Summary
Keywords
Full Transcript
April 5, 2024 Andreas Krause of ETH Zurich How can we enable 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 Bayesian 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-learn flexible probabilistic models from related tasks and simulations, and demonstrate our approaches on real-world applications, such as robotics tasks and tuning the SwissFEL Free Electron Laser. About the speaker: https://inf.ethz.ch/people/person-detail.krause.html More about the course can be found here: https://stanfordasl.github.io/robotics_seminar/ View the entire AA289 Stanford Robotics and Autonomous Systems Seminar playlist: https://www.youtube.com/playlist?list=PLoROMvodv4rMeercb-kvGLUrOq4HR6BZD ► Check out the entire catalog of courses and programs available through Stanford Online: https://online.stanford.edu/explore
Continue this lesson in the app
Install CourseHive on Android or iOS to keep learning while you move.
