UAI Spotlight Talk: BISCUIT - Causal Representation Learning from Binary Interactions

Abstract

In this spotlight talk, I gave a short overview of BISCUIT. BISCUIT is a method for learning the causal variables of an interative environment that is observed from high-dimensional inputs such as images. Using low-level action information, BISCUIT can be applied to many practical environments, such as for embodied AI. For more details, check out our paper and project page.