Efficient model-based reinforcement learning for robot control via online optimization
The International Journal of Robotics Research · 30.07.2026
DOI: 10.1177/02783649261457560 ↗Kurz gefasst
Fachartikel in der Zeitschrift The International Journal of Robotics Research, online erschienen am 30.07.2026. Verfasst von Fang Nan und 5 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Gefördert von: HORIZON EUROPE Digital, Industry and Space, NCCR Automation.
Abstract (Originalsprache)
We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free policy optimization, our method builds a dynamics model from real-time interaction data and performs policy updates guided by the learned dynamics model. This efficient model-based reinforcement learning scheme significantly reduces the number of samples to train control policies, enabling direct training on real-world rollout data. This significantly reduces the influence of bias in the simulated data, and facilitates the search for high-performance control policies. We adopt online optimization analysis to derive sublinear regret bounds under stochastic online optimization assumptions, providing formal guarantees on performance improvement as more interaction data are collected. Experimental evaluations were performed on a hydraulic excavator arm and a soft robot arm, where the algorithm demonstrates strong sample efficiency compared to model-free reinforcement learning methods, reaching comparable performance within hours. Robust adaptation to shifting dynamics was also observed when the payload condition was randomized. Our approach paves the way toward efficient and reliable on-robot learning for a broad class of challenging control tasks.
Förderung
- HORIZON EUROPE Digital, Industry and Space
- NCCR Automation
Zitieren
APA
Nan, F., Ma, H., Guan, Q., Hughes, J., Muehlebach, M., & Hutter, M. (2026). Efficient model-based reinforcement learning for robot control via online optimization. The International Journal of Robotics Research. https://doi.org/10.1177/02783649261457560
Vancouver
Nan F, Ma H, Guan Q, Hughes J, Muehlebach M, Hutter M. Efficient model-based reinforcement learning for robot control via online optimization. The International Journal of Robotics Research. 2026. doi:10.1177/02783649261457560
BibTeX
@article{Nan2026,
author = {Nan, Fang and Ma, Hao and Guan, Qinghua and Hughes, Josie and Muehlebach, Michael and Hutter, Marco},
title = {Efficient model-based reinforcement learning for robot control via online optimization},
journal = {The International Journal of Robotics Research},
year = {2026},
doi = {10.1177/02783649261457560}
}
EUVIMED