Friday, May 05, 2023 02:00PM

Seminar:  ISYE+ML Joint Seminar by Prof. Andreas Krause from ETH Zurich CS

Towards Safe and Efficient Learning in the Physical World

Speaker:  Prof. Andreas Krause (https://las.inf.ethz.ch/krausea)

Friday, May 5

2:00 p.m. -3: 00 p.m.

ISYE Main Building 228

Abstract: Reinforcement learning has seen stunning empirical breakthroughs. At its heart is the challenge of trading exploration -- collecting data for learning better models -- and exploitation -- using the estimate to make decisions.  In simulated environments (e.g., games), exploration is primarily a computational concern.  In real-world settings, exploration is costly, and a potentially dangerous proposition, as it requires experimenting with actions that have unknown consequences.  In this talk, I will present our work towards enabling agents to efficiently and safely learn online, from interaction with the real world. I will first present safe Bayesian optimization, where we quantify uncertainty in the unknown objective and constraints, and, under some regularity conditions, can guarantee both safety and convergence to a natural notion of reachable optimum.  I will then consider model-based deep reinforcement learning, where we use the epistemic uncertainty in the world model to guide exploration while ensuring safety. Lastly I will discuss how we can meta-learning suitable probabilistic models from related tasks, and demonstrate our approaches on real-world applications, such as robotics tasks and tuning the SwissFEL Free Electron Laser.  

 

Bio: Andreas Krause is a Professor of Computer Science at ETH Zurich, where he leads the Learning & Adaptive Systems Group. He also serves as Academic Co-Director of the Swiss Data Science Center and Chair of the ETH AI Center, and co-founded the ETH spin-off LatticeFlow. Before that he was an Assistant Professor of Computer Science at Caltech. He received his Ph.D. in Computer Science from Carnegie Mellon University (2008) and his Diplom in Computer Science and Mathematics from the Technical University of Munich, Germany (2004). He is an ELLIS Fellow, a Microsoft Research Faculty Fellow and a Kavli Frontiers Fellow of the US National Academy of Sciences. He received the Rössler Prize, ERC Starting Investigator and ERC Consolidator grants, the German Pattern Recognition Award, an NSF CAREER award as well as the ETH Golden Owl teaching award. His research has received awards at several premier conferences and journals, including Test of Time awards at KDD 2019 and ICML 2020. Andreas Krause currently serves as Action Editor for the Journal of Machine Learning Research and General Chair for ICML 2023.