Franki Nguimatsia Tiofack, Fabian Schramm, Théotime Le Hellard, Justin Carpentier
Published in International Conference on Machine Learning (ICML), 2026
We present SVL (Survival Value Learning), a probabilistic approach that reframes goal-conditioned reinforcement learning as a survival learning problem by modeling the time-to-goal as a probability distribution.
Fabian Schramm, Franki Nguimatsia Tiofack, Nicolas Perrin-Gilbert, Marc Toussaint, Justin Carpentier
Published in Robotics: Science and Systems (RSS), 2026
Sampling-based controllers, such as Model Predictive Path Integral (MPPI) methods, offer substantial flexibility but often suffer from high variance and low sample efficiency. To address these challenges, we introduce a hybrid variance-reduced MPPI framework that integrates a prior model into the sampling process.
Franki Nguimatsia Tiofack*, Théotime Le Hellard*, Fabian Schramm*, Nicolas Perrin-Gilbert, Justin Carpentier
* Equal contribution
Published in Fourteenth International Conference on Learning Representations (ICLR), 2026
We introduce Guided Flow Policy (GFP), which couples a multi-step flow-matching policy with a distilled one-step actor to focus on learning from high-value actions in offline reinforcement learning.
Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier
Published in Differentiable Systems and Scientific Machine Learning, EurIPS 2025, 2025
We propose a refinement of temporal-difference learning that enforces first-order Bellman consistency by training the value function to match both Bellman targets and their derivatives.
Fabian Schramm, Pierre Fabre, Nicolas Perrin-Gilbert, Justin Carpentier
Published in IEEE International Conference on Robotics and Automation (ICRA), 2025
We present a sampling-based model predictive control framework that enables emergent locomotion without relying on handcrafted gait patterns or predefined contact sequences.
Antoine Groudiev, Fabian Schramm, Éloïse Berthier, Justin Carpentier, Frederike Dümbgen
Published in American Control Conference (ACC), 2025
This paper applies the Kernel Sum of Squares framework for global sampling-based optimal control and estimation via semidefinite programming.
Antoine Bambade, Fabian Schramm, Sarah El Kazdadi, Stéphane Caron, Adrien Taylor, Justin Carpentier
Published in IEEE Transactions on Robotics, 2025
This paper presents ProxQP, a new and efficient QP solver for robotics and beyond.
Quentin Le Lidec, Louis Montaut, Yann de Mont-Marin, Fabian Schramm, Justin Carpentier
Published in arXiv, 2024
This paper introduces a unified and efficient method for computing analytical derivatives in robotics simulators.
Antoine Bambade, Fabian Schramm, Adrien Taylor, Justin Carpentier
Published in Twelfth International Conference on Learning Representations (ICLR), 2024
This paper presents primal-dual augmented Lagrangian techniques for computing derivatives of both feasible and infeasible QPs.
Quentin Le Lidec, Fabian Schramm, Louis Montaut, Cordelia Schmid, Ivan Laptev, Justin Carpentier
Published in Nonlinear Analysis: Hybrid Systems, International Federation of Automatic Control (IFAC) journal, 2024
This paper presents randomized smoothing to tackle non-smoothness issues commonly encountered in optimal control and provides key insights on the interplay between Reinforcement Learning and Optimal Control.
Alexis Duburcq, Fabian Schramm, Guilhem Boéris, Nicolas Bredeche, Yann Chevaleyre
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
This paper presents a reinforcement learning framework capable of learning robust standing push recovery for bipedal robots with a smooth out-of-the-box transfer to reality, requiring only instantaneous proprioceptive observations.