PhD position
Together with Frans Oliehoek, we are looking for a motivated candidate to work on the topics of theoretical machine learning, specifically in the domain of sequential decision-making, which includes bandit problems and theoretical reinforcement learning. The primary objective of this project is to analyze and design learning algorithms and prove theorems on formal guarantees regarding their performance. You will need to apply advanced mathematical and statistical techniques to achieve this. The project is situated in the context of efficient online learning, focusing on scaling with model complexity and function approximation.
Are you interested in this vacancy? Apply here before July 7th.
About the environment:
TU Delft consistently ranks very high among institutions of higher education globally and has a very large and active academic community of approximately 30,000 people from all corners of the world. As a city, Delft is one of the most charming cities in the Netherlands, with close connections to Rotterdam and The Hague, and is within 1-hour reach of Amsterdam.