Multi Agent RL

Multi-agent reinforcement learning (MARL) focuses on training multiple agents to cooperate or compete within a shared environment, aiming to optimize collective or individual performance. Current research emphasizes addressing challenges like credit assignment, communication, and scalability, often employing decentralized architectures, model-based approaches (like Dreamer), and techniques to improve data efficiency and stability (e.g., selective experience sharing and reward decoupling). MARL's significance lies in its potential to solve complex real-world problems requiring coordinated action from multiple autonomous entities, such as traffic control, robotics, and resource management.

Papers

October 21, 2024

FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL
Woosung Koh, Wonbeen Oh, Siyeol Kim, Suhin Shin, Hyeongjin Kim, Jaein Jang, Junghyun Lee, Se-Young Yun
Multi Agent Reinforcement Learning Domain Generalization Multi Agent Particle Multi Agent RL Inference Stage Trajectory Generalization

July 31, 2024

Multi-agent reinforcement learning for the control of three-dimensional Rayleigh-B\'enard convection
Joel Vasanth, Jean Rabault, Francisco Alcántara-Ávila, Mikael Mortensen, Ricardo Vinuesa
Deep Reinforcement Learning Multi Agent Reinforcement Learning External Control Control Policy Multi Agent RL Single Agent RL Rayleigh B\'enard Convection

April 11, 2024

Differentially Private Reinforcement Learning with Self-Play
Dan Qiao, Yu-Xiang Wang
Multi Agent Reinforcement Learning Differential Privacy Self Play Episodic Markov Decision Process Multi Agent RL Single Agent RL Private Reinforcement Learning

April 5, 2024

Best Response Shaping
Milad Aghajohari, Tim Cooijmans, Juan Agustin Duque, Shunichi Akatsuka, Aaron Courville
Multi Agent Deep Reinforcement Learning Opponent Modeling Best Response Multi Agent RL

February 21, 2024

A Neuro-Symbolic Approach to Multi-Agent RL for Interpretability and Probabilistic Decision Making
Chitra Subramanian, Miao Liu, Naweed Khan, Jonathan Lenchner, Aporva Amarnath, Sarathkrishna Swaminathan, Ryan Riegel, Alexander Gray
Multi Agent Reinforcement Learning Inherent Interpretability Neuro Symbolic Neuro Symbolic Approach Probabilistic Logic Multi Agent RL Bayesian Decision Logical Neural Network

November 1, 2023

Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning
Matthias Gerstgrasser, Tom Danino, Sarah Keren
Multi Agent Reinforcement Learning eXperience Report Multi Agent RL

August 9, 2023

AI4GCC -- Track 3: Consumption and the Challenges of Multi-Agent RL
Marco Jiralerspong, Gauthier Gidel
Technical Challenge Learning Dynamic Competition Platform Shared Track Consumption Data Multi Agent RL

July 3, 2023

Learning Multi-Agent Communication with Contrastive Learning
Yat Long Lo, Biswa Sengupta, Jakob Foerster, Michael Noukhovitch
LeArning Abstract Contrastive Learning Mutual Information Multi Agent Communication Human Communication Multi Agent RL Effective Communication

April 25, 2023

Centralized control for multi-agent RL in a complex Real-Time-Strategy game
Roger Creus Castanyer
Multi Agent Reinforcement Learning Learning Agent RL Agent Centralized Control Real Time Strategy Multi Agent RL Single Agent RL

February 15, 2023

Scalable Multi-Agent Reinforcement Learning with General Utilities
Donghao Ying, Yuhao Ding, Alec Koppel, Javad Lavaei
Multi Agent Reinforcement Learning Policy Gradient Task Utility Policy Gradient Algorithm Multi Agent RL

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 Deep Deterministic Policy Multi Agent RL Cooperative Multi Agent Learning

August 22, 2022

Formal Contracts Mitigate Social Dilemmas in Multi-Agent RL
Andreas A. Haupt, Phillip J. K. Christoffersen, Mehul Damani, Dylan Hadfield-Menell
Data Augmentation Multi Agent Reinforcement Learning Multi Objective Reinforcement Learning Selfish Agent Contract Theory Multi Agent RL Exploration Exploitation Tradeoff

June 1, 2022

Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RL
Siyi Hu, Chuanlong Xie, Xiaodan Liang, Xiaojun Chang
Long Term Cooperation Cooperative Multi Agent Reinforcement Learning Multi Agent Challenge Multi Agent Cooperation Multi Agent Task Multi Agent Particle Multi Agent RL Policy Model Challenging Role Type

April 10, 2022

MA-Dreamer: Coordination and communication through shared imagination
Kenzo Lobos-Tsunekawa, Akshay Srinivasan, Michael Spranger
Timely Communication Model Training Prior Coordination Agent Communication Decentralized Agent Multi Agent RL

December 23, 2021

Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling
Benjamin Freed, Aditya Kapoor, Ian Abraham, Jeff Schneider, Howie Choset
LeArning Abstract Multi Agent Reinforcement Learning Actor Critic Algorithm Multi Agent Policy Multi Agent RL