May 31, 2026 · cs.LGJ/K move · Enter open · S save
Bernd Frauenknecht, Devdutt Subhasish, Artur Eisele, Friedrich Solowjow+1
Institute for Data Science in Mechanical Engineering, RWTH Aachen University, 52062 Aachen, Germany
Model-based reinforcement learning (MBRL) infers information about the environment from a learned dynamics model and bears the potential to address open problems such as data efficient and safe learning in robotics. However, inaccuracies of the learned dynamics model are typically exploited by the agent, substantially hampering the capabilities of MBRL methods. We present a framework for dealing with inaccuracies of probabilistic models through targeted handling of uncertainty that effectively mitigates model exploitation. We present recent successes in learning directly on hardware and safe exploration, and discuss future directions for uncertainty-aware MBRL.