Open Problem: Model Selection for Contextual Bandits

Open Problem: Model Selection for Contextual Bandits
复制标题

开放问题:上下文强盗的模型选择

DOI:
--
复制
发表时间:
2020
期刊:
Annual Conference Computational Learning Theory
影响因子:
--
通讯作者:
Haipeng Luo
Haipeng Luo
中科院分区:
--
文献类型:
--
作者:
Dylan J. Foster;A. Krishnamurthy;Haipeng Luo

文献摘要

被引文献

相似文献

在统计学习中,模型选择算法允许学习者适应序列中最佳假设类的复杂性。我们询问上下文老虎机学习是否可以提供类似的保证。
In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees are possible for contextual bandit learning.