Skip to main content Skip to main navigation


Model-Based Uncertainty in Value Functions

Carlos E. Luis; Alessandro G. Bottero; Julia Vinogradska; Felix Berkenkamp; Jan Peters
In: Francisco J. R. Ruiz; Jennifer G. Dy; Jan-Willem van de Meent (Hrsg.). International Conference on Artificial Intelligence and Statistics. International Conference on Artificial Intelligence and Statistics (AISTATS), Pages 8029-8052, Proceedings of Machine Learning Research, Vol. 206, PMLR, 2023.


We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. In particular, we focus on characterizing the variance over values induced by a distribution over MDPs. Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation, but the over-approximation may result in inefficient exploration. We propose a new uncertainty Bellman equation whose solution converges to the true posterior variance over values and explicitly characterizes the gap in previous work. Moreover, our uncertainty quantification technique is easily integrated into common exploration strategies and scales naturally beyond the tabular setting by using standard deep reinforcement learning architectures. Experiments in difficult exploration tasks, both in tabular and continuous control settings, show that our sharper uncertainty estimates improve sample-efficiency.

Weitere Links