regret

This paper introduces THV-UCB, an algorithm for multi-objective bandit problems with slate selection, and establishes gap-free and gap-dependent regret bounds for hypervolume regret.

This paper introduces a normal-fan geometry for finite-horizon adversarial MDPs with fixed transitions, developing a face-crossing price that separates consequential from harmless non-stationarity. It shows that dynamic regret decomposes into intrinsic priced face motion plus within-face selection error.