5 years ago

Multi-Armed Bandits on Unit Interval Graphs.

Sattar Vakili, Xiao Xu, Qing Zhao, Ananthram Swami

An online learning problem with side information on the similarity and dissimilarity across different actions is considered. The problem is formulated as a stochastic multi-armed bandit problem with a graph-structured learning space. Each node in the graph represents an arm in the bandit problem and an edge between two nodes represents closeness in their mean rewards. It is shown that the resulting graph is a unit interval graph. A hierarchical learning policy is developed that offers sublinear scaling of regret with the size of the learning space by fully exploiting the side information through an offline reduction of the learning space and online aggregation of reward observations from similar arms. The order optimality of the proposed policy in terms of both the size of the learning space and the length of the time horizon is established through a matching lower bound on regret. It is further shown that when the mean rewards are bounded, complete learning with bounded regret over an infinite time horizon can be achieved. An extension to the case with only partial information on arm similarity and dissimilarity is also discussed.

Publisher URL: http://arxiv.org/abs/1802.04339

DOI: arXiv:1802.04339v1

You might also like
Discover & Discuss Important Research

Keeping up-to-date with research can feel impossible, with papers being published faster than you'll ever be able to read them. That's where Researcher comes in: we're simplifying discovery and making important discussions happen. With over 19,000 sources, including peer-reviewed journals, preprints, blogs, universities, podcasts and Live events across 10 research areas, you'll never miss what's important to you. It's like social media, but better. Oh, and we should mention - it's free.

  • Download from Google Play
  • Download from App Store
  • Download from AppInChina

Researcher displays publicly available abstracts and doesn’t host any full article content. If the content is open access, we will direct clicks from the abstracts to the publisher website and display the PDF copy on our platform. Clicks to view the full text will be directed to the publisher website, where only users with subscriptions or access through their institution are able to view the full article.