profile picture

About

Hi, I am Pietro Mazzaglia and I am a Senior Machine Learning Researcher at Qualcomm Research Netherlands, in Amsterdam.
The long-term goal of my research is to build embodied AI 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.
  • I did my PhD at Ghent University, Belgium, supervised by Prof. Bart Dhoedt and Dr. Tim Verbelen. During my PhD, I also interned at Qualcomm Research (Amsterdam, Netherlands), Dyson Robot Learning Lab (London, UK) and ServiceNow Research (Montreal, Canada).

Research interests

My main research interests are:
  • Embodied AI
  • Robotics
  • World models
  • Deep reinforcement learning

Research spotlight

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

Multimodal foundation world models for generalist embodied agents

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Aaron Courville, Sai Rajeswar

MFM-EAI workshop @ ICML 2024

Information-driven Affordance Discovery for Efficient Robotic Manipulation

Pietro Mazzaglia, Taco Cohen, Daniel Dijkman

ICRA 2024
GMPL workshop @ RSS 2023

Redundancy-aware Action Spaces for Robot Learning

Pietro Mazzaglia,* Nicholas Backshall,* Xiao Ma, Stephen James

Robotics and Automation Letters (RA-L) 2024

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 ( best paper award )