2025
Pareto Optimal Risk-Agnostic Distributional Bandits with Heavy-Tail Rewards
NeurIPS 2025poster
This paper addresses the problem of multi-risk measure agnostic multi-armed bandits in heavy-tailed reward settings. We propose a framework that leverages novel deviation inequalities for the $1$-Wasserstein distance to construct confidence intervals for Lipschitz risk measures. The distributional…