"In Conversation" Series
Lecturer:
Dr. Sarah Keren (Technion)
Title:
Encouraging Autonomous Agents to Behave Nicely
Abstract:
Autonomous AI agents are increasingly deployed in complex, uncertain environments where they must account for the presence of others while pursuing their own objectives. In many cases, they cannot succeed alone; they may need assistance from other agents to complete their tasks efficiently or even at all.
My recent work develops theoretical foundations for fostering cooperative behavior through the concept of Value of Assistance (VOA), a measure of the performance improvement enabled by assistive actions. A central challenge is teaching agents to reason about helpfulness: to recognize when help is required, when it is worthwhile to provide it, and how such actions align with their broader goals. I will demonstrate the benefits of VOA in multi-robot navigation and collaborative manipulation, and discuss extensions to stochastic and partially observable multi-agent settings, including ongoing applications in AI-enabled energy systems.
Short Bio:
Sarah Keren is a senior lecturer (assistant professor) at The Taub Faculty of Computer Science at the Technion - Israel Institute of Technology where she leads the Collaborative AI and Robotics (CLAIR) lab https://clair.cs.technion.ac.il. Before joining the Technion, Sarah was a postdoctoral fellow at Harvard University’s School of Engineering and Applied Sciences and Hebrew University of Jerusalem. She earned her PhD from the Technion.
Sarah’s research focuses on providing theoretical foundations for designing AI systems that are capable of effective collaboration with each other and with people. She has received several awards, including the ICAPS 2020 Best Dissertation Honorable Mention, the ICAPS 2014 Honorable Mention for Best Paper, and the Eric and Wendy Schmidt Postdoctoral Award for Women in Mathematical and Computing Sciences. Sarah’s work has been published in leading conferences and journals for AI and robotics, including IJCAI, AAAI, ICAPS, NeurIPS, AAMAS, JAIR, KR, IROS, and ICRA.
Location:
Eilat Hall, Feldman Building, Second Floor, Edmond Safra Campus.