ShangtongZhang/reinforcement-learning-an-introduction

Python Implementation of Reinforcement Learning: An Introduction

51
/ 100
Established

This project offers Python code examples that replicate the algorithms and figures from Sutton & Barto's 'Reinforcement Learning: An Introduction' textbook. It takes descriptions of various environments (like games or optimization problems) as input and produces outputs such as optimal policies, value functions, and learning curves, illustrating how different reinforcement learning methods perform. This resource is primarily for students, researchers, or practitioners learning or studying reinforcement learning concepts.

14,587 stars. No commits in the last 6 months.

Use this if you are studying the second edition of Sutton & Barto's 'Reinforcement Learning: An Introduction' and want to see practical, runnable code implementations of the concepts and algorithms presented in the book.

Not ideal if you are looking for a ready-to-use reinforcement learning library for building applications or solving new problems, as this is primarily an educational replication of textbook examples.

reinforcement-learning-education algorithm-replication computational-learning-theory optimal-control-learning sequential-decision-making
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

14,587

Forks

4,965

Language

Python

License

MIT

Last pushed

Aug 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ShangtongZhang/reinforcement-learning-an-introduction"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.