Exploration in POMDPs

Open Access
Authors
  • C. Dimitrakakis
Publication date 2008
Journal OGAI-Journal
Volume | Issue number 27 | 1
Pages (from-to) 24-31
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract In recent work, Bayesian methods for exploration in Markov decision processes (MDPs) and for solving known partially-observable Markov decision processes (POMDPs) have been proposed. In this paper we review the similarities and differences between those two domains and propose methods to deal with them simultaneously. This enables us to attack the Bayes-optimal reinforcement learning problem in POMDPs.
Document type Article
Published at http://www.science.uva.nl/research/isla/pub/IAS-UVA-08-01.pdf
Downloads
Permalink to this page
Back