Efficient model-based reinforcement learning for robot control via online optimization
The International Journal of Robotics Research
Published online on July 31, 2026
Abstract
The International Journal of Robotics Research, Ahead of Print.
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 ...
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 ...