articleIEEE Signal Processing MagazineNov 1, 2017Closed access

Deep Reinforcement Learning: A Brief Survey

Arizona State University · Institution of Engineering and Technology · +1 more institution

Indexed incrossref

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 higher-level 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…

Citation impact

4,248
total citations
FWCI
140.68
Percentile
100%
References
252
Citations per year

Authors

4

Topics & keywords

Keywords
  • Reinforcement learning
  • Computer science
  • Artificial intelligence
  • Deep learning
  • Field (mathematics)
  • Artificial neural network
  • Robotics
  • Asynchronous communication
No related works found for this paper.