arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.08714cs.LGcs.AIstat.ML
收藏

第一千零七十五章再探潜伏的盗贼

Latent Bandits Revisited

Google Research(谷歌研究院)

Joey Hong, Branislav Kveton, Manzil Zaheer, Yinlam Chow, Amr Ahmed, Craig Boutilier

摘要:

一个潜在的强盗问题是一个学习代理知道的手臂奖励分布的条件下,一个未知的离散的潜在状态。智能体的主要目标是识别潜在状态,之后它可以采取最佳行动。这种设置是在线和离线学习之间的自然中点-复杂的模型可以离线学习,代理在线识别潜在状态-在推荐系统中具有实际意义。在这项工作中,我们提出了一般的算法,这种设置的基础上,置信上限(UCB)和汤普森采样。我们的方法是上下文和模型的不确定性和错误的意识。我们提供了一个统一的理论分析,我们的算法,它有较低的遗憾比经典的强盗政策时,潜在状态的数量小于行动。一个全面的实证研究展示了我们的方法的优势。

英文摘要:

A latent bandit problem is one in which the learning agent knows the arm reward distributions conditioned on an unknown discrete latent state. The primary goal of the agent is to identify the latent state, after which it can act optimally. This setting is a natural midpoint between online and offline learning---complex models can be learned offline with the agent identifying latent state online---of practical relevance in, say, recommender systems. In this work, we propose general algorithms for this setting, based on both upper confidence bounds (UCBs) and Thompson sampling. Our methods are contextual and aware of model uncertainty and misspecification. We provide a unified theoretical analysis of our algorithms, which have lower regret than classic bandit policies when the number of latent states is smaller than actions. A comprehensive empirical study showcases the advantages of our approach.

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。

↑