Multi Agent Actor Critic

Multi-agent actor-critic (MAAC) methods are a class of reinforcement learning algorithms designed to enable coordinated behavior among multiple agents interacting within a shared environment. Current research focuses on improving the scalability and efficiency of MAAC, addressing challenges like high variance in gradient estimates and the need for efficient communication and coordination, often employing techniques like centralized training with decentralized execution and incorporating attention mechanisms or transformer architectures. These advancements are driving progress in diverse applications, including traffic control, power grid management, and robotic manipulation, where the ability to learn effective cooperative strategies in complex, multi-agent systems is crucial.

Papers

October 11, 2024

Multi-Agent Actor-Critics in Autonomous Cyber Defense
Mingjun Wang, Remington Dechene
Reinforcement Learning Multi Agent Learning Multi Agent Actor Critic Autonomous Cyber

July 26, 2024

Order-Optimal Global Convergence for Average Reward Reinforcement Learning via Actor-Critic Approach
Swetha Ganesh, Washim Uddin Mondal, Vaneet Aggarwal
Monte Carlo Multi Agent Actor Critic Policy Parametrization Average Reward Reinforcement Learning

May 23, 2024

Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
Matteo Bettini, Ryan Kortvelesy, Amanda Prorok
Multi Agent Reinforcement Learning Multi Agent System Multi Agent Actor Critic Behavioral Diversity

March 20, 2024

Multi-agent Reinforcement Traffic Signal Control based on Interpretable Influence Mechanism and Biased ReLU Approximation
Zhiyue Luo, Jun Xu, Fanglin Chen
Multi Agent Reinforcement Learning ReLU Network Traffic Signal Control Traffic Network Multi Agent Actor Critic

December 7, 2023

August 23, 2023

${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
Dingyang Chen, Qi Zhang
Cooperative Multi Agent Reinforcement Learning Valuation Model Multi Agent Actor Critic Symmetry Constraint Euclidean Symmetry

July 5, 2023

SACHA: Soft Actor-Critic with Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding
Qiushi Lin, Hang Ma
Multi Agent Reinforcement Learning Multi Agent Path Finding Soft Actor Critic Multi Agent Actor Critic

May 30, 2023

Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility
Flora Charbonnier, Bei Peng, Thomas Morstyn, Malcolm McCulloch
Multi Agent Reinforcement Learning Multi Agent Actor Critic Decentralized Cooperation

March 1, 2023

A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning
Woojun Kim, Whiyoung Jung, Myungsik Cho, Youngchul Sung
Multi Agent Reinforcement Learning Variational Method Maximum Entropy Reinforcement Learning Multi Agent Actor Critic

February 9, 2023

Quantum Multi-Agent Actor-Critic Networks for Cooperative Mobile Access in Multi-UAV Systems
Chanyoung Park, Won Joon Yun, Jae Pyoung Kim, Tiago Koketsu Rodrigues, Soohyun Park, Soyi Jung, Joongheon Kim
Multi Agent Reinforcement Learning Quantum Computing Quantum Physic Multiple Unmanned Aerial Vehicle Multi UAV Multi Agent Actor Critic Cooperative Communication

January 4, 2023

Quantum Multi-Agent Actor-Critic Neural Networks for Internet-Connected Multi-Robot Coordination in Smart Factory Management
Won Joon Yun, Jae Pyoung Kim, Soyi Jung, Jae-Hyun Kim, Joongheon Kim
Multi Agent Reinforcement Learning Multi Agent System Quantum Computing Multi Robot Quantum Physic Variational Quantum Circuit Multi Robot Coordination Multi Agent Actor Critic Smart Factory

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

November 6, 2022

EdgeVision: Towards Collaborative Video Analytics on Distributed Edges for Performance Maximization
Guanyu Gao, Yuqi Dong, Ran Wang, Xin Zhou
Video Analytics Enhancing Efficiency Manipulation Edge Detection Module Multi Agent Actor Critic Resource Constrained Edge

October 24, 2022

AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay
Adarsh Sehgal, Muskan Sehgal, Hung Manh La
Actor Critic Deep Deterministic Policy Gradient Critic Model Multi Agent Actor Critic Hindsight Experience Replay

October 11, 2022

A Multi-Agent Approach for Adaptive Finger Cooperation in Learning-based In-Hand Manipulation
Lingfeng Tao, Jiucai Zhang, Michael Bowman, Xiaoli Zhang
Multi Agent Robotic Hand Hand Manipulation Multi Agent Actor Critic Adaptive Finger

September 20, 2022

Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning
Yuchen Xiao, Weihao Tan, Christopher Amato
Multi Agent Reinforcement Learning Actor Critic Reinforcement Learning Multi Agent Actor Critic Asynchronous Learning Asynchronous Approach

September 2, 2022

Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction
Taher Jafferjee, Juliusz Ziomek, Tianpei Yang, Zipeng Dai, Jianhong Wang, Matthew Taylor, Kun Shao, Jun Wang, David Mguni
Multi Agent Reinforcement Learning Decentralized Training Multi Agent MuJoCo Multi Agent Actor Critic Reinforcement Learning System Tame Function

June 8, 2022

Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer
Minrui Wang, Mingxiao Feng, Wengang Zhou, Houqiang Li
Transformer Based Multi Agent Reinforcement Learning Transformer Based Model Multi Agent Actor Critic Power Network Voltage Control

April 12, 2022

Multi-agent Actor-Critic with Time Dynamical Opponent Model
Yuan Tian, Klaus-Rudolf Kladny, Qin Wang, Zhiwu Huang, Olga Fink
Multi Agent Reinforcement Learning Opponent Modeling Multi Agent Actor Critic Multi Agent Particle

Multi Agent Actor Critic

Papers

Multi-Agent Actor-Critics in Autonomous Cyber Defense

Order-Optimal Global Convergence for Average Reward Reinforcement Learning via Actor-Critic Approach

Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning

Multi-agent Reinforcement Traffic Signal Control based on Interpretable Influence Mechanism and Biased ReLU Approximation

A Scalable Network-Aware Multi-Agent Reinforcement Learning Framework for Decentralized Inverter-based Voltage Control

Multi Actor-Critic DDPG for Robot Action Space Decomposition: A Framework to Control Large 3D Deformation of Soft Linear Objects

${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning

SACHA: Soft Actor-Critic with Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding

Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility

A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning

Quantum Multi-Agent Actor-Critic Networks for Cooperative Mobile Access in Multi-UAV Systems

Quantum Multi-Agent Actor-Critic Neural Networks for Internet-Connected Multi-Robot Coordination in Smart Factory Management

Interpreting Primal-Dual Algorithms for Constrained Multiagent Reinforcement Learning

EdgeVision: Towards Collaborative Video Analytics on Distributed Edges for Performance Maximization

AACHER: Assorted Actor-Critic Deep Reinforcement Learning with Hindsight Experience Replay

A Multi-Agent Approach for Adaptive Finger Cooperation in Learning-based In-Hand Manipulation

Asynchronous Actor-Critic for Multi-Agent Reinforcement Learning

Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction

Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer

Multi-agent Actor-Critic with Time Dynamical Opponent Model