Causal graph based dynamic optimization of hierarchies for factored MDPs

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

Abstract

This paper presents an approach based on casual graph to optimize the task hierarchies for Hierarchical Reinforcement Learning (HRL). We conducted experiments to show that the resulting task hierarchies can improve effectiveness of reinforcement leaning.

Original languageEnglish
Title of host publicationProceedings - 2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012
Pages579-582
Number of pages4
DOIs
StatePublished - 2012
Externally publishedYes
Event2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012 - Macau, China
Duration: 4 Dec 20127 Dec 2012

Publication series

NameProceedings - 2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012

Conference

Conference2012 IEEE/WIC/ACM International Conference on Web Intelligence, WI 2012
Country/TerritoryChina
CityMacau
Period4/12/127/12/12

Keywords

  • Complex systems
  • casual graph
  • genetic programming
  • hierarchical reinforcement learning

Cite this