Skip to main navigation Skip to search Skip to main content

Particle Swarm Based Reinforcement Learning

  • Xi'an Jiaotong University
  • CETC Key Laboratory of Data Link Technology Xi’an

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

With the vigorous development of computer-related technology, the “perception + decision” paradigm of the combination of deep learning and reinforcement learning has become a research hotspot. Nowadays, deep reinforcement learning algorithms have been successfully applied to the fields of games, industry and commerce. However, deep reinforcement learning algorithms often fall into the dilemma of “exploration” and “exploitation”, and the effect of these algorithms is easily affected by the quality of hyperparameters. In order to make up for the defects mentioned above, this paper introduces the particle swarm based reinforcement learning framework (PRL). Compared with the standard reinforcement learning algorithms, this framework greatly improves the exploration ability and obtains better scores in a series of gym experimental tests.

Original languageEnglish
Title of host publicationData Mining and Big Data - 7th International Conference, DMBD 2022, Proceedings
EditorsYing Tan, Yuhui Shi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages27-36
Number of pages10
ISBN (Print)9789811992964
DOIs
StatePublished - 2022
Event7th International Conference on Data Mining and Big Data, DMBD 2022 - Beijing, China
Duration: 21 Nov 202224 Nov 2022

Publication series

NameCommunications in Computer and Information Science
Volume1744 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference7th International Conference on Data Mining and Big Data, DMBD 2022
Country/TerritoryChina
CityBeijing
Period21/11/2224/11/22

Keywords

  • Particle swarm optimization
  • Reinforcement learning
  • Twin delayed deep deterministic policy gradients

Fingerprint

Dive into the research topics of 'Particle Swarm Based Reinforcement Learning'. Together they form a unique fingerprint.

Cite this