Recently, a number of researchers have proposed spectral algorithms for learning models of dynamical systems—for example, Hidden Markov Models (HMMs), Partially Observable Marko...
: Partially-observable Markov decision processes provide a very general model for decision-theoretic planning problems, allowing the trade-offs between various courses of actions t...
— We introduce the Oracular Partially Observable Markov Decision Process (OPOMDP), a type of POMDP in which the world produces no observations; instead there is an “oracle,” ...
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...
In this paper, we describe the partially observable Markov decision process pomdp approach to nding optimal or near-optimal control strategies for partially observable stochastic ...
Anthony R. Cassandra, Leslie Pack Kaelbling, Micha...