资源分类
》 资源 》论文》From Bandits to Experts: A Tale of Domination and Independence

From Bandits to Experts: A Tale of Domination and Independence

2020-01-16 | |  61 |   39 |   0

Abstract

We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir [14]. Our main result is a characterization of regret in the directed observability model in terms of the dominating and independence numbers of the observability graph (which must be accessible before selecting an action). In the undirected case, we show that the learner can achieve optimal regret without even accessing the observability graph before selecting an action. Both results are shown using variants of the Exp3 algorithm operating on the observability graph in a time-ef?cient manner.

上一篇：Learning Stochastic Inverses

下一篇：Auditing: Active Learning with Outcome-Dependent Query Costs

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...