There are 2 repositories under sutton-barto-book topic.
self-studying the Sutton & Barto the hard way
Solutions to Sutton and Barto book exercises
Cheatsheet of Reinforcement Learning (Based on Sutton-Barto Book - 2nd Edition)
A summary of important concepts and algorithms in RL
Reinforcement Learning Algorithms in FrozenLake-v1
A python implementation of the concepts in the book "Reinforcement Learning: An Introduction" by R.S. Sutton and A. G. Barto.
Chapter notes and exercise solutions for Reinforcement Learning: An Introduction by Sutton and Barto
Python implementation of RL algorithms presented in Richard Sutton and Andrew Barto's book Reinforcement Learning: An Introduction (second edtion)
reinforcement learning algorithms, models and experiments
Reinforcement Learning (Sutton, Barto) - solved exercises
|| Studying RL the hard way || Implementation of Important Algorithms in PyTorch from "Reinforcement Learning an Introduction" by Sutton and Barto along with RL papers
⚡️ Code and Notes 📝 for Grokking Deep RL and RL: An Introduction by Sutton & Barto(2nd edition, 2018) 🤘
Recreation of the classic video-game "The Snake" into a 3D scenario. Implemented with Monte Carlo ES algorithm.
This repo consists of all the Python notebooks that are part of the Coursera specialization for Reinforcement Learning.
Implementations of RL Algos and solved exercises for Sutton&Barto RLAI
simple cliff walk implementation
Train an AI to drive on a simple racetrack, by using reinforcement learning with Q-Learning and Monte Carlo. Inspired by Sutton and Barto's book.
My own codes for exercises of the book by Sutton and Barto
Own implementation of the Q-learning algorithm presented on the example of the "treasure hunter" game.
My take on some problems from "Reinforcement Learning: An Introduction" by Sutton & Barto
Windy Grid World solution from sutton and bartos book.
self-studying the Sutton & Barto the hard way
Some python implementations from the book, "Reinforcement Learning: An Introduction" by Andrew Barto and Richard S. Sutton.