Earlier Version

What is decidable about partially observable Markov decision processes with ω-regular objectives

K. Chatterjee, M. Chmelik, M. Tracol, What Is Decidable about Partially Observable Markov Decision Processes with ω-Regular Objectives, IST Austria, 2013.

Download
OA 483.41 KB

Technical Report | Published | English
Department
Series Title
IST Austria Technical Report
Abstract
We consider partially observable Markov decision processes (POMDPs) with ω-regular conditions specified as parity objectives. The class of ω-regular languages extends regular languages to infinite strings and provides a robust specification language to express all properties used in verification, and parity objectives are canonical forms to express ω-regular conditions. The qualitative analysis problem given a POMDP and a parity objective asks whether there is a strategy to ensure that the objective is satis- fied with probability 1 (resp. positive probability). While the qualitative analysis problems are known to be undecidable even for very special cases of parity objectives, we establish decidability (with optimal complexity) of the qualitative analysis problems for POMDPs with all parity objectives under finite- memory strategies. We establish asymptotically optimal (exponential) memory bounds and EXPTIME- completeness of the qualitative analysis problems under finite-memory strategies for POMDPs with parity objectives.
Publishing Year
Date Published
2013-02-20
Page
41
ISSN
IST-REx-ID

Cite this

Chatterjee K, Chmelik M, Tracol M. What Is Decidable about Partially Observable Markov Decision Processes with ω-Regular Objectives. IST Austria; 2013. doi:10.15479/AT:IST-2013-109-v1-1
Chatterjee, K., Chmelik, M., & Tracol, M. (2013). What is decidable about partially observable Markov decision processes with ω-regular objectives. IST Austria. https://doi.org/10.15479/AT:IST-2013-109-v1-1
Chatterjee, Krishnendu, Martin Chmelik, and Mathieu Tracol. What Is Decidable about Partially Observable Markov Decision Processes with ω-Regular Objectives. IST Austria, 2013. https://doi.org/10.15479/AT:IST-2013-109-v1-1.
K. Chatterjee, M. Chmelik, and M. Tracol, What is decidable about partially observable Markov decision processes with ω-regular objectives. IST Austria, 2013.
Chatterjee K, Chmelik M, Tracol M. 2013. What is decidable about partially observable Markov decision processes with ω-regular objectives, IST Austria, 41p.
Chatterjee, Krishnendu, et al. What Is Decidable about Partially Observable Markov Decision Processes with ω-Regular Objectives. IST Austria, 2013, doi:10.15479/AT:IST-2013-109-v1-1.
Main File(s)
Access Level
OA Open Access
Last Uploaded
2018-12-12T11:53:06Z


Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar