Deciding the Value 1 Problem for sharp-acyclic Partially Observable Markov Decision Processes

Abstract : The value 1 problem is a natural decision problem in algorithmic game theory. For partially observable Markov decision processes with reachability objective, this problem is defined as follows: are there observational strategies that achieve the reachability objective with probability arbitrarily close to 1? This problem was shown undecidable recently. Our contribution is to introduce a class of partially observable Markov decision processes, namely ]-acyclic partially observable Markov decision processes, for which the value 1 problem is decidable. Our algorithm is based on the construction of a two-player perfect information game, called the knowledge game, abstracting the behaviour of a ]-acyclic partially observable Markov decision process M such that the first player has a winning strategy in the knowledge game if and only if the value of M is 1.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01006394
Contributor : Hugo Gimbert <>
Submitted on : Monday, June 16, 2014 - 8:38:09 AM
Last modification on : Tuesday, February 12, 2019 - 12:06:02 PM
Long-term archiving on: Tuesday, September 16, 2014 - 11:01:07 AM

File

pomdp.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Hugo Gimbert, Youssouf Oualhadj. Deciding the Value 1 Problem for sharp-acyclic Partially Observable Markov Decision Processes. SOFSEM 2014, Jan 2014, Nový Smokovec, Slovakia. pp.281-292, ⟨10.1007/978-3-319-04298-5_25⟩. ⟨hal-01006394⟩

Share

Metrics

Record views

425

Files downloads

170