All existing approaches to uncertainty modeling can be expressed as ENNs, and any ENN can be identified with a Bayesian neural network. We propose a clear and simple metric for progress in ENNs: the KL-divergence with respect to a target distribution.

2021: Ian Osband, Zheng Wen, M. Asghari, Morteza Ibrahimi, Xiyuan Lu, Benjamin Van Roy

https://arxiv.org/pdf/2107.08924v1.pdf