Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
Franki Nguimatsia Tiofack*, Théotime Le Hellard*, Fabian Schramm*, Nicolas Perrin-Gilbert, Justin Carpentier — arXiv, 2025
Education
- B.S. in Mechanical Engineering, Technical University Munich, 2018
- M.S. in Robotics, Cognition, Intelligence, Technical University Munich, 2020
- Ph.D in Robotics, Inria and École Normale Supérieure de Paris, 2025 (expected)
Work experience
- 01/2021 - 01/2022: Research Engineer, Wandercraft, Paris
- Dynamic walking team (R&D)
- Reinforcement learning for self-balanced exoskeleton, leading to a patent application (US20250162141A1, 2025)
- 01/2022 - 01/2023: Research Engineer, Inria, Paris
Publications
First-order Sobolev Reinforcement Learning
Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier — Workshop on Differentiable Systems and Scientific Machine Learning, EurIPS 2025, 2025
Reference-Free Sampling-Based Model Predictive Control
Fabian Schramm, Pierre Fabre, Nicolas Perrin-Gilbert, Justin Carpentier — arXiv, 2025
KernelSOS for Global Sampling-Based Optimal Control and Estimation via Semidefinite Programming
Antoine Groudiev, Fabian Schramm, Éloïse Berthier, Justin Carpentier, Frederike Dümbgen — arXiv, 2025
PROXQP: an Efficient and Versatile Quadratic Programming Solver for Real-Time Robotics Applications and Beyond
Antoine Bambade, Fabian Schramm, Sarah El Kazdadi, Stéphane Caron, Adrien Taylor, Justin Carpentier — IEEE Transactions on Robotics, 2025
End-to-End and Highly-Efficient Differentiable Simulation for Robotics
Quentin Le Lidec, Louis Montaut, Yann de Mont-Marin, Fabian Schramm, Justin Carpentier — arXiv, 2024
Leveraging Randomized Smoothing for Optimal Control of Nonsmooth Dynamical Systems
Quentin Le Lidec, Fabian Schramm, Louis Montaut, Cordelia Schmid, Ivan Laptev, Justin Carpentier — Nonlinear Analysis: Hybrid Systems, International Federation of Automatic Control (IFAC) journal, 2024
Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning
Antoine Bambade, Fabian Schramm, Adrien Taylor, Justin Carpentier — Twelfth International Conference on Learning Representations (ICLR), 2023
Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante
Alexis Duburcq, Fabian Schramm, Guilhem Boéris, Nicolas Bredeche, Yann Chevaleyre — IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022