A Simple and Optimal Policy Design with Safety Against Heavy-Tailed Risk for Stochastic Bandits: SE and UCB Have Regret and an Regret TailResearch Paper
Stochastic multi-armed bandit policies are judged almost always by their expected regret. In operations settings such as dynamic pricing, assortment testing or clinical allocation, a decision maker also cares about the probability of a bad outcome: a policy whose regret is small on average can still incur regret linear in the horizon with non-negligible…