Vidal's library
Title: Discovering Hierarchy in Reinforcement Learning with HEXQ
Author: Bernhard Hengst
Book Tittle: Proceedings of the Nineteenth International Conference on Machine Learning
Pages: 243--250
Year: 2002
Abstract: An open problem in reinforcement learning is discovering hierarchical structure. HEXQ, an algorithm which automatically attempts to decompose and solve a model-free fac- tored MDP hierarchically is described. By searching for aliased Markov sub-space re- gions based on the state variables the algo- rithm uses temporal and state abstraction to construct a hierarchy of interlinked smaller MDPs.

Cited by 41  -  Google Scholar

@InProceedings{hengst02a,
  author =	 {Bernhard Hengst},
  title =	 {Discovering Hierarchy in Reinforcement Learning with
                  {HEXQ}},
  booktitle =	 {Proceedings of the Nineteenth International
                  Conference on Machine Learning},
  pages =	 {243--250},
  year =	 2002,
  abstract =	 {An open problem in reinforcement learning is
                  discovering hierarchical structure. HEXQ, an
                  algorithm which automatically attempts to decompose
                  and solve a model-free fac- tored MDP hierarchically
                  is described. By searching for aliased Markov
                  sub-space re- gions based on the state variables the
                  algo- rithm uses temporal and state abstraction to
                  construct a hierarchy of interlinked smaller MDPs.},
  keywords =     {learning reinforcement},
  url = 	 {http://jmvidal.cse.sc.edu/library/hengst02a.pdf},
  citeseer = 	 {hengst02discovering.html},
  googleid = 	 {OXSHyKx_1AgJ:scholar.google.com/},
  cluster = 	 {636273827441505337}
}
Last modified: Wed Mar 9 10:15:39 EST 2011