Foundations and Trends® in Machine Learning > Vol 11 > Issue 3-4

An Introduction to Deep Reinforcement Learning

By Vincent François-Lavet, McGill University, Canada, vincent.francois-lavet@mcgill.ca | Peter Henderson, McGill University, Canada, peter.henderson@mail.mcgill.ca | Riashat Islam, McGill University, Canada, riashat.islam@mail.mcgill.ca | Marc G. Bellemare, Google Brain, USA, bellemare@google.com | Joelle Pineau, McGill University, Canada, jpineau@cs.mcgill.ca

 
Suggested Citation
Vincent François-Lavet, Peter Henderson, Riashat Islam, Marc G. Bellemare and Joelle Pineau (2018), "An Introduction to Deep Reinforcement Learning", Foundations and Trends® in Machine Learning: Vol. 11: No. 3-4, pp 219-354. http://dx.doi.org/10.1561/2200000071

Publication Date: 20 Dec 2018
© 2018 V. François-Lavet, P. Henderson, R. Islam, M. G. Bellemare and J. Pineau
 
Subjects
Reinforcement learning,  Deep learning,  Artificial intelligence in robotics
 

Free Preview:

Download extract

Share

Journal details

Download article
In this article:
1. Introduction 
2. Machine learning and deep learning 
3. Introduction to reinforcement learning 
4. Value-based methods for deep RL 
5. Policy gradient methods for deep RL 
6. Model-based methods for deep RL 
7. The concept of generalization 
8. Particular challenges in the online setting 
9. Benchmarking Deep RL 
10. Deep reinforcement learning beyond MDPs 
11. Perspectives on deep reinforcement learning 
12. Conclusion 
Appendix 
References 

Abstract

Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has been able to solve a wide range of complex decisionmaking tasks that were previously out of reach for a machine. Thus, deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many more. This manuscript provides an introduction to deep reinforcement learning models, algorithms and techniques. Particular focus is on the aspects related to generalization and how deep RL can be used for practical applications. We assume the reader is familiar with basic machine learning concepts.

DOI:10.1561/2200000071

Book details

ISBN: 978-1-68083-538-0
156 pp. $99.00
Buy book (pb)
 
ISBN: 978-1-68083-539-7
156 pp. $140.00
Buy E-book (.pdf)
Table of contents:
1. Introduction
2. Machine learning and deep learning
3. Introduction to reinforcement learning
4. Value-based methods for deep RL
5. Policy gradient methods for deep RL
6. Model-based methods for deep RL
7. The concept of generalization
8. Particular challenges in the online setting
9. Benchmarking Deep RL
10. Deep reinforcement learning beyond MDPs
11. Perspectives on deep reinforcement learning
12. Conclusion
Appendix
References

An Introduction to Deep Reinforcement Learning

Deep reinforcement learning is the combination of reinforcement learning (RL) and deep learning. This field of research has recently been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine.

Deep RL opens up many new applications in domains such as healthcare, robotics, smart grids, finance, and many more. This book provides the reader with a starting point for understanding the topic. Although written at a research level it provides a comprehensive and accessible introduction to deep reinforcement learning models, algorithms and techniques. Particular focus is on the aspects related to generalization and how deep RL can be used for practical applications.

Written by recognized experts, this book is an important introduction to Deep Reinforcement Learning for practitioners, researchers and students alike.

 
MAL-071