随机多臂老虎机算法组合上置信界.pdfVIP

  • 0
  • 0
  • 约12.17万字
  • 约 37页
  • 2026-07-07 发布于上海
  • 举报

UpperConfidenceBoundsforCombiningStochasticBandits

AshokCutkoskyAbhimanyuDasManishPurohit

BostonUniversityGoogleResearchGoogleResearch

Boston,MAMountainView,CAMountainView,CA

ashok@abhidas@mpurohit@

0

2

0

2Abstract

c

eWeprovideasimplemethodtocombinestochasticbanditalgorithms.Ourapproachisbased

Dona“meta-UCB”procedurethattreatsea

文档评论(0)

1亿VIP精品文档

相关文档