2 citations · 6 across the 9 of their papers we have counts for
4 papers · 1 filter
First Order Model-Based RL through Decoupled Backpropagation
Joseph Amigo, Rooholla Khorrambakht, Elliot Chane-Sane +2
There is growing interest in reinforcement learning (RL) methods that leverage the simulator's derivatives to improve learning efficiency. While early gradient-based approaches hav…
Constrained Reinforcement Learning for Unstable Point-Feet Bipedal Locomotion Applied to the Bolt Robot
Constant Roux, Elliot Chane-Sane, Ludovic De Matteïs +4
Bipedal locomotion is a key challenge in robotics, particularly for robots like Bolt, which have a point-foot design. This study explores the control of such underactuated robots u…
Reinforcement Learning from Wild Animal Videos
Elliot Chane-Sane, Constant Roux, Olivier Stasse +1
We propose to learn legged robot locomotion skills by watching thousands of wild animal videos from the internet, such as those featured in nature documentaries. Indeed, such video…
SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience
Elliot Chane-Sane, Joseph Amigo, Thomas Flayols +2
Parkour poses a significant challenge for legged robots, requiring navigation through complex environments with agility and precision based on limited sensory inputs. In this work,…