Multi Agent Deep Deterministic Policy

Multi-agent deep deterministic policy gradient (MADDPG) methods are a class of reinforcement learning algorithms designed to enable coordinated decision-making in systems with multiple interacting agents. Current research focuses on improving the efficiency and robustness of MADDPG, particularly through incorporating attention mechanisms, hierarchical game structures, and multi-objective reward functions to address complex scenarios like autonomous driving, smart grids, and traffic control. These advancements aim to enhance the performance and scalability of MADDPG for real-world applications requiring decentralized control and cooperation among multiple agents. The resulting improvements in efficiency, safety, and resource optimization have significant implications across various domains.

Papers

October 10, 2024

Variational Inequality Methods for Multi-Agent Reinforcement Learning: Performance and Stability Gains
Baraah A. M. Sidahmed, Tatjana Chavdarova
Multi Agent Reinforcement Learning System Performance Actor Critic Algorithm Variational Inequality Multi Agent Setting Multi Agent Particle Multi Agent Deep Deterministic Policy

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

June 20, 2024

Multi-Task Lane-Free Driving Strategy for Connected and Automated Vehicles: A Multi-Agent Deep Reinforcement Learning Approach
Mehran Berahman, Majid Rostami-Shahrbabaki, Klaus Bogenberger
Autonomous Driving Multi Task Automated Driving Strategy Logic Connected Behavior Multi Agent Deep Deterministic Policy Lane Free

April 2, 2024

EnergAIze: Multi Agent Deep Deterministic Policy Gradient for Vehicle to Grid Energy Management
Tiago Fonseca, Luis Ferreira, Bernardo Cabral, Ricardo Severino, Isabel Praca
Vehicle Plan Energy Management Multi Agent Deep Deterministic Policy Energy Management System Vehicle to Grid Energy Flexibility

September 13, 2023

Characterizing Speed Performance of Multi-Agent Reinforcement Learning
Samuel Wiggins, Yuan Meng, Rajgopal Kannan, Viktor Prasanna
Multi Agent Reinforcement Learning Speed Effect Multi Agent Communication Multi Agent Deep Deterministic Policy

June 16, 2023

Cooperative Multi-Objective Reinforcement Learning for Traffic Signal Control and Carbon Emission Reduction
Cheng Ruei Tang, Jun Wei Hsieh, Shin You Teng
Multi Objective Reinforcement Learning Traffic Signal Control Carbon Emission Multi Agent Deep Deterministic Policy

May 4, 2023

Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula
Boling Yang, Liyuan Zheng, Lillian J. Ratliff, Byron Boots, Joshua R. Smith
Multiple Agent Emergent Behavior Stackelberg Game Multi Agent Reinforcement Multi Agent Deep Deterministic Policy

April 17, 2023

Control and Coordination of a SWARM of Unmanned Surface Vehicles using Deep Reinforcement Learning in ROS
Shrudhi R S, Sreyash Mohanty, Dr. Susan Elias
Deep Reinforcement Learning Multi Agent Reinforcement Learning Robot Operating System Unmanned Surface Prior Coordination Communication Model Natural Swarm Multi Agent Deep Deterministic Policy

March 3, 2023

Multi-Target Pursuit by a Decentralized Heterogeneous UAV Swarm using Deep Multi-Agent Reinforcement Learning
Maryam Kouzeghar, Youngbin Song, Malika Meghjani, Roland Bouffanais
Multi Agent Reinforcement Learning Multi Agent Deep Deterministic Policy Pursuit Evasion Heterogeneous UAV

January 20, 2023

On Multi-Agent Deep Deterministic Policy Gradients and their Explainability for SMARTS Environment
Ansh Mittal, Aditya Malte
Autonomous Driving High Explainability Policy Reinforcement Learning Autonomous Driving Research Smart Environment Multi Agent RL Multi Agent Deep Deterministic Policy Cooperative Multi Agent Learning

October 24, 2022

The Design and Realization of Multi-agent Obstacle Avoidance based on Reinforcement Learning
Enyu Zhao, Chanjuan Liu, Houfu Su, Yang Liu
Reinforcement Learning Product Design Multi Agent System Multi Agent Reinforcement Multi Agent Navigation Multi Agent Deep Deterministic Policy

August 30, 2022

A further exploration of deep Multi-Agent Reinforcement Learning with Hybrid Action Space
Hongzhi Hua, Guixuan Wen, Kaigui Wu
Deep Reinforcement Learning Environment Exploration Action Space Multi Agent Deep Reinforcement Learning Multi Agent Particle Multi Agent Deep Deterministic Policy

June 6, 2022

Balancing Profit, Risk, and Sustainability for Portfolio Management
Charl Maree, Christian W. Omlin
Reinforcement Learning High Quality Risk Description Portfolio Optimization Portfolio Management Sustainability Information Multi Agent Deep Deterministic Policy Balancing Market

May 23, 2022

Cooperative Reinforcement Learning on Traffic Signal Control
Chi-Chun Chao, Jun-Wei Hsieh, Bor-Shiun Wang
Reinforcement Learning Traffic Signal Control Multi Agent Deep Deterministic Policy

Multi Agent Deep Deterministic Policy

Papers

Variational Inequality Methods for Multi-Agent Reinforcement Learning: Performance and Stability Gains

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

Multi-Task Lane-Free Driving Strategy for Connected and Automated Vehicles: A Multi-Agent Deep Reinforcement Learning Approach

EnergAIze: Multi Agent Deep Deterministic Policy Gradient for Vehicle to Grid Energy Management

Characterizing Speed Performance of Multi-Agent Reinforcement Learning

Cooperative Multi-Objective Reinforcement Learning for Traffic Signal Control and Carbon Emission Reduction

Stackelberg Games for Learning Emergent Behaviors During Competitive Autocurricula

Control and Coordination of a SWARM of Unmanned Surface Vehicles using Deep Reinforcement Learning in ROS

Multi-Target Pursuit by a Decentralized Heterogeneous UAV Swarm using Deep Multi-Agent Reinforcement Learning

On Multi-Agent Deep Deterministic Policy Gradients and their Explainability for SMARTS Environment

The Design and Realization of Multi-agent Obstacle Avoidance based on Reinforcement Learning

A further exploration of deep Multi-Agent Reinforcement Learning with Hybrid Action Space

Balancing Profit, Risk, and Sustainability for Portfolio Management

Cooperative Reinforcement Learning on Traffic Signal Control