gengyue Han, Hao Wang, Michael Zhang
Multi Agent Multi Agent Deep Reinforcement Learning Traffic Signal Control Joint Optimization Vehicle Routing Signal Control

Multi Agent Deep Reinforcement Learning

Papers

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

A Learning-based Incentive Mechanism for Mobile AIGC Service in Decentralized Internet of Vehicles

A Scalable and Parallelizable Digital Twin Framework for Sustainable Sim2Real Transition of Multi-Agent Reinforcement Learning Systems

Multi-Agent Deep Reinforcement Learning for Distributed Satellite Routing

MAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning

Joint Intrinsic Motivation for Coordinated Exploration in Multi-Agent Deep Reinforcement Learning

Interference-Aware Emergent Random Access Protocol for Downlink LEO Satellite Networks

Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control

Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management

MADRL-based UAVs Trajectory Design with Anti-Collision Mechanism in Vehicular Networks

Cooperative Edge Caching Based on Elastic Federated and Multi-Agent Deep Reinforcement Learning in Next-Generation Network

Deep Reinforcement Multi-agent Learning framework for Information Gathering with Local Gaussian Processes for Water Monitoring

Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems

Scalable Decentralized Cooperative Platoon using Multi-Agent Deep Reinforcement Learning

Canaries and Whistles: Resilient Drone Communication Networks with (or without) Deep Reinforcement Learning

Multi-Agent Reinforcement Learning for Power Control in Wireless Networks via Adaptive Graphs

Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategies

Orchestration of Emulator Assisted Mobile Edge Tuning for AI Foundation Models: A Multi-Agent Deep Reinforcement Learning Approach

Fair collaborative vehicle routing: A deep multi-agent reinforcement learning approach

Joint Optimization of Traffic Signal Control and Vehicle Routing in Signalized Road Networks using Multi-Agent Deep Reinforcement Learning