Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210343460> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4210343460 abstract "We consider optimal control of an unknown multi-agent linear quadratic (LQ) system where the dynamics and the cost are coupled across the agents through the mean-field (i.e., empirical mean) of the states and controls. Directly using single-agent LQ learning algorithms in such models results in regret which increases polynomially with the number of agents. We propose a new Thompson sampling based learning algorithm which exploits the structure of the system model and show that the expected Bayesian regret of our proposed algorithm for a system with agents of |M| different types at time horizon T is $widetilde {mathcal{O}}left({{{left| M right|}^{1.5}}sqrt T }right)$ irrespective of the total number of agents, where the $widetilde {mathcal{O}}$ notation hides logarithmic factors in T . We present detailed numerical experiments to illustrate the salient features of the proposed algorithm." @default.
- W4210343460 created "2022-02-08" @default.
- W4210343460 creator A5005770424 @default.
- W4210343460 creator A5014239528 @default.
- W4210343460 creator A5018463719 @default.
- W4210343460 creator A5040616226 @default.
- W4210343460 creator A5076978447 @default.
- W4210343460 date "2021-12-14" @default.
- W4210343460 modified "2023-10-18" @default.
- W4210343460 title "Thompson sampling for linear quadratic mean-field teams" @default.
- W4210343460 cites W1972484140 @default.
- W4210343460 cites W1981214223 @default.
- W4210343460 cites W1983321045 @default.
- W4210343460 cites W1997001104 @default.
- W4210343460 cites W2026964400 @default.
- W4210343460 cites W2038686546 @default.
- W4210343460 cites W2039467271 @default.
- W4210343460 cites W2073155476 @default.
- W4210343460 cites W2094826322 @default.
- W4210343460 cites W2097730910 @default.
- W4210343460 cites W2147873335 @default.
- W4210343460 cites W2162725061 @default.
- W4210343460 cites W2168405694 @default.
- W4210343460 cites W2292219073 @default.
- W4210343460 cites W2783297289 @default.
- W4210343460 cites W3015500735 @default.
- W4210343460 cites W3119037855 @default.
- W4210343460 cites W4297852499 @default.
- W4210343460 doi "https://doi.org/10.1109/cdc45484.2021.9683030" @default.
- W4210343460 hasPublicationYear "2021" @default.
- W4210343460 type Work @default.
- W4210343460 citedByCount "2" @default.
- W4210343460 countsByYear W42103434602022 @default.
- W4210343460 countsByYear W42103434602023 @default.
- W4210343460 crossrefType "proceedings-article" @default.
- W4210343460 hasAuthorship W4210343460A5005770424 @default.
- W4210343460 hasAuthorship W4210343460A5014239528 @default.
- W4210343460 hasAuthorship W4210343460A5018463719 @default.
- W4210343460 hasAuthorship W4210343460A5040616226 @default.
- W4210343460 hasAuthorship W4210343460A5076978447 @default.
- W4210343460 hasBestOaLocation W42103434602 @default.
- W4210343460 hasConcept C105795698 @default.
- W4210343460 hasConcept C106131492 @default.
- W4210343460 hasConcept C11413529 @default.
- W4210343460 hasConcept C118615104 @default.
- W4210343460 hasConcept C126255220 @default.
- W4210343460 hasConcept C129844170 @default.
- W4210343460 hasConcept C134306372 @default.
- W4210343460 hasConcept C140779682 @default.
- W4210343460 hasConcept C202444582 @default.
- W4210343460 hasConcept C2524010 @default.
- W4210343460 hasConcept C28826006 @default.
- W4210343460 hasConcept C31972630 @default.
- W4210343460 hasConcept C33923547 @default.
- W4210343460 hasConcept C39927690 @default.
- W4210343460 hasConcept C41008148 @default.
- W4210343460 hasConcept C50817715 @default.
- W4210343460 hasConcept C9652623 @default.
- W4210343460 hasConceptScore W4210343460C105795698 @default.
- W4210343460 hasConceptScore W4210343460C106131492 @default.
- W4210343460 hasConceptScore W4210343460C11413529 @default.
- W4210343460 hasConceptScore W4210343460C118615104 @default.
- W4210343460 hasConceptScore W4210343460C126255220 @default.
- W4210343460 hasConceptScore W4210343460C129844170 @default.
- W4210343460 hasConceptScore W4210343460C134306372 @default.
- W4210343460 hasConceptScore W4210343460C140779682 @default.
- W4210343460 hasConceptScore W4210343460C202444582 @default.
- W4210343460 hasConceptScore W4210343460C2524010 @default.
- W4210343460 hasConceptScore W4210343460C28826006 @default.
- W4210343460 hasConceptScore W4210343460C31972630 @default.
- W4210343460 hasConceptScore W4210343460C33923547 @default.
- W4210343460 hasConceptScore W4210343460C39927690 @default.
- W4210343460 hasConceptScore W4210343460C41008148 @default.
- W4210343460 hasConceptScore W4210343460C50817715 @default.
- W4210343460 hasConceptScore W4210343460C9652623 @default.
- W4210343460 hasLocation W42103434601 @default.
- W4210343460 hasLocation W42103434602 @default.
- W4210343460 hasOpenAccess W4210343460 @default.
- W4210343460 hasPrimaryLocation W42103434601 @default.
- W4210343460 hasRelatedWork W2018584428 @default.
- W4210343460 hasRelatedWork W2060032448 @default.
- W4210343460 hasRelatedWork W2089630933 @default.
- W4210343460 hasRelatedWork W2947263763 @default.
- W4210343460 hasRelatedWork W3036057128 @default.
- W4210343460 hasRelatedWork W3100063304 @default.
- W4210343460 hasRelatedWork W3141524051 @default.
- W4210343460 hasRelatedWork W4243612371 @default.
- W4210343460 hasRelatedWork W4287753704 @default.
- W4210343460 hasRelatedWork W844485786 @default.
- W4210343460 isParatext "false" @default.
- W4210343460 isRetracted "false" @default.
- W4210343460 workType "article" @default.