Cooperative Agent

Cooperative agent research focuses on designing and analyzing systems where multiple agents work together to achieve a common goal, often in complex or uncertain environments. Current research emphasizes robust algorithms, such as those based on reinforcement learning (including multi-agent variants like Qmix and VDN), graph neural networks, and large language models (LLMs), to enable effective communication, coordination, and resilience to adversarial attacks or unreliable communication. These advancements are significant for various applications, including robotics, autonomous systems, and human-AI collaboration, by improving efficiency, robustness, and the ability to handle increasingly complex tasks. The field is also actively exploring methods for enhancing transparency and explainability in multi-agent systems.

Papers

November 11, 2022

Autotelic Reinforcement Learning in Multi-Agent Environments
Eleni Nisioti, Elías Masquil, Gautier Hamon, and Clément Moulin-Frier
Decentralized Learning Multi Agent Environment Cooperative Agent Multi Agent Exploration Multi Goal Autotelic Agent Coordination Game

October 23, 2022

A Cooperative Reinforcement Learning Environment for Detecting and Penalizing Betrayal
Nikiforos Pittaras
Data Detection Cooperative Agent Self Interested Agent Betrayal Detection

October 14, 2022

Decentralized Coverage Path Planning with Reinforcement Learning and Dual Guidance
Yongkai Liu, Jiawei Hu, Wei Dong
Reinforcement Learning Multiple Robot Coverage Path Planning Cooperative Agent Decentralized Reinforcement Learning Rethinking Guidance

June 26, 2022

Tackling Asymmetric and Circular Sequential Social Dilemmas with Reinforcement Learning and Graph-based Tit-for-Tat
Tangui Le Gléau, Xavier Marjou, Tayeb Lemlouma, Benoit Radier
Reinforcement Learning Information Asymmetry Cooperative Agent Non Cooperative Game Empirical Game Sequential Social Dilemma

May 24, 2022

Graph Convolutional Reinforcement Learning for Collaborative Queuing Agents
Hassan Fawaz, Julien Lesca, Pham Tran Anh Quang, Jérémie Leguay, Djamal Zeghlache, Paolo Medagliani
Multi Agent Reinforcement Learning Multi Agent Deep Q Network Graph Reinforcement Learning Cooperative Agent Competitive Agent

April 26, 2022

Toward Policy Explanations for Multi-Agent Reinforcement Learning
Kayla Boggess, Sarit Kraus, Lu Feng
Multi Agent Reinforcement Learning Multi Agent Agent Behavior Explainable Reinforcement Learning Cooperative Agent Interpretable Policy

April 9, 2022

Trust-based Rate-Tunable Control Barrier Functions for Non-Cooperative Multi-Agent Systems
Hardik Parwana, Dimitra Panagou
Multi Agent System Control Barrier Function Cooperative Agent Heterogeneous Multi Agent Non Cooperative

November 29, 2021

Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning
Ralvi Isufaj, Marsel Omeri, Miquel Angel Piera
Collision Avoidance Graph Reinforcement Learning Cooperative Agent Conflict Detection

November 12, 2021

Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation
Martin Figura, Yixuan Lin, Ji Liu, Vijay Gupta
Multi Agent Reinforcement Learning Actor Critic Algorithm Function Approximation Adversarial Agent Cooperative Agent Byzantine Agent

Cooperative Agent

Papers

Autotelic Reinforcement Learning in Multi-Agent Environments

A Cooperative Reinforcement Learning Environment for Detecting and Penalizing Betrayal

Decentralized Coverage Path Planning with Reinforcement Learning and Dual Guidance

Tackling Asymmetric and Circular Sequential Social Dilemmas with Reinforcement Learning and Graph-based Tit-for-Tat

Graph Convolutional Reinforcement Learning for Collaborative Queuing Agents

Toward Policy Explanations for Multi-Agent Reinforcement Learning

Trust-based Rate-Tunable Control Barrier Functions for Non-Cooperative Multi-Agent Systems

Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning

Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation