Timezone: »

 
Poster
Meta-Thompson Sampling
Branislav Kveton · Mikhail Konobeev · Manzil Zaheer · Chih-wei Hsu · Martin Mladenov · Craig Boutilier · Csaba Szepesvari

Thu Jul 22 09:00 PM -- 11:00 PM (PDT) @
in Poster Session 6 »

Efficient exploration in bandits is a fundamental online learning problem. We propose a variant of Thompson sampling that learns to explore better as it interacts with bandit instances drawn from an unknown prior. The algorithm meta-learns the prior and thus we call it MetaTS. We propose several efficient implementations of MetaTS and analyze it in Gaussian bandits. Our analysis shows the benefit of meta-learning and is of a broader interest, because we derive a novel prior-dependent Bayes regret bound for Thompson sampling. Our theory is complemented by empirical evaluation, which shows that MetaTS quickly adapts to the unknown prior.

Keywords: Bandits · Reinforcement Learning and Planning

Author Information

Branislav Kveton (Google Research)
Mikhail Konobeev (University of Alberta)
Manzil Zaheer (Google Research)
Chih-wei Hsu (Google Research)
Martin Mladenov (Google)
Craig Boutilier (Google)
Csaba Szepesvari (DeepMind/University of Alberta)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors