OpenAI recently published a fun paper where they showed using evolution algorithms to train policy networks to perform on par with state of the art reinforcement deep learning. In this talk we’ll try to reimplement the main ideas in that paper using Neanderthal (blazing fast matrix and linear algebra computations) and Cortex (neural networks); make it massively distributed using Onyx; build a simulation environment using re-frame; and of course save our princess from no particular harm in our toy game example. Built my first computer out of Lego bricks and learned to program soon after. Secretly just want to be left alone to restore old airplanes in some shed, so I spent my time building tools and teaching computers how to make me obsolete. Worked on everything from telescopes to web apps to BI tools to analytics infrastructures; but most proud of making people fall in love with data.