dc.contributor.author | Barry, Jennifer | |
dc.contributor.author | Barry, Daniel T. | |
dc.contributor.author | Aaronson, Scott | |
dc.date.accessioned | 2014-09-12T17:39:21Z | |
dc.date.available | 2014-09-12T17:39:21Z | |
dc.date.issued | 2014-09 | |
dc.date.submitted | 2014-06 | |
dc.identifier.issn | 1050-2947 | |
dc.identifier.issn | 1094-1622 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/89468 | |
dc.description.abstract | We present quantum observable Markov decision processes (QOMDPs), the quantum analogs of partially observable Markov decision processes (POMDPs). In a QOMDP, an agent is acting in a world where the state is represented as a quantum state and the agent can choose a superoperator to apply. This is similar to the POMDP belief state, which is a probability distribution over world states and evolves via a stochastic matrix. We show that the existence of a policy of at least a certain value has the same complexity for QOMDPs and POMDPs in the polynomial and infinite horizon cases. However, we also prove that the existence of a policy that can reach a goal state is decidable for goal POMDPs and undecidable for goal QOMDPs. | en_US |
dc.description.sponsorship | National Science Foundation (U.S.) (Grant 0844626) | en_US |
dc.description.sponsorship | National Science Foundation (U.S.) (Grant 1122374) | en_US |
dc.description.sponsorship | National Science Foundation (U.S.) (Waterman Award) | en_US |
dc.publisher | American Physical Society | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1103/PhysRevA.90.032311 | en_US |
dc.rights | 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. | en_US |
dc.source | American Physical Society | en_US |
dc.title | Quantum partially observable Markov decision processes | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Barry, Jennifer, Daniel T. Barry, and Scott Aaronson. "Quantum partially observable Markov decision processes." Phys. Rev. A 90, 032311 (September 2014). © 2014 American Physical Society | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science | en_US |
dc.contributor.mitauthor | Aaronson, Scott | en_US |
dc.relation.journal | Physical Review A | en_US |
dc.eprint.version | Final published version | en_US |
dc.type.uri | http://purl.org/eprint/type/JournalArticle | en_US |
eprint.status | http://purl.org/eprint/status/PeerReviewed | en_US |
dc.date.updated | 2014-09-09T22:00:24Z | |
dc.language.rfc3066 | en | |
dc.rights.holder | American Physical Society | |
dspace.orderedauthors | Barry, Jennifer; Barry, Daniel T.; Aaronson, Scott | en_US |
dc.identifier.orcid | https://orcid.org/0000-0003-1333-4045 | |
mit.license | PUBLISHER_POLICY | en_US |
mit.metadata.status | Complete | |