MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT

• Published in: Probability in the engineering and informational sciences Vol. 29; no. 1; pp. 51 - 76
• Main Authors: Cowan, Wesley, Katehakis, Michael N.
• Format: Journal Article
• Language: English
• Published: New York, USA Cambridge University Press 01.01.2015
• Subjects: Activation; Collection; Constants; Decisions; Depreciation; Discounts; Mathematical analysis; Mathematical models; Probability; Receiving; Stochasticity

Generally, the multi-armed has been studied under the setting that at each time step over an infinite horizon a controller chooses to activate a single process or bandit out of a finite collection of independent processes (statistical experiments, populations, etc.) for a single period, receiving a...