profile picture


Hi, I am Pietro Mazzaglia and I am a PhD researcher in Artificial Intelligence at the University of Ghent, Belgium, supervised by Tim Verbelen and Bart Dhoedt.
The objective of my research is to build intelligent agents that discover and learn how to behave in the environment by interacting with it.

Personal background

  • I grew up in Catania, a sunny city next to a volcano in the east coast of Sicily, Italy.
  • During my bachelor, I lived and studied at the superior graduate institute Scuola Superiore di Catania, where I was a scholar while attending the BSc Computer Engineering course at the University of Catania.
  • For my master degree, I moved to Manchester, UK, where I studied Artificial Intelligence at The University of Manchester.

Research interests

My main research interests are:
  • Deep reinforcement learning
  • Unsupervised RL (exploration, skills)
  • World models
  • Robotics
  • Active inference
If you are interested in working together, feel free to contact me at my email: (click to show)

Research spotlight

Here's a selection of my research contributions.
For an exhaustive list, please check my Google Scholar profile.

FOCUS: Object-Centric World Models for Robotics Manipulation

Stefano Ferraro*, Pietro Mazzaglia*, Tim Verbelen, Bart Dhoert

Robot Representations workshop @ RSS 2023 (best paper)
GMPL workshop @ RSS 2023

Choreographer: Learning and Adapting Skills in Imagination

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Alexandre Lacoste, Sai Rajeswar

ICLR 2023 (top-25%, spotlight)
Offline RL workshop @ ICML 2022 (oral)
Deep RL workshop @ ICML 2022

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels

Sai Rajeswar*, Pietro Mazzaglia*, Tim Verbelen, Alexandre Piché, Bart Dhoedt, Aaron Courville, Alexandre Lacoste

ICML 2023 (oral)
DARL workshop @ ICML 2022

Curiosity-Driven Exploration via Latent Bayesian Surprise

Pietro Mazzaglia, Ozan Çatal, Tim Verbelen, Bart Dhoedt

AAAI 2022 (oral)
SSL-RL workshop @ ICLR 2021

Contrastive Active Inference

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt

NeurIPS 2021

The Free Energy Principle for Perception and Action: A Deep Learning Perspective

Pietro Mazzaglia, Tim Verbelen, Ozan Çatal, Bart Dhoedt

Entropy 2022