Timezone: »

 
Poster
Bootstrapping Upper Confidence Bound
Botao Hao · Yasin Abbasi Yadkori · Zheng Wen · Guang Cheng

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #38
in Algorithms -- Bandit Algorithms »

Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration inequalities, which thus lead to over-exploration. In this paper, we propose a non-parametric and data-dependent UCB algorithm based on the multiplier bootstrap. To improve its finite sample performance, we further incorporate second-order correction into the above construction. In theory, we derive both problem-dependent and problem-independent regret bounds for multi-armed bandits under a much weaker tail assumption than the standard sub-Gaussianity. Numerical results demonstrate significant regret reductions by our method, in comparison with several baselines in a range of multi-armed and linear bandit problems.

Keywords: Bandit Algorithms · Algorithms
[ Paper]  [ Poster] 

Author Information

Botao Hao (Purdue University)
Yasin Abbasi Yadkori (VinAI Research/ VinTech JSC.,)
Zheng Wen (DeepMind)
Guang Cheng (Purdue University)

More from the Same Authors