This repository is a curated collection of research and review papers on Multi-Agent Reinforcement Learning (MARL), organized by topic and publication date. It serves as a comprehensive resource for researchers and practitioners in the MARL field, offering a structured overview of foundational concepts, algorithms, and applications, particularly in LLMs and robotics.

How It Works

The repository functions as a bibliography, categorizing papers into key areas such as tutorials, reviews, frameworks, and specific research themes like joint action learning, cooperation, security, self-play, communication, and transfer learning. It also highlights MARL applications in Large Language Models (LLMs) and Robotics, providing a temporal and thematic map of the field's evolution.

Quick Start & Requirements

This is a curated list of papers, not a software library. No installation or execution is required.

Highlighted Details

• Extensive coverage of MARL subfields including coordination, security, self-play, and communication.
• Dedicated sections for MARL applications in LLMs and Robotics.
• Papers are sorted chronologically within categories, aiding historical research.
• Includes seminal works and recent advancements, spanning from 1994 to 2024.

Maintenance & Community

The project welcomes suggestions and pull requests. The sharing principle is for research purposes, with provisions for authors to request paper removal.

Licensing & Compatibility

The repository itself is a collection of links to academic papers. The licensing and usage terms are dictated by the original publishers of the papers.

Limitations & Caveats

This is a passive collection of papers and does not provide code, implementations, or direct access to the research content itself. Users must locate and access the papers through their respective academic channels.