Technical - Partner Event
AI Seminar – Daniel Brown
When
Oct. 15, 2021 - Oct. 15, 2021
12:00 PM – 1:00 PM MST
Where
Online
Online
Presenter: Daniel Brown, UC Berkeley
Title: Efficient and Robust Learning of Human Intent
Abstract: I will discuss recent research towards autonomous systems that learn reward functions and policies from human demonstrations and preferences. One problem that arises when learning from human input is that there is often a large amount of uncertainty over the human’s true intent and the corresponding desired robot behavior. To address this problem, I will discuss research along three fronts: (1) how to enable a robot to maintain efficient and accurate representations of its uncertainty, (2) how a robot can use this representation of uncertainty to generate risk-averse solutions, and (3) how a robot can actively query for additional human feedback to reduce its uncertainty over the human’s intent and improve the robustness of its learned policy.
Bio: Daniel is a postdoc at UC Berkeley, advised by Anca Dragan and Ken Goldberg. His research interests include robot learning, reward inference, AI safety, and multi-agent systems. In 2021, Daniel was selected as a Robotics: Science and Systems Pioneer. He received his Ph.D. in computer science from the University of Texas at Austin, where he worked with Scott Niekum on safe imitation learning. Prior to starting his PhD, Daniel worked for the Air Force Research Lab's Information Directorate where he studied bio-inspired swarms and multi-agent planning.
The University of Alberta Artificial Intelligence (AI) Seminar is a weekly meeting where researchers (including students, developers, and professors) interested in AI can share their current research. Presenters include local speakers from the University of Alberta and industry as well as other institutions. The seminars discuss a wide range of topics related in any way to Artificial Intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems are of interest. Learn more at the AI Seminar website and by subscribing to the mailing list!
Looking to build AI capacity? Need a speaker at your event?
