The Complexity of Policy Evaluation for Finite-Horizon Partially-Observable Markov Decision Processes

Abstract

A partially-observable Markov decision process (POMDP) is a generalization of a Markov decision process that allows for incomplete information regarding the state of the system. POMDPs are used to model controlled stochastic processes, from health care to manufacturing control processes (see 19] for more examples). We consider several avors of nite-horizon… (More)
DOI: 10.1007/BFb0029956

Topics

Figures and Tables

Sorry, we couldn't extract any figures or tables for this paper.

Slides referencing similar topics