Matthia Sabatelli is an Assistant Professor in Reinforcement Learning at the University of Groningen with a decade of experience bridging research and teaching in machine learning. He holds a PhD from the University of Liège and an MSc in Artificial Intelligence from Groningen, and supervises students across theoretical and applied RL topics. His hands-on work includes updating deep learning course materials and practical GAN tutorials in PyTorch, reflecting a commitment to reproducible, educational code. Based in Groningen, he combines academic rigour with practical engineering, often surfacing research through course development and publicly shared notebooks. Colleagues and students know him for making complex RL concepts accessible and for keeping a lively, if sometimes self-described “not frequently updated,” personal research page.
11 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Department of Electrical Engineering and Computer Science, Doctor of Philosophy - PhD, Department of Electrical Engineering and Computer Science at University of Liège
Master of Science (MSc), Artificial Intelligence, Master of Science (MSc), Artificial Intelligence at University of Groningen
Undergraduate Degree in Interfaces and Communication Technology, Undergraduate Degree in Interfaces and Communication Technology at Università degli Studi di Trento
Contributions summary:Matthia's commits primarily involve modifications to a GAN (Generative Adversarial Network) tutorial, specifically within a Jupyter Notebook environment. They removed a sequential instance, updated the GAN lecture, and added code for tutorial 01, including tensor manipulations. They focused on the architecture and training loop for the GAN and the notebook content of a tutorial about tensors and operations within the PyTorch framework. Their work demonstrates hands-on application of deep learning concepts.
Official implementation of the paper "Approximating two value functions instead of one: towards characterizing a new family of Deep Reinforcement Learning Algorithms": https://arxiv.org/abs/1909.01779 To appear at the next NeurIPS2019 DRL-Workshop
Contributions:53 commits, 15 pushes, 1 comment in 1 year 11 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.