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

BISCUIT learns causal variables from interactive environments

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.

Date
Aug 3, 2023 12:10 — 12:30
Location
Pittsburgh, USA