Asymptotically Optimal Strategies For Combinatorial Semi-Bandits in Polynomial Time
2021-02-14Code Available0· sign in to hype
Thibaut Cuvelier, Richard Combes, Eric Gourdin
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/dourouc05/CombinatorialBandits.jlOfficialnone★ 8
Abstract
We consider combinatorial semi-bandits with uncorrelated Gaussian rewards. In this article, we propose the first method, to the best of our knowledge, that enables to compute the solution of the Graves-Lai optimization problem in polynomial time for many combinatorial structures of interest. In turn, this immediately yields the first known approach to implement asymptotically optimal algorithms in polynomial time for combinatorial semi-bandits.