Best Arm Identification for Heuristic-Based Multi-Armed Bandits
碩士 === 國立交通大學 === 資訊科學與工程研究所 === 105 === This paper first presents a variant of the Multi-Armed Bandit (MAB) problem, called heuristic-based MAB (H-MAB) problem, where heuristics are available to help identify the best arm. We then propose a recommendation model for H-MAB. Based on H-MAB and the mod...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2016
|
Online Access: | http://ndltd.ncl.edu.tw/handle/50986727356455862790 |