Return to search

Finite Memory Policies for Partially Observable Markov Decision Proesses

This dissertation makes contributions to areas of research on planning with POMDPs: complexity theoretic results and heuristic techniques. The most important contributions are probably the complexity of approximating the optimal history-dependent finite-horizon policy for a POMDP, and the idea of heuristic search over the space of FFTs.

Identiferoai:union.ndltd.org:uky.edu/oai:uknowledge.uky.edu:gradschool_diss-1326
Date01 January 2001
CreatorsLusena, Christopher
PublisherUKnowledge
Source SetsUniversity of Kentucky
Detected LanguageEnglish
Typetext
Formatapplication/pdf
SourceUniversity of Kentucky Doctoral Dissertations

Page generated in 0.0204 seconds