A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions |
| |
Authors: | Kung-Yu Chen Chien-Tai Lin |
| |
Affiliation: | (1) Department of Mathematics, Tmkang University, 251 Tamsui, Taiwan |
| |
Abstract: | A bandit problem with infinitely many Bernoulli arms is considered. The parameters of Bernoulli arms are independent and identically distributed random variables from a generalized beta distributionG3B(a, b, λ) witha, b>0 and 0<λ<2. Under the generalized beta prior distributions, we first derive the asymptotic expected failure rates ofk-failure strategies, and then obtain a lower bound for the expected failure rate over all strategies investigated in Berry et al. (1997). The asymptotic expected failure rates for the other three strategies studied in Berry et al. (1997) are also included. Numerical estimations for a variety of generalized beta prior distributions are presented to illustrate the performances of these strategies. |
| |
Keywords: | Dynamic allocation of Bernoulli processes k-failure strategy m-run strategy N-learning strategy non-recallingm-run strategy sequential experimentation |
本文献已被 SpringerLink 等数据库收录! |