Viet-Anh on Software Logo

What is: Bayesian Reward Extrapolation?

SourceSafe Imitation Learning via Fast Bayesian Reward Inference from Preferences
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Bayesian Reward Extrapolation is a Bayesian reward learning algorithm that scales to high-dimensional imitation learning problems by pre-training a low-dimensional feature encoding via self-supervised tasks and then leveraging preferences over demonstrations to perform fast Bayesian inference.