---

About

I hold a BSc and MSc in Artificial Intelligence at the University of Groningen. During my undergraduate studies, I became captivated by reinforcement learning agents that learned superhuman capabilities in playing games, which sparked my interest in pursuing this direction of AI research. I developed a particular interest in model-based reinforcement learning algorithms, as I believe that incorporating a model of the world is essential for developing intelligent agents. During my Master’s, I developed multi-task and transfer learning techniques for agents making use of such world models, resulting in a paper published in Transactions on Machine Learning Research. I am now pursuing a Ph.D. at Queen Mary University of London under the guidance of Dr. Paulo Rauber.

Research Topic

My current research focuses on developing reinforcement learning algorithms that are both scalable and sample-efficient. In particular, the algorithms are based on principled model-based Bayesian algorithms, and I prioritize preserving their core principles in the scalable versions. This is exemplified in my first paper published at International Conference on Machine Learning (ICML), where I successfully scaled the Posterior Sampling for Reinforcement Learning algorithm while closely following its original formulation. This resulted in Posterior Sampling for Deep Reinforcement Learning, an algorithm competitive with other state-of-the-art algorithms in Atari games, labeled as a milestone in model-based reinforcement learning research by one of the conference reviewers.

---

GAIG Publications

2024

2023

• 2023 Posterior Sampling for Deep Reinforcement Learning
  Remo Sasso and Michelangelo Conserva and Paulo Rauber, in International Conference on Machine Learning, 2023.
  ICML'23
  
  

2022

2021