CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning

no code implementations • 27 Mar 2024 • Elliot Chane-Sane, Pierre-Alexandre Leziart, Thomas Flayols, Olivier Stasse, Philippe Souères, Nicolas Mansard

In this work, we advocate for integrating constraints into robot learning and present Constraints as Terminations (CaT), a novel constrained RL algorithm.

reinforcement-learning Reinforcement Learning (RL)

Torque Controlled Locomotion of a Biped Robot with Link Flexibility

no code implementations • 27 Oct 2022 • Nahuel A Villa, Pierre Fernbach, Maximilien Naveau, Guilhem Saurel, Ewen Dantec, Nicolas Mansard, Olivier Stasse

The stabilizer and motion generator are designed together to ensure feasibility under the assumption of bounded errors.