- About
- Events
- Calendar
- Graduation Information
- Cornell Learning Machines Seminar
- Student Colloquium
- BOOM
- Fall 2024 Colloquium
- Conway-Walker Lecture Series
- Salton 2024 Lecture Series
- Seminars / Lectures
- Big Red Hacks
- Cornell University - High School Programming Contests 2024
- Game Design Initiative
- CSMore: The Rising Sophomore Summer Program in Computer Science
- Explore CS Research
- ACSU Research Night
- Cornell Junior Theorists' Workshop 2024
- People
- Courses
- Research
- Undergraduate
- M Eng
- MS
- PhD
- Admissions
- Current Students
- Computer Science Graduate Office Hours
- Advising Guide for Research Students
- Business Card Policy
- Cornell Tech
- Curricular Practical Training
- A & B Exam Scheduling Guidelines
- Fellowship Opportunities
- Field of Computer Science Ph.D. Student Handbook
- Graduate TA Handbook
- Field A Exam Summary Form
- Graduate School Forms
- Instructor / TA Application
- Ph.D. Requirements
- Ph.D. Student Financial Support
- Special Committee Selection
- Travel Funding Opportunities
- Travel Reimbursement Guide
- The Outside Minor Requirement
- Diversity and Inclusion
- Graduation Information
- CS Graduate Minor
- Outreach Opportunities
- Parental Accommodation Policy
- Special Masters
- Student Spotlights
- Contact PhD Office
From Sample-Efficiency to User-Driven AI Assessment: Learning Generalizable Knowledge for Reliable Sequential Decision Making (via Zoom)
Abstract: Can we enable autonomous agents to learn generalizable knowledge that improves planning performance across a range of unseen tasks? In this talk I will present recent advances on learning for a range of sequential decision-making problems, from generalizable planning and learning for long-horizon tasks in deterministic and stochastic environments to enabling end-users to assess the limits and capabilities of their AI systems, even as these systems adapt and learn. In the first part of the talk I will focus on neuro-symbolic abstractions for robot planning and our recent work on learning such abstractions from scratch. These methods facilitate generalizable learning that can be transferred to much larger problems and they outperform existing approaches on tasks that were not seen during training. In the second part of the talk, I will discuss research challenges and solution approaches for a new, emerging problem: while we expect AI systems to continually adapt and learn, the problem of enabling end-users to safely determine the limits and capabilities of their changing AI systems remains largely unaddressed. I will conclude with some of our recent results on user-driven assessment of adaptive black-box AI systems.
Bio: Siddharth Srivastava is an Assistant Professor of Computer Science in the School of Computing and Augmented Intelligence at Arizona State University. Prof. Srivastava was a Staff Scientist at the United Technologies Research Center in Berkeley. Prior to that, he was a postdoctoral researcher in the RUGS group at the University of California Berkeley. He received his PhD in Computer Science from the University of Massachusetts Amherst. His research interests include robotics and AI, with a focus on reasoning, planning, and acting under uncertainty. His work on integrated task and motion planning for household robotics has received coverage from international news media. He is a recipient of the NSF CAREER award, a Best Paper award at the International Conference on Automated Planning and Scheduling (ICAPS) and an Outstanding Dissertation award from the Department of Computer Science at UMass Amherst. He served as conference chair for ICAPS 2019 and currently serves as an Associate Editor for the Journal of AI Research.