Universal Humanoid Motion Representations for Physics-Based Control

arXiv:2310.04582v2 Announce Type: replace
Abstract: We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. Due to the high dimensionality of humanoids and the inherent difficulties in reinforcement learning, prior methods have focused on learning skill embeddings for a narrow range of movement styles (e.g. locomotion, game characters) from specialized motion datasets. This limited scope hampers their applicability in complex tasks. We close this gap by significantly increasing the coverage of our …

abstract arxiv control cs.cv cs.gr cs.ro dimensionality embeddings humanoid humanoids narrow physics prior reinforcement reinforcement learning representation skills type universal