SafePILCO: a software tool for safe and data-efficient policy synthesis
Kyriakos Polymenakos, Nikitas Rontsis, Alessandro Abate, Stephen Roberts · arXiv (Cornell University) · 2020
SafePILCO is a software tool for safe and data-efficient policy search with reinforcement learning. It extends the known PILCO algorithm, originally written in MATLAB, to support safe learning. We provide a Python implementation and leverage existing libraries that allow the codebase to remain short and modular, which is appropriate for wider use by the verification, reinforcement learning, and control communities.