Optimal plans for dynamic programming problems

Himmelberg, C. J. ; Parthasarathy, T. ; Van Vleck, F. S. (1976) Optimal plans for dynamic programming problems Mathematics of Operations Research, 1 (4). pp. 390-394. ISSN 0364-765X

Full text not available from this repository.

Official URL: http://mor.journal.informs.org/content/1/4/390.sho...

Related URL: http://dx.doi.org/10.1287/moor.1.4.390


It is proved that there exist stationary optimal plans for discounted dynamic programming problems, and that there exist semi-Markov ε-optimal plans for positive dynamic programming problems. The actions are required to be taken in a variable action set F(s), and the reward function r(s, a) is a Borel measurable function of (s, a) and an u.s.c. function of a. Our results are related to recent work by Furukawa, Maitra, and Schal. The key tool is a generalization of a selection theorem of Dubins and Savage.

Item Type:Article
Source:Copyright of this article belongs to Informs.
Keywords:Positive and Discounted Dynamic Programming; Measurable Selections; Optimal Reward; Optimal Strategy; Borel Sets
ID Code:90955
Deposited On:15 May 2012 09:55
Last Modified:15 May 2012 09:55

Repository Staff Only: item control page