POMDPs under probabilistic semantics Conference Paper


Author(s): Chatterjee, Krishnendu; Chmelík, Martin
Title: POMDPs under probabilistic semantics
Affiliation IST Austria
Abstract: We consider partially observable Markov decision processes (POMDPs) with limit-average payoff, where a reward value in the interval [0,1] is associated to every transition, and the payoff of an infinite path is the long-run average of the rewards. We consider two types of path constraints: (i) quantitative constraint defines the set of paths where the payoff is at least a given threshold λ ∈ (0, 1]; and (ii) qualitative constraint which is a special case of quantitative constraint with λ = 1. We consider the computation of the almost-sure winning set, where the controller needs to ensure that the path constraint is satisfied with probability 1. Our main results for qualitative path constraint are as follows: (i) the problem of deciding the existence of a finite-memory controller is EXPTIME-complete; and (ii) the problem of deciding the existence of an infinite-memory controller is undecidable. For quantitative path constraint we show that the problem of deciding the existence of a finite-memory controller is undecidable.
Conference Title: UAI: Uncertainty in Artificial Intelligence
Volume: 221
Conference Dates: July 11-15, 2013
Conference Location: Bellevue, Washington, USA
Publisher: AUAI Press  
Date Published: 2015-04-01
Start Page: 46
End Page: 72
URL:
DOI: 10.1016/j.artint.2014.12.009
Notes: We thank anonymous reviewers for several important suggestions that helped us to improve the presentation of the paper.
Open access: yes (repository)