In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
Survey
|
App. Res. of Comp. Printed Article
Vol. 40, 2023 No. 11
3201-3210

Exploration approaches in deep reinforcement learning based on uncertainty: a review

Pang Jinhui
Feng Zicong
School of Computer Science, Beijing Institution of Technology, Beijing 100081, China
DOI: 10.19734/j.issn.1001-3695.2023.03.0130

Abstract

In recent years, DRL has made significant achievements in many complex sequence decision problem scenarios, such as game artificial intelligence, unmanned driving, robotics and finance. However, in many real-world application, DRL is faced with the problem of high sampling cost and low sampling efficiency. The ubiquitous uncertainty in the scene is an important reason for affecting the problem, deep reinforcement learning exploration methods based on uncertainty have become an important idea to solve the above problems. Firstly, this paper briefly introduced the important concepts and mainstream algorithms of DRL. Then it listed three classic exploration methods, and discussed the shortcoming of these methods in complex scenarios. After that, this paper introduced the concept of uncertainty and the background of importing uncertainty into the research of DRL exploration problems. On this basis, it summarized the existing exploration methods based on uncertainty, which were divided into three forms: optimism based, environmental uncertainty based and aleatoric uncertainty based approaches. It also analyzed the basic principles, advantages and disadvantages of each methods in detail. Finally, this review prospected the challenges and possible development directions of DRL exploration based on uncertainty.

Publish Information

DOI: 10.19734/j.issn.1001-3695.2023.03.0130
Publish at: Application Research of Computers Printed Article, Vol. 40, 2023 No. 11
Section: Survey
Pages: 3201-3210
Serial Number: 1001-3695(2023)11-001-3201-10

Publish History

[2023-06-07] Accepted Paper
[2023-11-05] Printed Article

Cite This Article

逄金辉, 冯子聪. 基于不确定性的深度强化学习探索方法综述 [J]. 计算机应用研究, 2023, 40 (11): 3201-3210. (Pang Jinhui, Feng Zicong. Exploration approaches in deep reinforcement learning based on uncertainty: a review [J]. Application Research of Computers, 2023, 40 (11): 3201-3210. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)