Romain Deffayet — accepted AI-conference papers

2025

Disentangled Object-Centric Image Representation for Robotic Manipulation

David Emukpere, Romain Deffayet, Bingbing Wu, Romain Brégier, Michael Niemaz, Jean-Luc Meunier +3

IROS 2025

Learning robotic manipulation skills from vision is a promising approach for developing robotics applications that can generalize broadly to real-world scenarios. As such, many approaches to enable this vision have been explored with fruitful results. Particularly, object-centric representation meth

Cited by 2 Source ↗Scholar ↗

2025

Distributional Reinforcement Learning with Dual Expectile-Quantile Regression

Sami Jullien, Romain Deffayet, Jean-Michel Renders, Paul Groth, Maarten de Rijke

UAI 2025

Distributional reinforcement learning (RL) has proven useful in multiple benchmarks as it enables approximating the full distribution of returns and extracts a rich feedback from environment samples. The commonly used quantile regression approach to distributional RL – based on asymmetric $L_1$ loss

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗