Coarse-Grained Smoothness for Reinforcement Learning in Metric Spaces

Omer Gottesman, Kavosh Asadi, Cameron S. Allen, Samuel Lobel, George Konidaris, Michael L. Littman

Abstract: Principled decision-making in continuous state–action spaces is impossible without some assumptions. A common approach is to assume Lipschitz continuity of the Q-function. We show that, unfortunate...