Goodreads helps you keep track of books you want to read.
Start by marking “Reinforcement Learning: An Introduction” as Want to Read:
Reinforcement Learning: An Introduction
Enlarge cover
Rate this book
Clear rating
Open Preview

Reinforcement Learning: An Introduction

(Adaptive Computation and Machine Learning)

4.51  ·  Rating details ·  504 ratings  ·  56 reviews
Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications.

Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach t
Hardcover, 322 pages
Published February 26th 1998 by Bradford Book
More Details... Edit Details

Friend Reviews

To see what your friends thought of this book, please sign up.

Reader Q&A

To ask other readers questions about Reinforcement Learning, please sign up.

Be the first to ask a question about Reinforcement Learning

Community Reviews

Showing 1-30
Average rating 4.51  · 
Rating details
 ·  504 ratings  ·  56 reviews

More filters
Sort order
Start your review of Reinforcement Learning: An Introduction
☘Misericordia☘ ⚡ϟ⚡⛈⚡☁ ❇️❤❣
Takeouts: thoughts on
- Mone-Karlo methods,
- dynamic programming,
- learning from temporal differences.
Jon Gauthier
Despite its age, this book is still the canonical introduction to reinforcement learning.
I'm reading parts as necessary — not sure if I'll ever read cover-to-cover. In any case this has been an indispensable resource in my research career.
From the outside, RL seems mathy and somewhat stilted; from the inside, there is a lot of room for creativity and the core concepts are quite straightforward. I credit this book (along with some incredibly talented mentors) for introducing me to that beautiful
Jul 05, 2017 rated it it was amazing
I' not finished this book but already want to leave a review. This is a very readable and still rigorous description of reinforcement learning. The main difference between this book and many others in the field of machine learning is that the author really tries to make his work approachable by others. Reading this is a joy, highly recommended. ...more
Oleg Dats
Jul 24, 2018 rated it it was amazing
Shelves: ai
One of the best book I ever read. A big step toward AI. The book inspired me to dig deeper.
A good supplementary would be an online course by Sutton's student and a former lead at Deepmind David Silver.
Alex Telfar
Dec 24, 2018 rated it really liked it
Really good textbook.
I was surprised about how well we understand much of RL. Coming from ML this was a welcome novelty.
Although, I would have like to see a few more of the proofs and for there to be exercises.
Andrei Khrapavitski
Dec 30, 2017 rated it it was amazing
The book I spent my Christmas holidays with was Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto. The authors are considered the founding fathers of the field. And the book is an often-referred textbook and part of the basic reading list for AI researchers. Given my own interest and fledgling attempts in the area (I trained my first models in 2017), I thought worthwhile to spend some time learning some basics.

Reinforcement learning is one of the hottest fields in
Fermin Quant
Jan 30, 2017 rated it really liked it
Great book explaining the basic concepts of reinforcement learning. Parts I and II are very well explained. Part III I didn't like much but still quite informative, seems to be oriented for future research. ...more
Ondrej Sykora
Jan 04, 2012 rated it it was amazing
For me, this is one of the best books on AI. Even though the material is not that simple, everything is clearly explained and the book is comprehensible even for people who are not familiar with the concepts. Even though this is an older book, it is still the best I've seen on the topic. ...more
Mar 08, 2019 rated it it was amazing
Concise introduction to the field that is fueling the development of autonomous agents.
Will Dorrell
Apr 03, 2020 rated it it was amazing  ·  review of another edition
A really excellent textbook serving as an introduction to the field of Reinforcement Learning.

Does a really great job in a lot of ways:
i) very clear descriptions of almost all concepts
ii) a very systematic description that allows you to build a framework for understanding the field, permitting you to fit new bits of information into that framework
iii) Shows current work, extensions and touches on some recent exciting developments

Not so good:
i) trys very hard to be light on the maths, to the exte
Nov 17, 2017 rated it really liked it
A little dated, but in terms of learning the basics without a whole lot of digging, this is probably the best book out there. If you are thinking about getting into RL, I would recommend reading this first, then maybe Decision Making Under Uncertainty, reading some papers, reading the white paper on OpenAI's gym, and then messing around with gym. Sutton gives some excellent resources for understanding the history of RL and the maths behind it all, and if you have the time, it's worth reading all ...more
Crystal-Leigh Clitheroe
Feb 10, 2018 rated it really liked it
I only had enough knowledge to follow this book up until about chapter 10. Even so, so far one of my favourite books on machine learning. Clear, well-described problems within well-structured chapters, which build on each other in a logical way. Some folks have a working directory of the most illustrative problems from the book here: ...more
Sep 09, 2020 rated it really liked it  ·  review of another edition
Dense and informative. It would be helpful if there was a greater focus on building basic intuition with descriptive figures before diving into the technical details and heavy math. Like many textbooks the exercises felt like enormous jumps from the material and a better guide into them would be nice. Overall, though the book does give a nice tour-de-force of all the learning strategies developed to date and explores nuances of their behavior.
Bart Keulen
May 23, 2017 rated it it was amazing
Since its arrival it has been considered the bible for reinforcement learning. Sutton and Barto explain everything very well. I recommend this book to everyone who wants to start in the field of reinforcement learning. I do have to say that the first edition is missing some new developments, but a second edition is on the way (free pdf can be found online).
Jean Martins
Jan 14, 2019 rated it it was amazing
"Also related to TD learning are Holland's (1975, 1976) early ideas about consistency among value predictions. These influenced one of the authors (Barto), who was a graduate student from 1970 to 1975 at the University of Michigan, where Holland was teaching. Holland's ideas led to a number of TD-related systems..." ...more
John Doe
Dec 31, 2019 rated it it was amazing
Shelves: cs
worth re-reading.
great illustration on fundamental conceptual ideas.
needs some time to internalize all the methods and tricks about RL.
once you really got the idea, reinforcement learning becomes very intuitive.
yep, that's the most sensible way to build an automatic learning/optimizing robot.
Shyam Poovaiah
This is the book I read while following my RL course in IISc.
A good supplemental material to this book would be David Silver's course on the same topic on YouTube.
This book is succinct and provides the required intuitions.
Along with the Math and the Algorithms the initial chapters provide the breakthroughs in Behavioral Psychology which led to progress in RL.
Jul 08, 2018 rated it it was amazing
Read the 2017 draft in parts. Provides rigorous descriptions of RL algorithms in a readable manner. One of my favorite books on Machine Learning.

I recommend anyone interested in learning RL to start with this and then moving into papers.
Dec 21, 2018 rated it it was amazing  ·  review of another edition
Shelves: psychology
Excellent introduction to reinforcement learning. Well written, and does a good job of walking the reader through the algorithms and building a depth and breadth of knowledge. A lot of interesting examples included as well.
Budi Prawira
Jul 27, 2019 rated it it was amazing  ·  review of another edition
Best reference book for Reinforcement Learning

I used the first edition of this book as one of the key reference for my graduation thesis back in the 90s. This second edition brings everything up to date. It reminds me why I love RL so much.
Abdullah Shams
Aug 05, 2019 rated it really liked it  ·  review of another edition
Really natural progression and base covreage along the book, as you develpe from the broad to central, to the perticular, to the future.

Really recommend it to everyone who wants to build a knowledge around reinforcment lrearning and have a strong clear foundations.
Lara Thompson
Nov 05, 2019 rated it it was amazing  ·  review of another edition
Shelves: technical
Constantly building from simple algorithms to more complex ones and their variations. A beautiful taxonomy of RL is built. The examples are simple enough to try oneself and yet complex enough to distinguish the different approaches. Highly recommend.
Gourav Sengupta
Sep 08, 2020 rated it it was amazing  ·  review of another edition
okay, no one can review this book, this is a book based on which the entire subject has evolved. Its wonderfully written, lucid, clear, and helps to create the basis for evolving the subject for the next generations.

Farhad Da
Jan 31, 2021 rated it it was amazing  ·  review of another edition
I read this book along "Reinforcement Learning Specialization" in Coursera:

This book is compelling, complete, and it explains concepts in a way that is very understandable.
Nov 21, 2017 rated it really liked it
Excellent book for beginners on Reinforcement learning. The language may be little verbose but the examples are sufficient to grasp the concept.
Jan 12, 2018 rated it it was amazing
Done 4 chapters. I already feel like a Ninja! Damn!
Bing Wang
Jan 18, 2018 rated it it was amazing
Second edition, in progress
Richard S. Sutton and Andrew G. Barto ⃝c 2014, 2015, 2016, 2017

Skipped Chap 14 - 16 (Use Case)
Jun 17, 2018 rated it really liked it
Shelves: technical-10x, ai
The only RL textbook, and lucky for me it got its first update in 20 years just as I began.
Silvia Tulli
Jul 16, 2019 rated it it was amazing
Reinforcement Learning Introduction
Cristian Vasquez
Apr 23, 2020 rated it it was amazing
This rating is for the second edition.
« previous 1 next »
There are no discussion topics on this book yet. Be the first to start one »

Readers also enjoyed

  • Deep Learning
  • Pattern Recognition and Machine Learning
  • Introduction to Algorithms
  • Hands-On Machine Learning with Scikit-Learn, Keras, and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent Systems
  • The Book of Why: The New Science of Cause and Effect
  • The Hundred-Page Machine Learning Book
  • The Elements of Statistical Learning: Data Mining, Inference, and Prediction
  • Deep Learning with PyTorch
  • Probabilistic Graphical Models: Principles and Techniques
  • Deep Reinforcement Learning Hands-On: Apply modern RL methods, with deep Q-networks, value iteration, policy gradients, TRPO, AlphaGo Zero and more
  • Deep Learning with Python
  • Effective Modern C++: 42 Specific Ways to Improve Your Use of C++11 and C++14
  • A Philosophy of Software Design
  • What Is Life? with Mind and Matter and Autobiographical Sketches
  • The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World
  • Hands-On Machine Learning with Scikit-Learn and TensorFlow
  • Gödel, Escher, Bach: an Eternal Golden Braid
  • Slicing Pie - Funding Your Business Without Funds
See similar books…

Goodreads is hiring!

If you like books and love to build cool products, we may be looking for you.
Learn more »
Richard S. Sutton is Professor of Computing Science and AITF Chair in Reinforcement Learning and Artificial Intelligence at the University of Alberta, and also Distinguished Research Scientist at DeepMind.

Other books in the series

Adaptive Computation and Machine Learning (1 - 10 of 22 books)
  • Bioinformatics: The Machine Learning Approach (Adaptive Computation and Machine Learning)
  • Graphical Models for Machine Learning and Digital Communication
  • Learning in Graphical Models
  • Causation, Prediction, and Search (Adaptive Computation and Machine Learning)
  • Principles of Data Mining
  • Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
  • Learning Kernel Classifiers: Theory and Algorithms
  • Introduction to Machine Learning
  • Gaussian Processes for Machine Learning
  • Semi-Supervised Learning

News & Interviews

Ciannon Smart has been holed up in her England home since the pandemic began a year ago, but by no means has she been idle. She’s been on...
17 likes · 3 comments