Font Size: a A A

Finite memory policies for partially observable Markov decision processes

Posted on:2002-03-26Degree:Ph.DType:Dissertation
University:University of KentuckyCandidate:Lusena, Christopher DavidFull Text:PDF
GTID:1468390011492298Subject:Computer Science
Abstract/Summary:
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.
Keywords/Search Tags:Heuristic
Related items