Odalric-Ambrym Maillard, Shie Mannor
In International Conference on Machine Learning, 2014.
| We consider a multi-armed bandit problem where the reward distributions are indexed by two sets –one for arms, one for type– and can be partitioned into a small number of clusters according to the type. First,we consider the setting where all reward distributions are known and all types have the same underlying cluster, the type’s identity is, however, unknown. Second, we study the case where types may come from different classes, which is significantly more challenging. Finally, we tackle the case where the reward distributions are completely unknown. In each setting, we introduce specific algorithms and derive non-trivial regret performance. Numerical experiments show that, in the most challenging agnostic case, the proposed algorithm achieves excellent performance in several difficult scenarios. |
You can dowload the Java code used to generate the experiments here.
| (coming soon) |
* The HAL open-access online archive system seeks to make research results available to the widest audience, independently of the major publisher, and cooperates with other large international archives like arXiv.