Dynamic programming for ergodic control with partial observations

Borkar, V. S. (2003) Dynamic programming for ergodic control with partial observations Stochastic Processes and their Applications, 103 (2). pp. 293-310. ISSN 0304-4149

PDF - Publisher Version

Official URL: http://linkinghub.elsevier.com/retrieve/pii/S03044...

Related URL: http://dx.doi.org/10.1016/S0304-4149(02)00190-4


A dynamic programming principle is derived for a discrete time Markov control process taking values in a finite dimensional space, with ergodic cost and partial observations. This uses the embedding of the process into another for which an accessible atom exists and hence a coupling argument can be used. In turn, this is used for deriving a martingale dynamic programming principle for ergodic control of partially observed diffusion processes, by ‘lifting’ appropriate estimates from a discrete time problem associated with it to the continuous time problem.

Item Type:Article
Source:Copyright of this article belongs to Elsevier Science.
ID Code:5275
Deposited On:18 Oct 2010 07:49
Last Modified:16 May 2016 15:48

Repository Staff Only: item control page