Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems.
Stefan Depeweg, José Miguel Hernández-Lobato, Finale Doshi‐Velez, Steffen Udluft · arXiv (Cornell University) · 2017
Bayesian neural networks (BNNs) with latent variables are probabilistic models which can automatically identify complex stochastic patterns in the data. We study in these models a decomposition of predictive uncertainty into its epistemic and aleatoric components. We show how such a decomposition arises naturally in a Bayesian active learning scenario and develop a new objective for reliable reinforcement learning (RL) with an epistemic and aleatoric risk element. Our experiments illustrate the usefulness of the resulting decomposition in active learning and reliable RL.