Free online chapter-by-chapter companion for Qiu Xipeng's Chinese deep learning textbook, in a full edition and a general-reader edition, with PDFs and errata.
alxndrTL/little-book-rl
A short introductory book on reinforcement learning, from basics to applied algorithms, with PyTorch implementations in the repo.
- Stars
- 1,715
- Forks
- 96
- Open issues
- 1
- Last commit
- 3 months ago
What is it?
The Little Book of Reinforcement Learning is a short introduction to reinforcement learning that moves from foundational concepts to applied algorithms. This repository hosts the book together with its supplementary material.
The algos/ folder contains PyTorch implementations of the algorithms covered in the book, ranging from Monte Carlo methods to PPO. The supplementary/ folder holds a document with detailed explanations and formal proofs for the dynamic programming algorithms that the book introduces briefly.
The book is distributed under a non-commercial Creative Commons license (CC BY-SA 4.0), and a printed edition is available for purchase.
Key features
- 01Covers reinforcement learning from basic concepts to applied algorithms.
- 02Provides PyTorch implementations of algorithms from Monte Carlo to PPO.
- 03Includes supplementary proofs for dynamic programming methods.
- 04Distributed under a non-commercial CC BY-SA 4.0 license.
Use cases
- Learning reinforcement learning from scratch with a concise textbook.
- Studying working PyTorch code alongside the algorithms described in the book.
- Reviewing the proofs behind dynamic programming methods.
Things to know
- The README describes the license as non-commercial but names CC BY-SA 4.0, which does not restrict commercial use, so the terms are unclear.
- The repository metadata lists no license.
- The README gives no installation or run instructions for the PyTorch implementations in algos/.
Topics
FAQ
- What is little-book-rl?
- A short introductory book on reinforcement learning, from basics to applied algorithms, with PyTorch implementations in the repo. The Little Book of Reinforcement Learning is a short introduction to reinforcement learning that moves from foundational concepts to applied algorithms. This repository hosts the book together with its supplementary material.
- Is little-book-rl free to use? What license does it have?
- little-book-rl has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is little-book-rl still maintained?
- Updated within 6 months. The last commit to little-book-rl was on Jul 14, 2026.
- What can I use little-book-rl for?
- Learning reinforcement learning from scratch with a concise textbook. Studying working PyTorch code alongside the algorithms described in the book. Reviewing the proofs behind dynamic programming methods.
- Where can I get little-book-rl?
- The source code and installation instructions are on GitHub: https://github.com/alxndrTL/little-book-rl
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Model-definition framework for state-of-the-art text, vision, audio and multimodal machine learning models, for inference and training.
AI-oriented quantitative investment platform from Microsoft covering data, model training, backtesting and order execution for quant research.
Ray is a unified framework for scaling Python and AI applications from a laptop to a cluster, with a distributed runtime and AI libraries.
Unity ML-Agents Toolkit lets Unity games and simulations serve as environments for training AI agents with reinforcement and imitation learning.
PyTorch implementations of reinforcement learning algorithms, designed as a reliable, consistent baseline for research and applications.