arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1402.6779cs.LGcs.DScs.GT
收藏

足智多谋的上下文强盗

Resourceful Contextual Bandits

Google Research(谷歌研究院);Microsoft Research(微软研究院)

Ashwinkumar Badanidiyuru, John Langford, Aleksandrs Slivkins

摘要:

我们研究的上下文土匪与资源的辅助约束,这是常见的在现实世界中的应用,如选择广告或动态定价的项目。我们设计的第一个算法来解决这些问题,处理时间以外的资源约束,并提高了一个平凡的减少非上下文的情况下。我们考虑非常一般的背景土匪(任意的政策集,例如Dudik等人。(UAI'11))和土匪与资源限制(土匪背包,Badanidiyuru等人。(FOCS'13)),并证明了一个遗憾的保证与接近最优的统计特性。

英文摘要:

We study contextual bandits with ancillary constraints on resources, which are common in real-world applications such as choosing ads or dynamic pricing of items. We design the first algorithm for solving these problems that handles constrained resources other than time, and improves over a trivial reduction to the non-contextual case. We consider very general settings for both contextual bandits (arbitrary policy sets, e.g. Dudik et al. (UAI'11)) and bandits with resource constraints (bandits with knapsacks, Badanidiyuru et al. (FOCS'13)), and prove a regret guarantee with near-optimal statistical properties.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑