Date: September 12, 2025
Speaker: David Fridovich-Keil, University of Texas
Title: Auto-Encoding Bayesian Inverse Games
Abstract: This talk will present our recent work on inverting noncooperative games. In these problems, we aim to identify hidden parameters of agents’ objective functions and/or constraints based upon observations of their actions. Existing approaches are limited to reconstructing point estimates of these hidden parameters; in this work, however, we develop a variational inference framework for estimating the full Bayesian posterior. We will see how a motion planner can then make use of this additional information to generate safer and more efficient trajectories in human-robot interactions.
Bio: David Fridovich-Keil is an assistant professor of aerospace engineering at the University of Texas at Austin. Fridovich-Keil's research investigates a wide variety of multi-agent strategic decision-making problems, and focuses on establishing game-theoretic models of these interactions, inverting those models to infer agents' intentions from data, and leveraging that information to guide future interactions. A key aim of Fridovich-Keil's recent work has been to integrate these capabilities with generative machine learning by leveraging fundamental connections with optimization theory and differentiable programming. Fridovich-Keil is the recipient of an NSF Graduate Research Fellowship and an NSF CAREER award.