Nonapproximability Results for Partially Observable Markov Decision Processes

06/01/2011
by   J. Goldsmith, et al.
University of Kentucky
0

We show that for several variations of partially observable Markov decision processes, polynomial-time algorithms for finding control policies are unlikely to or simply don't have guarantees of finding policies within a constant factor or a constant summand of optimal. Here "unlikely" means "unless some complexity classes collapse," where the collapses considered are P=NP, P=PSPACE, or P=EXP. Until or unless these collapses are shown to hold, any control-policy designer must choose between such performance guarantees and efficient computation.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/30/2013

Planning with Partially Observable Markov Decision Processes: Advances in Exact Solution Method

There is much interest in using partially observable Markov decision pro...
03/24/2015

Geometry and Determinism of Optimal Stationary Control in Partially Observable Markov Decision Processes

It is well known that for any finite state Markov decision process (MDP)...
06/11/2014

Quantum POMDPs

We present quantum observable Markov decision processes (QOMDPs), the qu...
10/04/2019

Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget

Active perception strategies enable an agent to selectively gather infor...
01/21/2022

On probability-raising causality in Markov decision processes

The purpose of this paper is to introduce a notion of causality in Marko...
12/07/2017

Remarks on Bayesian Control Charts

There is a considerable amount of ongoing research on the use of Bayesia...
08/19/2019

Evaluating Hierarchies through A Partially Observable Markov Decision Processes Methodology

Hierarchical clustering has been shown to be valuable in many scenarios,...