#artificial intelligence
Oct 2025
Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Bandits
The results establish ensemble sampling as a provable and practical randomized exploration approach for nonlinear contextual bandits as well as introducing techniques that address challenges specific to nonlinear models.
Jia-Zheng Sun, Weixin Wang, Pan Xu
· arXiv.org · 2 citations
· ⚡1