Optimality of independently randomized symmetric policies for exchangeable stochastic teams with infinitely many decision makers

Simple item page
buir.contributor.authorSaldi, Naci
buir.contributor.orcidSaldi, Naci|0000-0002-2677-7366
dc.citation.epage32en_US
dc.citation.spage1en_US
dc.citation.volumeNumberVolume 0: Ahead of Printen_US
dc.contributor.authorSanjari, S.
dc.contributor.authorSaldi, Naci
dc.contributor.authorYüksel, S.
dc.date.accessioned2023-02-27T10:42:58Z
dc.date.available2023-02-27T10:42:58Z
dc.date.issued2022-08-24
dc.departmentDepartment of Mathematicsen_US
dc.descriptionWe study stochastic teams (known also as decentralized stochastic control problems or identical interest stochastic dynamic games) with large or countably infinite numbers of decision makers and characterize the existence and structural properties of (globally) optimal policies. We consider both static and dynamic nonconvex teams where the cost function and dynamics satisfy an exchangeability condition. To arrive at existence and structural results for optimal policies, we first introduce a topology on control policies, which involves various relaxations given the decentralized information structure. This is then utilized to arrive at a de Finetti–type representation theorem for exchangeable policies. This leads to a representation theorem for policies that admit an infinite exchangeability condition. For a general setup of stochastic team problems with N decision makers, under exchangeability of observations of decision makers and the cost function, we show that, without loss of global optimality, the search for optimal policies can be restricted to those that are N-exchangeable. Then, by extending N-exchangeable policies to infinitely exchangeable ones, establishing a convergence argument for the induced costs, and using the presented de Finetti–type theorem, we establish the existence of an optimal decentralized policy for static and dynamic teams with countably infinite numbers of decision makers, which turns out to be symmetric (i.e., identical) and randomized. In particular, unlike in prior work, convexity of the cost in policies is not assumed. Finally, we show the near optimality of symmetric independently randomized policies for finite N-decision-maker teams and thus establish approximation results for N-decision-maker weakly coupled stochastic teams.en_US
dc.description.provenanceSubmitted by Samet Emre (samet.emre@bilkent.edu.tr) on 2023-02-27T10:42:58Z No. of bitstreams: 1 Optimality _of _independently _randomized _symmetric _policies _for _exchangeable _stochastic _teams _with _infinitely _many _decision _makers.pdf: 981236 bytes, checksum: 318063c4c630e04d9cdd4abfb080d49d (MD5)en
dc.description.provenanceMade available in DSpace on 2023-02-27T10:42:58Z (GMT). No. of bitstreams: 1 Optimality _of _independently _randomized _symmetric _policies _for _exchangeable _stochastic _teams _with _infinitely _many _decision _makers.pdf: 981236 bytes, checksum: 318063c4c630e04d9cdd4abfb080d49d (MD5) Previous issue date: 2022-08-24en
dc.identifier.doi10.1287/moor.2022.1296en_US
dc.identifier.eissn1526-5471
dc.identifier.urihttp://hdl.handle.net/11693/111813
dc.language.isoEnglishen_US
dc.publisherInstitute for Operations Research and the Management Sciences (INFORMS)en_US
dc.relation.isversionofhttps://doi.org/10.1287/moor.2022.1296en_US
dc.source.titleMathematics of Operations Researchen_US
dc.subjectStochastic teamsen_US
dc.subjectMean-field theoryen_US
dc.subjectDecentralized stochastic controlen_US
dc.subjectExchangeable processesen_US
dc.titleOptimality of independently randomized symmetric policies for exchangeable stochastic teams with infinitely many decision makersen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Optimality _of _independently _randomized _symmetric _policies _for _exchangeable _stochastic _teams _with _infinitely _many _decision _makers.pdf
Size:
958.24 KB
Format:
Adobe Portable Document Format
Description:
Makale Dosyası
Download

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Scholarly Publications - Mathematics