带资源约束的上下文老虎机
机器学习
2015-08-03 v6 数据结构与算法
计算机科学与博弈论
摘要
我们研究了带有资源辅助约束的上下文老虎机，这在现实世界应用中很常见，例如选择广告或物品的动态定价。我们设计了首个解决这些问题的算法，该算法能够处理除时间之外的受约束资源，并改进了对非上下文情形的平凡归约。我们为上下文老虎机（任意策略集，例如 Dudik 等 (UAI'11)）和带资源约束的老虎机（带背包的老虎机，Badanidiyuru 等 (FOCS'13)）考虑了非常一般的设定，并证明了具有近最优统计性质的遗憾界保证。
引用
@article{arxiv.1402.6779,
title = {Resourceful Contextual Bandits},
author = {Ashwinkumar Badanidiyuru and John Langford and Aleksandrs Slivkins},
journal= {arXiv preprint arXiv:1402.6779},
year = {2015}
}
备注
This is the full version of a paper in COLT 2014. Version history: (v2) Added some details to one of the proofs, (v3) a big revision following comments from COLT reviewers (but no new results), (v4) edits in related work, minor edits elsewhere. (v6) A correction for Theorem 3, corollary for contextual dynamic pricing with discretization; updated follow-up work & open questions