AISTATS 2015poster361 citations

Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits

Branislav Kveton, Zheng Wen, Azin Ashkan, Csaba Szepesvari

Abstract

A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to constraints, and then observes stochastic weights of these items and receives their sum as a payoff. In this paper, we close the problem of computationally and sample efficient learning in stochastic combinatorial semi-bandits. In particular, we analyze a UCB-like algorithm for solving the problem, which is known to be computationally efficient; and prove O(K L (1 / ∆) \log n) and O(\sqrtK L n \log n) upper bounds on its n-step regret, where L is the number of ground items, K is the maximum number of chosen items, and ∆is the gap between the expected returns of the optimal and best suboptimal solutions. The gap-dependent bound is tight up to a constant factor and the gap-free bound is tight up to a polylogarithmic factor.

BibTeX
@InProceedings{pmlr-v38-kveton15,
  title = 	 {{Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits}},
  author = 	 {Kveton, Branislav and Wen, Zheng and Ashkan, Azin and Szepesvari, Csaba},
  booktitle = 	 {Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics},
  pages = 	 {535--543},
  year = 	 {2015},
  editor = 	 {Lebanon, Guy and Vishwanathan, S. V. N.},
  volume = 	 {38},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {San Diego, California, USA},
  month = 	 {09--12 May},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v38/kveton15.pdf},
  url = 	 {https://proceedings.mlr.press/v38/kveton15.html},
  abstract = 	 {A stochastic combinatorial semi-bandit is an online learning problem where at each step a learning agent chooses a subset of ground items subject to constraints, and then observes stochastic weights of these items and receives their sum as a payoff. In this paper, we close the problem of computationally and sample efficient learning in stochastic combinatorial semi-bandits. In particular, we analyze a UCB-like algorithm for solving the problem, which is known to be computationally efficient; and prove O(K L (1 / ∆) \log n) and O(\sqrtK L n \log n) upper bounds on its n-step regret, where L is the number of ground items, K is the maximum number of chosen items, and ∆is the gap between the expected returns of the optimal and best suboptimal solutions. The gap-dependent bound is tight up to a constant factor and the gap-free bound is tight up to a polylogarithmic factor.}
}
Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits · AISTATS 2015