Research Explorer

Your browser does not support JavaScript or JavaScript is not enabled. Without JavaScript some functions of this webapplication may be disabled or cause error messages. To enable JavaScript, please consult the manual of your browser or contact your system administrator.

Researcher

Pietro Mazzaglia

Publications & Research Data

Awards & Distinctions

25 Results

2025

FOCUS : object-centric world models for robotic manipulation

Stefano FerraroPietro MazzagliaTim VerbelenBart Dhoedt

A1 Journal Article in FRONTIERS IN NEUROROBOTICS

Maximum causal entropy inverse constrained reinforcement learning

Mattijs BaertPietro MazzagliaSam LerouxPieter Simoens

A1 Journal Article in MACHINE LEARNING

Representing positional information in generative world models for object manipulation

Stefano FerraroPietro MazzagliaTim VerbelenBart DhoedtSai Rajeswar

2024

Efficient learning strategies for embodied intelligence

Pietro MazzagliaBart DhoedtTim Verbelen

GenRL : multimodal-foundation world models for generalization in embodied agents

Pietro MazzagliaTim VerbelenBart DhoedtA. CourvilleS. Rajeswar

Information-driven affordance discovery for efficient robotic manipulation

Pietro MazzagliaT. CohenD. Dijkman

Multimodal foundation world models for generalist embodied agents

Pietro MazzagliaTim VerbelenBart DhoedtA. CourvilleS. Rajeswar

Object-centric scene representations using active inference

Toon Van de MaeleTim VerbelenPietro MazzagliaStefano FerraroBart Dhoedt

A1 Journal Article in NEURAL COMPUTATION

Redundancy-aware action spaces for robot learning

Pietro MazzagliaNicholas BackshallXiao MaStephen James

A1 Journal Article in IEEE ROBOTICS AND AUTOMATION LETTERS

Representing positional information in generative world models for object manipulation

Stefano FerraroPietro MazzagliaTim VerbelenBart DhoedtS. Rajeswar

2023

Choreographer : learning and adapting skills in imagination

Pietro MazzagliaTim VerbelenBart DhoedtLacoste A.Rajeswar S.

Disentangling shape and pose for object-centric deep active inference models

Stefano FerraroToon Van de MaelePietro MazzagliaTim VerbelenBart Dhoedt

FOCUS : object-centric world models for robotics manipulation

Stefano FerraroPietro MazzagliaTim VerbelenBart Dhoedt

Home run : finding your way home by imagining trajectories

Daria de TinguyPietro MazzagliaTim VerbelenBart Dhoedt

Learning to navigate from scratch using world models and curiosity : the good, the bad, and the ugly

Daria de TinguySven RemmeryPietro MazzagliaTim VerbelenBart Dhoedt

Mastering the unsupervised reinforcement learning benchmark from Pixels

S. RajeswarPietro MazzagliaTim VerbelenA. PicheBart DhoedtA. CourvilleA. Lacoste

Uncertainty-driven affordance discovery for efficient robotics manipulation

Pietro MazzagliaT. CohenD. Dijkman

2022

Chunking space and time with information geometry

Tim VerbelenDaria de TinguyPietro MazzagliaOzan CatalAdam Safron

Computational optimization of image-based reinforcement learning for robotics

Stefano FerraroToon Van de MaelePietro MazzagliaTim VerbelenBart Dhoedt

A1 Journal Article in SENSORS

Curiosity-driven exploration via latent Bayesian surprise

Pietro MazzagliaOzan CatalTim VerbelenBart Dhoedt

The free energy principle for perception and action : a deep learning perspective

Pietro MazzagliaTim VerbelenOzan CatalBart Dhoedt

A1 Journal Article in ENTROPY

Unsupervised model-based pre-training for data-efficient reinforcement learning from pixels

Sai RajeswarPietro MazzagliaTim VerbelenAlexandre PichéBart DhoedtAaron CourvilleAlexandre Lacoste

2021

A learning gap between neuroscience and reinforcement learning

Samuel WauthierPietro MazzagliaOzan CatalCedric De BoomTim VerbelenBart Dhoedt

Contrastive active inference

Pietro MazzagliaTim VerbelenBart Dhoedt

Self-supervised exploration via latent Bayesian surprise

Pietro MazzagliaOzan CatalTim VerbelenBart Dhoedt