A Relative Value Iteration Algorithm for Non-degenerate Controlled Diffusions

Autor:	Arapostathis, Ari, Borkar, Vivek S.
Rok vydání:	2011
Předmět:	Mathematics - Optimization and Control
Zdroj:	SIAM J. Control Optim. 50 (2012), no. 4, 1886-1902
Druh dokumentu:	Working Paper
DOI:	10.1137/110850529
Popis:	The ergodic control problem for a non-degenerate controlled diffusion controlled through its drift is considered under a uniform stability condition that ensures the well-posedness of the associated Hamilton-Jacobi-Bellman (HJB) equation. A nonlinear parabolic evolution equation is then proposed as a continuous time continuous state space analog of White's `relative value iteration' algorithm for solving the ergodic dynamic programming equation for the finite state finite action case. Its convergence to the solution of the HJB equation is established using the theory of monotone dynamical systems and also, alternatively, by using the theory of reverse martingales. Comment: 17 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1110.1273 Zobrazit plný text záznamu View this record from Arxiv