Asymptotically Optimal Information-Directed Sampling. Kirschner, J., Lattimore, T., Vernade, C., & Szepesvári, C. In pages 2777–2821.
Asymptotically Optimal Information-Directed Sampling [pdf]Paper  Asymptotically Optimal Information-Directed Sampling [link]Link  abstract   bibtex   
We introduce a simple and efficient algorithm for stochastic linear bandits with finitely many actions that is asymptotically optimal and (nearly) worst-case optimal in finite time. The approach is based on the frequentist information-directed sampling (IDS) framework, with a surrogate for the information gain that is informed by the optimization problem that defines the asymptotic lower bound. Our analysis sheds light on how IDS balances the trade-off between regret and information and uncovers a surprising connection between the recently proposed primal-dual methods and the IDS algorithm. We demonstrate empirically that IDS is competitive with UCB in finite-time, and can be significantly better in the asymptotic regime.

Downloads: 0