Luisa Zintgraf

PhD Student
University of Oxford

Hi everyone! I'm Luisa, and am currently doing a PhD at the University of Oxford under the Microsoft Research Scholarship. My supervisors are Shimon Whiteson and Katja Hofmann, and my main research focus is Meta Reinforcement Learning.

Previously I worked at the University of Brussels under supervision of Diederik Roijers and Ann Nowé. My main focus there was user modelling and preference elicitation, in the context of multi-objective decision making.

I did my Bachelor degree in Mathematics at the University of Hamburg, and a Master degree in Artificial Intelligence at the University of Amsterdam. For my master thesis I worked with Taco Cohen and Max Welling on visualising how neural networks make decisions.


Lorem ipsum dolor sit amet, consectetur adipiscing elit. Cras lobortis mollis arcu, vel vulputate justo consectetur quis. Donec quis fringilla arcu lorem ipsum dolor sit amet nullam. Consequat adipiscing phasellus.

Donec cursus nunc ut rhoncus volutpat. Suspendisse dictum volutpat orci sit amet consequat. Duis fermentum urna et ligula lacinia faucibus efficitur non sapien. Nulla cursus arcu sapien. Nulla luctus tellus dapibus erat tincidunt feugiat. Suspendisse potenti lorem ipsum dolor. Magna sed risus bibendum, ullamcorper risus eget, accumsan odio. Ut ornare mi aliquet, ultrices velit vitae tempor augue fermentum tempus. Interested? Get in touch!

Selected Publications

VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning. Luisa Zintgraf, Kyriacos Shiarlis, Maximilian Igl, Sebastian Schulze, Yarin Gal, Katja Hofmann, Shimon Whiteson. ICLR 2020. | paper | code |

Fast Context Adaptation via Meta-Learning. Luisa Zintgraf, Kyriacos Shiarlis, Vitaly Kurin, Katja Hofmann, Shimon Whiteson. ICML 2019. | paper | code | blog |

Ordered Preference Elicitation Strategies for Supporting Multi-Objective Decision Making. Luisa Zintgraf, Diederik Roijers, Sjoerd Linders, Catholijn Jonker, Ann Nowé. AAMAS 2018. | paper | code |

Deep Variational Reinforcement Learning for POMDPs. Maximilian Igl, Luisa Zintgraf, Tuan Anh Le, Frank Wood, Shimon Whiteson. ICML 2018. | paper | code |

Interactive Thompson Sampling for Multi-Objective Multi-Armed Bandits. Diederik Roijers, Luisa Zintgraf, Ann Nowé. ADT 2017. | paper |

Interpretation of Microbiota-Based Diagnostics by Explaining Individual Classifier Decisions. Anat Eck, Luisa Zintgraf, Evelien de Groot, Tim de Meij, Taco Cohen, Paul Savelkoul, Max Welling, AE Budding. BMC bioinformatics 18. | paper |

Visualizing Deep Neural Network Decisions: Prediction Difference Analysis. Luisa Zintgraf, Taco Cohen, Tameem Adel, Max Welling. ICLR 2017. | paper | code |

For a full list, see my Google scholar profile.