# Reinforcement Learning
=> ../academic/ Theodore Tollet
2023-05-11

A collection of resources relevant to the study of reinforcement learning.

=> https://raw.githubusercontent.com/fakemonk1/Reinforcement-Learning-Lunar_Lander/master/images/3.gif lunar lander
An RL agent completes a 2D model moon landing in the lunar lander environment.
=> https://github.com/fakemonk1/Reinforcement-Learning-Lunar_Lander source
=> gallery.gmi gallery

[1] These are considered the primary introductions to Reinforcement Learning:
=> http://incompleteideas.net/book/the-book-2nd.html 2019 | "Reinforcement Learning: An Introduction" by Sutton & Barto
=> https://www.davidsilver.uk/teaching/ 2015 | David Silver's UCL Lectures

[2] Pieter Abbeel’s 6-part lecture series is intuitively explained, giving each topic’s motivation:
=> https://youtube.com/playlist?list=PLwRJQ4m4UJjNymuBM9RdmB3Z9N5-0IlY0 2022 | Foundations of Deep RL

[3] Bertsekas' book provides a comprehensive research focussed approach:
=> https://web.mit.edu/dimitrib/www/RLbook.html 2023 | "A Course in Reinforcement Learning"

[4] Hugging Face provide a well structured & popular contemporary DeepRL course:
=> https://huggingface.co/learn/deep-rl-course/unit0/introduction 2018 | Welcome to the 🤗 Deep Reinforcement Learning Course

[5] Lillian Weng's blog post below is a superb reference for the core concepts:
=> https://lilianweng.github.io/posts/2018-02-19-rl-overview/ 2018 | A (Long) Peek into RL


## Python Tools
=> https://github.com/Farama-Foundation/Gymnasium Gymnasium (Gym)
Provides the standard interface for reinforcement learning environments, in addition to a collection of common environments.

=> https://github.com/DLR-RM/stable-baselines3 Stable Baselines3 (SB3)
Reliable PyTorch-based implementations of widely used RL algorithms.


## Other
=> https://cs.stanford.edu/people/karpathy/reinforcejs/index.html [6] REINFORCEjs: Interactive DP, TD-learning & DQN in your browser!
=> https://github.com/aikorea/awesome-rl An unmaintained (since 2022) but useful list of varying quality
=> https://github.com/eugeneyan/applied-ml#reinforcement-learning 12 uses of RL in industry


## People
[1]
=> http://www.incompleteideas.net/ Richard Sutton
=> https://people.cs.umass.edu/~barto/ Andrew Barto
=> https://www.davidsilver.uk/ David Silver

[2]
=> https://people.eecs.berkeley.edu/~pabbeel/ Pieter Abbeel

[3]
=> https://web.mit.edu/dimitrib/www/home.html Dmitri Bertsekas

[4]
=> https://simoninithomas.com/ Thomas Simonini
=> https://osanseviero.github.io/hackerllama/ Omar Sansevier
=> https://sayak.dev/ Sayak Paul

[5]
=> http://lilianweng.github.io/ Lilian Weng

[6]
=> https://karpathy.ai/ Andrej Karpathy

---
Feel free to send comments & corrections to me at:
=> https://sigmoid.social/@ttollet @ttollet@sigmoid.social

Last updated 2023-05-17