GoSafeOpt: Scalable safe exploration for global optimization of dynamical systems

Artificial Intelligence, vol. 320, pp. 103922

Abstract

Learning optimal control policies directly on physical systems is challenging. 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. This work proposes GoSafeOpt as the first provably safe and optimal algorithm that can safely discover globally optimal policies for systems with high-dimensional state space. We demonstrate the superiority of GoSafeOpt over competing model-free safe learning methods in simulation and hardware experiments on a robot arm.

Authors 6

1. Bhavya Sukhija corresponding

   ETH Zurich

   Affiliation as printed

   Department of Computer Science, ETH Zürich, Switzerland

2. Matteo Turchetta

   ETH Zurich

   Affiliation as printed

   Department of Computer Science, ETH Zürich, Switzerland

3. David Lindner

   ETH Zurich

   Affiliation as printed

   Department of Computer Science, ETH Zürich, Switzerland

4. Andreas Krause

   ETH Zurich

   Affiliation as printed

   Department of Computer Science, ETH Zürich, Switzerland

5. Sebastian Trimpe Aachen Institute for Data Science in Mechanical Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Germany

6. Dominik Baumann

   Uppsala University · Aalto University

   Affiliation as printed

   Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland

   Department of Information Technology, Uppsala University, Sweden