RL-Resources

Useful resources relating to Reinforcement Learning

Table of Contents

• RL-Resources
  • Table of Contents
  • Blogs
  • Courses
  • Algorithm Papers or Applications
  • Competitions
  • Other Lists

Blogs

• Pathmind AI Wiki: A Beginner's Guide to Deep Reinforcement Learning
• OpenAI PPO Baselines: Provides short explanation of PPO, with baselines of PPO, PPO2, ACER, and TRPO.
• Kaparthy RL: Andrej Kaparthy's Thoughts on RL
• Lil'Log Lilian Weng's Blog, all things RL
• Hugging Face Illustrating Reinforcement Learning from Human Feedback (RLHF)
• Hugging Face Introducing Decision Transformers on Hugging Face 🤗
• Deepmind Optimising computer systems with more generalised AI tools

Courses

• Hugging Face Deep-RL: Course on Deep-RL
• Stanford CS234: Stanford course on RL
• Berkeley Deep-RL: Berkeley course on RL
• Kaggle: Quick courses on a variety of data science and ML topics
• OpenAI Spinning Up: Educational resource produced by OpenAI that makes it easier to learn about Deep-RL
• UCLxDavid-Silver RL: David Silver teaches RL at UCL in 2015
• DeepMind YT Playlist: A series of lectures by DeepMind

Algorithm Papers or Applications

• (ICML'15): Trust Region Policy Optimization (TRPO) PDF
• Solving Large Imperfect Information Games Using (CFR+) PDF
• MCCFR: Monte Carlo Sampling for Regret Minimization in Extensive Games PDF
• Pluribus: Superhuman AI for multiplayer poker PDF Meta AI Blog
• ReBeL: Combining Deep Reinforcement Learning and Search for Imperfect-Information Games arXiv Github
• AlphaStar: Mastering the real-time strategy game StarCraft II Deepmind Blog
• Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy Deepmind Blog Nature
• Mastering Stratego, the classic game of imperfect information Deepmind Blog DeepNash Paper Science Article DeepNash Code

Competitions

• Lux AI: Multi-agent RL, unit navigation, resource gathering, macro and micro strategies, multi-variable optimization, resource gathering , and allocation problem

Other Lists

• MSAIL: Michigan Student Artificial Intelligence Lab