NP-Hardness of checking the unichain condition in average cost MDPs
Author(s)
Tsitsiklis, John N.
DownloadTsitsiklis-2007-NP-Hardness of checking the unichain condition in average cost MDPs.pdf (144.4Kb)
MIT_AMENDMENT
MIT Amendment
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
The unichain condition requires that every policy in an MDP result in a single ergodic class, and guarantees that the optimal average cost is independent of the initial state. We show that checking whether the unichain condition fails to hold is an NP-complete problem. We conclude with a brief discussion of the merits of the more general weak accessibility condition.
Date issued
2006-08Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer ScienceJournal
Operations Research Letters
Publisher
Elsevier
Citation
Tsitsiklis, John N. “NP-Hardness of Checking the Unichain Condition in Average Cost MDPs.” Operations Research Letters 35.3 (2007): 319–323. Web. 12 Apr. 2012. © 2006 Elsevier B.V.
Version: Final published version
ISSN
0167-6377