GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems



Bhavya Sukhija, Matteo Turchetta, David Lindner, Andreas Krause, Sebastian Trimpe, Dominik Baumann

  Overview of the proposed method. Urheberrecht: © Bhavya Sukhija Illustrative example with disjoint safe regions in the policy space.


Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage. Most existing model-free learning methods that guarantee safety, i.e., no failures, during exploration are limited to local optima. A notable exception is the GoSafe algorithm, which, unfortunately, cannot handle high-dimensional systems and hence cannot be applied to most real-world dynamical systems. This work proposes GoSafeOpt as the first algorithm that can safely discover globally optimal policies for high-dimensional systems while giving safety and optimality guarantees. We demonstrate the superiority of GoSafeOpt over competing model-free safe learning methods on a robot arm that would be prohibitive for GoSafe.

Published in Artificial Intelligence.