ELLIS PhD Award for former doctoral student Felix Berkenkamp

Felix Berkenkamp, a former doctoral student in the Learning & Adaptive Systems Group, has received the ELLIS PhD Award for his thesis titled "Safe Exploration in Reinforcement Learning: Theory and Applications in Robotics". His work pioneers provably safe reinforcement learning algorithms and demonstrates them on robotic platforms. His approaches use probabilistic models to cautiously learn about the system online, while eventually enabling increasingly performant behavior as supported by data. Felix Berkenkamp was advised by Prof. Andreas Krause from the Department of Computer Science at ETH Zurich and co-advised by Prof. Angela Schoellig from the University of Toronto.

The annual ELLIS PhD Award was created by the European Lab fo Learning & Intelligent Systems (ELLIS) to recognise and encourage outstanding doctoral theses in fields related to artificial intelligence and machine learning. One male and one female awardee are chosen each year.