|
Avtomatika i Telemekhanika, 2011, Issue 5, Pages 127–138
(Mi at1708)
|
|
|
|
This article is cited in 11 scientific papers (total in 11 papers)
Stochastic Systems, Queuing Systems
Finding minimax strategy and minimax risk in a random environment (the two-armed bandit problem)
A. V. Kolnogorov Yaroslav-the-Wise State University, Novgorod, Russia
Abstract:
Minimax strategy and risk in a stationary random environment are found as Bayesian ones corresponding to the worst prior distribution. For environments with normally distributed incomes with unit variance and expectations that depend only on the alternative selected, this distribution can be chosen to be symmetric and asymptotically uniform. This lets one use numerical methods. The results can be used for systems with parallel data processing, in particular, for controlling environments with distributions other than normal.
Citation:
A. V. Kolnogorov, “Finding minimax strategy and minimax risk in a random environment (the two-armed bandit problem)”, Avtomat. i Telemekh., 2011, no. 5, 127–138; Autom. Remote Control, 72:5 (2011), 1017–1027
Linking options:
https://www.mathnet.ru/eng/at1708 https://www.mathnet.ru/eng/at/y2011/i5/p127
|
Statistics & downloads: |
Abstract page: | 479 | Full-text PDF : | 127 | References: | 79 | First page: | 12 |
|