This repository curates top-tier conference papers on Reinforcement Learning (RL), serving as a valuable resource for researchers and practitioners to track the latest advancements, trends, and cutting-edge algorithms. It categorizes papers by subfields like Multi-Agent RL, Meta RL, and RL with LLMs, providing direct links to PDFs and, where available, code.

How It Works

The project functions as a curated list, meticulously organized by RL sub-fields. Each entry includes the paper title, direct PDF link, author(s), and publication venue/year. The structure facilitates easy navigation and discovery of relevant research within specific RL domains.

Quick Start & Requirements

• No installation required; it's a curated list.
• Access to the internet to view linked papers.
• Links to official quick-start, docs, demo, or other relevant pages: GitHub Repository

Highlighted Details

• Comprehensive coverage of major RL conferences (NeurIPS, ICML, ICLR, AAAI, IJCAI, etc.).
• Categorization into key RL sub-fields: MARL, Meta RL, HRL, Offline RL, IRL, and RL with LLMs.
• Inclusion of PDF links for all listed papers and code links where available.
• Actively updated with recent conference papers (e.g., AAAI'23, ICML'23, ICLR'23).

Maintenance & Community

• The repository was created in January 2023 and has seen recent updates in November 2023.
• Contributions are welcomed via pull requests or direct contact with the maintainer.

Licensing & Compatibility

• The repository itself does not specify a license. The content consists of links to research papers, which are governed by their respective publishers' licenses.

Limitations & Caveats

The repository is a curated list and does not provide implementations or code for the papers. Code links are only included when explicitly provided by the paper's authors.