|
Elliot Chane-Sane Postdoctoral Researcher in Robot Learning I am a postdoctoral researcher at LAAS-CNRS in the Gepetto team working on robot learning under the supervision of Nicolas Mansard. Previously, I completed my PhD in the Willow team of Inria Paris and École Normale Supérieure, advised by Ivan Laptev and Cordelia Schmid. I am interested in deep learning and robotics, with a particular focus on imitation and reinforcement learning for control. Prior to research, I received an engineering degree from École Polytechnique and a MASt (Part III) in Mathematical Statistics from the University of Cambridge. Email / Google Scholar / Linkedin / Github |
|
Research |
|
SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience
Elliot Chane-Sane*, Joseph Amigo*, Thomas Flayols, Ludovic Righetti, Nicolas Mansard CoRL, 2024 project page / video / arXiv / code End-to-end visual reinforcement learning for agile legged robot parkour |
|
CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning
Elliot Chane-Sane*, Pierre-Alexandre Leziart*, Thomas Flayols, Olivier Stasse, Philippe Souères, Nicolas Mansard IROS, 2024 project page / video / arXiv / code Simple and effective constrained reinforcement learning and its application to agile legged locomotion |
|
Learning Video-Conditioned Policies for Unseen Manipulation Tasks
Elliot Chane-Sane, Cordelia Schmid, Ivan Laptev ICRA, 2023 project page / arXiv Zero-shot human video demonstration to robot manipulation |
|
Goal-Conditioned Reinforcement Learning with Imagined Subgoals
Elliot Chane-Sane, Cordelia Schmid, Ivan Laptev ICML, 2021 project page / arXiv / code Hierarchical reinforcement learning to train non-hierarchical policies for long-horizon goal-reaching tasks |
|
Design and source code from Jon Barron's website. |