ATTENTION: The software behind KU ScholarWorks is being upgraded to a new version. Starting July 15th, users will not be able to log in to the system, add items, nor make any changes until the new version is in place at the end of July. Searching for articles and opening files will continue to work while the system is being updated.
If you have any questions, please contact Marianne Reed at mreed@ku.edu .
Discretized Maximum Likelihood and Almost Optimal Adaptive Control of Ergodic Markov Models
dc.contributor.author | Duncan, Tyrone E. | |
dc.contributor.author | Pasik-Duncan, Bozenna | |
dc.contributor.author | Stettner, L. | |
dc.date.accessioned | 2015-03-12T16:53:23Z | |
dc.date.available | 2015-03-12T16:53:23Z | |
dc.date.issued | 1998-04-02 | |
dc.identifier.citation | Duncan, T. E., Pasik-Duncan, B., Stettner, L. "Discretized Maximum Likelihood and Almost Optimal Adaptive Control of Ergodic Markov Models." SIAM J. Control Optim., 36(2), 422–446. (25 pages). http://dx.doi.org/10.1137/S0363012996298369 | en_US |
dc.identifier.uri | http://hdl.handle.net/1808/17069 | |
dc.description | This is the published version, also available here: http://dx.doi.org/10.1137/S0363012996298369. | en_US |
dc.description.abstract | Three distinct controlled ergodic Markov models are considered here. The models are a discrete time controlled Markov process with complete observations, a controlled diffusion process with complete observations, and a discrete time controlled Markov process with partial observations. The partial observations for the third model have the special form of complete observations in a fixed recurrent set and noisy observations in its complement. For each of the models an almost self-optimizing adaptive control is given. These adaptive controls are constructed from a family of estimates that use a finite discretization of the parameter set and a finite family of almost optimal ergodic controls by a randomized certainty equivalence method. A continuity property of the information of a model for one parameter value with respect to another is used to establish this almost optimality property. | en_US |
dc.publisher | Society for Industrial and Applied Mathematics | en_US |
dc.subject | adaptive control | en_US |
dc.subject | ergodic control | en_US |
dc.subject | Markov processes | en_US |
dc.subject | controlled Markov processes | en_US |
dc.subject | almost optimal adaptive control | en_US |
dc.title | Discretized Maximum Likelihood and Almost Optimal Adaptive Control of Ergodic Markov Models | en_US |
dc.type | Article | |
kusw.kuauthor | Duncan, T. E. | |
kusw.kuauthor | Pasik-Duncan, Bozenna J. | |
kusw.kudepartment | Mathematics | en_US |
dc.identifier.doi | 10.1137/S0363012996298369 | |
kusw.oaversion | Scholarly/refereed, publisher version | |
kusw.oapolicy | This item does not meet KU Open Access policy criteria. | |
dc.rights.accessrights | openAccess |