Fuzzy policy gradient reinforcement learning for leader-follower systems

Gu, Dongbing and Yang, Erfu; Gu, Jason and Liu, Peter X., eds. (2005) Fuzzy policy gradient reinforcement learning for leader-follower systems. In: 2005 IEEE International Conference on Mechatronics & Automations. IEEE, GBR, pp. 1557-1561. ISBN 078039044X (https://doi.org/10.1109/ICMA.2005.1626787)

Abstract

This paper presents a policy gradient multi-agent reinforcement learning algorithm for leader-follower systems. In this algorithm, cooperative dynamics of the leader-follower control is modelled as an incentive Stackelberg game. A linear incentive mechanism is used to connect the leader and follower policies. Policy gradient reinforcement learning explicitly explores policy parameter space to search the optimal policy. Fuzzy logic controllers are used as the policy. The parameters of fuzzy logic controllers can be improved by this policy gradient algorithm.

ORCID iDs

Yang, Erfu ORCID: https://orcid.org/0000-0003-1813-5950

• Share and Export
  

  MPEG-21 DIDLASCII CitationHTML CitationRefWorksMETSSimple MetadataRDF+XMLMultiline CSVEndNoteEP3 XMLBibTeXRDF+N3AtomData Cite XMLMODSJSONOpenURL ContextObject in SpanRDF+N-TriplesDublin CoreReferOpenURL ContextObjectRIOXX2 XMLRIS (EndNote Online, Zotero, Ref manager, etc)
• Item metadata

  Item type:	Book Section
  ID code:	53294
  Dates:	Date Event 1 July 2005 Published
  Subjects:	Technology > Electrical engineering. Electronics Nuclear engineering
  Department:	Faculty of Engineering > Design, Manufacture and Engineering Management
  Depositing user:	Pure Administrator
  Date deposited:	05 Jun 2015 10:30
  Last modified:	11 Nov 2024 15:00
  Related URLs:	Scopus publication Journal or Publication Event
  URI:	https://strathprints.strath.ac.uk/id/eprint/53294