CS Colloquium: Siddharth Srivastava (Arizona State University) - Principles and Algorithms for Data-Efficient Assistive Sequential Decision Making

Speaker: Siddharth Srivastava, Arizona State University

Talk Title: Principles and Algorithms for Data-Efficient Assistive Sequential Decision Making

Series: Computer Science Colloquium

Abstract: Can we balance efficiency and reliability while designing assistive AI systems? What would such AI systems need to provide? In this talk I will present some of our recent work addressing these questions. In particular, I will show that a few fundamental principles of abstraction are surprisingly effective in designing efficient and reliable AI systems that can plan and act over multiple timesteps. Our results show that abstraction mechanisms are invaluable not only in improving the efficiency of sequential decision making, but also in developing AI systems that can explain their own behavior to non-experts, and in computing user-interpretable assessments of the limits and capabilities of Black-Box AI systems. I will also present some of our work on learning the requisite abstractions in a bottom-up fashion. Throughout the talk I will highlight the theoretical guarantees that our methods provide along with results from empirical evaluations featuring decision-support/digital AI systems and physical robots.

This lecture satisfies requirements for CSCI 591: Research Colloquium.

Join Zoom Meeting
URL

Meeting ID: 993 9548 2251

One tap mobile
+16699006833,,99395482251# US (San Jose)
+13462487799,,99395482251# US (Houston)

Dial by your location
+1 669 900 6833 US (San Jose)
+1 346 248 7799 US (Houston)
+1 253 215 8782 US (Tacoma)
+1 301 715 8592 US (Washington DC)
+1 312 626 6799 US (Chicago)
+1 646 876 9923 US (New York)


Host: Sven Koenig

Webcast: URL