MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
Styleloco: Generative adversarial distillation for natural humanoid robot locomotion
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2verdicts
UNVERDICTED 2representative citing papers
Reinforcement learning with a constellation-based reward enables direct, efficient humanoid locomotion to short-range SE(2) targets, outperforming velocity-tracking baselines in simulation and transferring to hardware.
citing papers explorer
-
MuGen: Multi-Skill Generative Locomotion Controller for Humanoid Robots
MuGen learns a generative latent representation of multi-skill humanoid locomotion from heterogeneous human data using VQ-VAEs and RL, then distills a deployable policy that tracks unseen motions and reuses the latent space.
-
No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets
Reinforcement learning with a constellation-based reward enables direct, efficient humanoid locomotion to short-range SE(2) targets, outperforming velocity-tracking baselines in simulation and transferring to hardware.