|
Teoriya Veroyatnostei i ee Primeneniya, 1978, Volume 23, Issue 2, Pages 313–330
(Mi tvp3039)
|
|
|
|
This article is cited in 10 scientific papers (total in 10 papers)
The existence of a stationary $\varepsilon$-optimal policy for a finite Markov chain
E. A. Faĭnberg Moscow State University of Railway Communications
Abstract:
The existence of a stationary average reward $\varepsilon$-optimal policy is proved for discrete time Markov decision chains with finitely many states, compact sets of actions, continuous transition functions and upper semicontinuous reward functions.
Received: 02.03.1976
Citation:
E. A. Faǐnberg, “The existence of a stationary $\varepsilon$-optimal policy for a finite Markov chain”, Teor. Veroyatnost. i Primenen., 23:2 (1978), 313–330; Theory Probab. Appl., 23:2 (1979), 297–313
Linking options:
https://www.mathnet.ru/eng/tvp3039 https://www.mathnet.ru/eng/tvp/v23/i2/p313
|
Statistics & downloads: |
Abstract page: | 161 | Full-text PDF : | 85 |
|