Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 3 months ago.

Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems
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.
Decomposition of Uncertainty for Active Learning and Reliable Reinforcement Learning in Stochastic Systems
by Stefan Depeweg, José Miguel HernándezLobato, Finale DoshiVelez, Steffen Udluft
https://arxiv.org/pdf/1710.07283v1.pdf
You must be logged in to reply to this topic.