Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Human in the Loop Learning (HiLL) Workshop at NeurIPS 2022

Differentiable User Models

Alex Hämäläinen · Mustafa Mert Çelikok · Samuel Kaski


Abstract:

Probabilistic user modeling is essential for building collaborative AI systems within probabilistic frameworks. However, modern advanced user models, often designed as cognitive behavior simulators, are computationally prohibitive for interactive use in cooperative AI assistants. In this extended abstract, we address this problem by introducing widely-applicable differentiable surrogates for bypassing this computational bottleneck; the surrogates enable using modern behavioral models with online computational cost which is independent of their original computational cost. We show experimentally that modeling capabilities comparable to likelihood-free inference methods are achievable, with over eight orders of magnitude reduction in computational time. Finally, we demonstrate how AI-assistants can computationally feasibly use cognitive models in a previously studied menu-search task.

Chat is not available.