Optimality of independently randomized symmetric policies for exchangeable stochastic teams with infinitely many decision makers
buir.contributor.author | Saldi, Naci | |
buir.contributor.orcid | Saldi, Naci|0000-0002-2677-7366 | |
dc.citation.epage | 32 | en_US |
dc.citation.spage | 1 | en_US |
dc.citation.volumeNumber | Volume 0: Ahead of Print | en_US |
dc.contributor.author | Sanjari, S. | |
dc.contributor.author | Saldi, Naci | |
dc.contributor.author | YĆ¼ksel, S. | |
dc.date.accessioned | 2023-02-27T10:42:58Z | |
dc.date.available | 2023-02-27T10:42:58Z | |
dc.date.issued | 2022-08-24 | |
dc.department | Department of Mathematics | en_US |
dc.description | We 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 Finettiātype 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 Finettiātype 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.provenance | Submitted 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.provenance | Made 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: 2022-08-24 | en |
dc.identifier.doi | 10.1287/moor.2022.1296 | en_US |
dc.identifier.eissn | 1526-5471 | |
dc.identifier.uri | http://hdl.handle.net/11693/111813 | |
dc.language.iso | English | en_US |
dc.publisher | Institute for Operations Research and the Management Sciences (INFORMS) | en_US |
dc.relation.isversionof | https://doi.org/10.1287/moor.2022.1296 | en_US |
dc.source.title | Mathematics of Operations Research | en_US |
dc.subject | Stochastic teams | en_US |
dc.subject | Mean-field theory | en_US |
dc.subject | Decentralized stochastic control | en_US |
dc.subject | Exchangeable processes | en_US |
dc.title | Optimality of independently randomized symmetric policies for exchangeable stochastic teams with infinitely many decision makers | en_US |
dc.type | Article | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- 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
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.69 KB
- Format:
- Item-specific license agreed upon to submission
- Description: