GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems

Understand

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.