Hierarchical World Models as Visual Whole-Body Humanoid Controllers
Nicklas Hansen, Jyothir S V, Vlad Sobal, Yann LeCun, Xiaolong Wang, Hao Su
Abstract
Whole-body control for humanoids is challenging due to the high-dimensional nature of the problem, coupled with the inherent instability of a bipedal morphology. Learning from visual observations further exacerbates this difficulty. In this work, we explore highly data-driven approaches to visual whole-body humanoid control based on reinforcement learning, without any simplifying assumptions, reward design, or skill primitives. Specifically, we propose a hierarchical world model in which a high-level agent generates commands based on visual observations for a low-level agent to execute, both of which are trained with rewards. Our approach produces highly performant control policies in 8 tasks with a simulated 56-DoF humanoid, while synthesizing motions that are broadly preferred by humans. Code and videos: https://www.nicklashansen.com/rlpuppeteer
BibTeX
@inproceedings{
hansen2025hierarchical,
title={Hierarchical World Models as Visual Whole-Body Humanoid Controllers},
author={Nicklas Hansen and Jyothir S V and Vlad Sobal and Yann LeCun and Xiaolong Wang and Hao Su},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=7wuJMvK639}
}