A brief survey of deep reinforcement learning
File(s)
Accepted version
Author(s)
Arulkumaran, K
Deisenroth, MP
Brundage, M
Bharath, AA
Type
Journal Article
Abstract
Deep reinforcement learning (DRL) is poised to revolutionize the field of artificial intelligence (AI) and represents a step toward building autonomous systems with a higherlevel understanding of the visual world. Currently, deep learning is enabling reinforcement learning (RL) to scale to problems that were previously intractable, such as learning to play video games directly from pixels. DRL algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of RL, then progress to the main streams of value-based and policy-based methods. Our survey will cover central algorithms in deep RL, including the deep Q-network (DQN), trust region policy optimization (TRPO), and asynchronous advantage actor critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via RL. To conclude, we describe several current areas of research within the field.
Date Issued
2017-11-09
Date Acceptance
2017-08-01
Citation
IEEE Signal Processing Magazine, 2017, 34, pp.26-38
ISSN
1053-5888
Publisher
Institute of Electrical and Electronics Engineers
Start Page
26
End Page
38
Journal / Book Title
IEEE Signal Processing Magazine
Volume
34
Copyright Statement
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Identifier
https://arxiv.org/pdf/1708.05866.pdf
Subjects
cs.LG
cs.AI
stat.ML
0906 Electrical And Electronic Engineering
0913 Mechanical Engineering
Networking & Telecommunications
Article Number
6