Improved Learning Complexity in Combinatorial Pure Exploration Bandits

@InProceedings{pmlr-v51-gabillon16,
  title = 	 {Improved Learning Complexity in Combinatorial Pure Exploration Bandits},
  author = 	 {Gabillon, Victor and Lazaric, Alessandro and Ghavamzadeh, Mohammad and Ortner, Ronald and Bartlett, Peter},
  booktitle = 	 {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {1004--1012},
  year = 	 {2016},
  editor = 	 {Gretton, Arthur and Robert, Christian C.},
  volume = 	 {51},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Cadiz, Spain},
  month = 	 {09--11 May},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v51/gabillon16.pdf},
  url = 	 {https://proceedings.mlr.press/v51/gabillon16.html},
  abstract = 	 {We study the problem of combinatorial pure exploration in the stochastic multi-armed bandit problem. We first construct a new measure of complexity that provably characterizes the learning performance of the algorithms we propose for the fixed confidence and the fixed budget setting. We show that this complexity is never higher than the one in existing work and illustrate a number of configurations in which it can be significantly smaller. While in general this improvement comes at the cost of increased computational complexity, we provide a series of examples, including a planning problem, where this extra cost is not significant.}
}