This event has passed.

Spring 2025 GRASP SFI: Lillian Ratliff, University of Washington, “Fragile Foundations? Building Robustness into Reasoning with Algorithmic Agents”

Name: Spring 2025 GRASP SFI: Lillian Ratliff, University of Washington, “Fragile Foundations? Building Robustness into Reasoning with Algorithmic Agents”
Start: 2025-04-09T13:00:00-04:00
End: 2025-04-09T14:00:00-04:00
Location: Levine 307

April 9 at 1:00 PM - 2:00 PM

This will be a hybrid event with in-person attendance in Levine 307 and virtual attendance on Zoom.

ABSTRACT

As AI-enabled systems become integral to critical domains, their robustness is increasingly tested by dynamic environments, continual learning, and inferential uncertainty. Whether an AI proxy informs high-stakes medical decisions or an embodied agent relies on a foundation model to reason across modalities, today’s training and deployment methodologies remain inherently fragile. This fragility often stems from a reliance on stationarity assumptions, overly symmetric training paradigms, and a failure to account for other adapting agents—leading to systems that generalize poorly, misestimate uncertainty, and break down in interactive settings.

This talk presents recent theoretical contributions and algorithmic design principles for robust inference and influence when reasoning with algorithmic agents. In particular, it explores how tools from control and game theory—when integrated into machine learning, and vice versa—enable uncertainty adaptation and the synthesis of decision-making strategies for influencing algorithmic agents. Through motivating examples, the talk will illustrate how bridging these disciplines leads to more robust AI systems that can reason, adapt, and interact effectively in complex, non-stationary environments. The first part will focus on algorithms with non-asymptotic convergence guarantees in time-varying settings with a hierarchical game structure. The second part will address uncertainty quantification and adaptation in safety-critical, multi-agent, embodied AI systems. The talk will conclude with a discussion of open questions and future directions.

Lillian Ratliff

University of Washington

Lillian J. Ratliff is an Associate Professor in the Department of Electrical and Computer Engineering at the University of Washington. Ratliff also holds Adjunct Associate Professor positions in the Allen School of Computer Science and Engineering and the Department of Aeronautics and Astronautics at UW. Ratliff is also an Amazon Scholar within Amazon Robotics. Prior to joining UW, Ratliff obtained her PhD in EECS at UC Berkeley. Ratliff holds a MS and BS in Electrical Engineering as well as a BS in Mathematics. Ratliff’s research interests lie at the intersection of game theory and economics, optimization, machine learning, and control theory. Ratliff is the recipient of an NSF Graduate Research Fellowship (2009), NSF CISE Research Initiation Initiative award (2017), and an NSF CAREER award (2019), and the ONR Young Investigator award (2020). She was awarded the UW CoE Junior Faculty Award in 2021, and was also an invited speaker at the NAE China-America Frontiers of Engineering Symposium (2019). Ratliff currently holds the Dhanani Endowed Faculty Fellowship (2020).

Details

Date:: April 9
Time:: 1:00 PM - 2:00 PM
Event Category:: Seminar
Website:: https://www.grasp.upenn.edu/events/spring-2025-grasp-sfi-lillian-ratliff/

Organizer

: General Robotics, Automation, Sensing and Perception (GRASP) Lab
Email: grasplab@seas.upenn.edu
: View Organizer Website

Venue

: Levine 307
: 3330 Walnut Street
Philadelphia, PA 19104 United States + Google Map