BALAJI, Nikhil, Stefan KIEFER, Petr NOVOTNÝ, Guillermo A. PÉREZ and Mahsa SHIRMOHAMMADI. On the Complexity of Value Iteration. Online. In Christel Baier, Ioannis Chatzigiannakis, Paola Flocchini, Stefano Leonardi. Proceedings of the 46th International Colloquium on Automata, Languages, and Programming (ICALP 2019). Dagstuhl, Germany: Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, 2019. p. "102:1"-"102:15", 15 pp. ISBN 978-3-95977-109-2. Available from: https://dx.doi.org/10.4230/LIPIcs.ICALP.2019.102. [citováno 2024-04-24]
Other formats:   BibTeX LaTeX RIS
Basic information
Original name On the Complexity of Value Iteration
Authors BALAJI, Nikhil (356 India), Stefan KIEFER (276 Germany), Petr NOVOTNÝ (203 Czech Republic, guarantor, belonging to the institution), Guillermo A. PÉREZ (340 Honduras) and Mahsa SHIRMOHAMMADI (364 Islamic Republic of Iran)
Edition Dagstuhl, Germany, Proceedings of the 46th International Colloquium on Automata, Languages, and Programming (ICALP 2019), p. "102:1"-"102:15", 15 pp. 2019.
Publisher Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10200 1.2 Computer and information sciences
Country of publisher Germany
Confidentiality degree is not subject to a state or trade secret
Publication form electronic version available online
RIV identification code RIV/00216224:14330/19:00107669
Organization unit Faculty of Informatics
ISBN 978-3-95977-109-2
ISSN 1868-8969
Doi http://dx.doi.org/10.4230/LIPIcs.ICALP.2019.102
Keywords in English Markov decision processes; probabilistic verification; value iteration
Tags core_A, firank_A, formela-ver
Tags International impact, Reviewed
Changed by Changed by: doc. RNDr. Petr Novotný, Ph.D., učo 172743. Changed: 17/4/2020 12:16.
Abstract
Value iteration is a fundamental algorithm for solving Markov Decision Processes (MDPs). It computes the maximal n-step payoff by iterating n times a recurrence equation which is naturally associated to the MDP. At the same time, value iteration provides a policy for the MDP that is optimal on a given finite horizon n. In this paper, we settle the computational complexity of value iteration. We show that, given a horizon n in binary and an MDP, computing an optimal policy is EXPTIME-complete, thus resolving an open problem that goes back to the seminal 1987 paper on the complexity of MDPs by Papadimitriou and Tsitsiklis. To obtain this main result, we develop several stepping stones that yield results of an independent interest. For instance, we show that it is EXPTIME-complete to compute the n-fold iteration (with n in binary) of a function given by a straight-line program over the integers with max and + as operators. We also provide new complexity results for the bounded halting problem in linear-update counter machines.
Links
GA19-15134Y, interní kód MUName: Verifikace a analýza pravděpodobnostních programů
Investor: Czech Science Foundation
GJ19-15134Y, research and development projectName: Verifikace a analýza pravděpodobnostních programů
PrintDisplayed: 24/4/2024 01:04