Pascal van der Vaart

Delft University of Technology

pascal.jpg

I’m a PhD student in machine learning at the Sequential Decision Making group at the Delft University of Technology. My research is on reinforcement learning, where agents learn by interacting with their environment to maximize long-term rewards. In this area I focus on uncertainty quantification and efficient exploration, mainly through Bayesian methods. Other research interests include Bayesian neural networks, generative models and Monte Carlo samplers.

Outside of research I enjoy hiking, tinkering with microelectronics, 3D printing and specialty coffee.

news

Feb 05, 2025 Website is up!

selected publications

  1. ebo.jpg
    Epistemic Bellman Operators
    Pascal R. Vaart, Matthijs T.J. Spaan, and Neil Yorke-Smith
    In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025
    To appear
  2. bayesian_ensembles.jpg
    Bayesian Ensembles for Exploration in Deep Reinforcement Learning
    Pascal R. Vaart, Neil Yorke-Smith, and Matthijs T. J. Spaan
    In Proceedings of the 2024 International Conference on Autonomous Agents and MultiAgent Systems, Auckland, New Zealand, 2024