Towards dynamic epistemic learning of actions for self-improving agents and multi-agent systems

Shuai Wang*

*Corresponding author for this work

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

Abstract

Action learning is an important aspect of self-improving. This paper explores a new approach for the learning of two types of actions, namely precondition-free actions and conditional actions. The corresponding two learning algorithms are designed and implemented using modern logic reasoners. Finally, a simple system of action learning agents is implemented to explore cooperative self-improving multi-agent systems.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE International Conference on Autonomic Computing, ICAC 2016
EditorsHolger Giese, Samuel Kounev, Jie Liu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages292-299
Number of pages8
ISBN (Electronic)9781509016532
DOIs
Publication statusPublished - 21 Sep 2016
Externally publishedYes
Event13th IEEE International Conference on Autonomic Computing, ICAC 2016 - Wurzburg, Germany
Duration: 18 Jul 201622 Jul 2016

Publication series

NameProceedings - 2016 IEEE International Conference on Autonomic Computing, ICAC 2016

Conference

Conference13th IEEE International Conference on Autonomic Computing, ICAC 2016
CountryGermany
CityWurzburg
Period18/07/1622/07/16

Keywords

  • action learning
  • dynamic epistemic logic
  • multi-agent system
  • self-improving

Fingerprint

Dive into the research topics of 'Towards dynamic epistemic learning of actions for self-improving agents and multi-agent systems'. Together they form a unique fingerprint.

Cite this