This repository is a comprehensive, curated list of resources for Reinforcement Learning (RL), aimed at researchers, students, and practitioners. It provides a structured overview of foundational theory, key papers, practical applications, and open-source tools, serving as a central hub for the RL community.

How It Works

The list is organized thematically, covering theory (lectures, books, surveys), papers and theses, applications across various domains (games, robotics, control), and practical resources like code repositories, tutorials, and open-source platforms. This broad categorization allows users to navigate the vast RL landscape efficiently.

Quick Start & Requirements

This is a curated list, not a runnable project. Installation and usage depend on the specific tools and libraries linked within the repository.

Highlighted Details

• Extensive collection of academic papers, including foundational works and recent advancements.
• Links to numerous open-source RL platforms and libraries (e.g., OpenAI Gym, DeepMind Lab, Ray RLlib, Unity ML Agents).
• Curated lecture series from top universities (DeepMind, UCL, UC Berkeley, Stanford, MIT).
• Categorized application examples in game playing, robotics, control, and operations research.

Maintenance & Community

The project is maintained by Hyunsoo Kim and Jiwon Kim. It encourages community contributions via pull requests. Links to external communities or active development discussions are not explicitly provided in the README.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific license. The licenses of the linked projects vary, and users should consult the individual repositories for their respective licensing terms and compatibility.

Limitations & Caveats

The README states that "This page is no longer maintained," suggesting potential staleness of links and information. The breadth of resources means users must independently verify the currency and relevance of individual items.