Partially observed discrete-time risk-sensitive mean field games

buir.contributor.authorSaldi, Naci
buir.contributor.orcidSaldi, Naci|0000-0002-2677-7366
dc.citation.epage32en_US
dc.citation.spage1en_US
dc.contributor.authorSaldi, Naci
dc.contributor.authorBaşar, T.
dc.contributor.authorRaginsky, M.
dc.date.accessioned2023-02-17T06:47:29Z
dc.date.available2023-02-17T06:47:29Z
dc.date.issued2022-06-07
dc.departmentDepartment of Mathematicsen_US
dc.description.abstractIn this paper, we consider discrete-time partially observed mean-field games with the risk-sensitive optimality criterion. We introduce risk-sensitivity behavior for each agent via an exponential utility function. In the game model, each agent is weakly coupled with the rest of the population through its individual cost and state dynamics via the empirical distribution of states. We establish the mean-field equilibrium in the infinite-population limit using the technique of converting the underlying original partially observed stochastic control problem to a fully observed one on the belief space and the dynamic programming principle. Then, we show that the mean-field equilibrium policy, when adopted by each agent, forms an approximate Nash equilibrium for games with sufficiently many agents. We first consider finite-horizon cost function and then discuss extension of the result to infinite-horizon cost in the next-to-last section of the paper.en_US
dc.identifier.doi10.1007/s13235-022-00453-zen_US
dc.identifier.eissn2153-0793
dc.identifier.issn2153-0785
dc.identifier.urihttp://hdl.handle.net/11693/111472
dc.language.isoEnglishen_US
dc.publisherBirkhaeuser Scienceen_US
dc.relation.isversionofhttps://doi.org/10.1007/s13235-022-00453-zen_US
dc.source.titleDynamic Games and Applicationsen_US
dc.subjectMean field gamesen_US
dc.subjectPartial observationen_US
dc.subjectRisk sensitive costen_US
dc.titlePartially observed discrete-time risk-sensitive mean field gamesen_US
dc.typeArticleen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Partially observed discrete-time risk-sensitive mean field games.pdf
Size:
720.62 KB
Format:
Adobe Portable Document Format
Description:
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: