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

@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