SafePILCO: a software tool for safe and data-efficient policy synthesis
This work provides a tool for researchers and practitioners in verification, reinforcement learning, and control to perform safe policy search, but it is incremental as it builds on an existing algorithm.
The authors tackled the problem of safe and data-efficient policy synthesis in reinforcement learning by developing SafePILCO, a Python software tool that extends the PILCO algorithm to include safety features, resulting in a modular and accessible implementation for broader community use.
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.