Neuroevolution: Artificial intelligence learns by adapting and evolving Genetic Literacy Project

Five new papers from Uber in San Francisco, California, demonstrate the power of so-called neuroevolution to play video games, solve mazes, and even make a simulated robot walk. Neuroevolution [is] a process of mutating and selecting the best neural networks. At Uber, such applications might include driving autonomous cars, setting customer prices, or routing vehicles to passengers. But the team, part of a broad research effort, had no specific uses in mind when doing the work. In part, they merely wanted to challenge what Jeff Clune, another Uber co-author, calls "the modern darlings" of machine learning: algorithms that use something called "gradient descent," The most novel Uber paper uses a completely different approach that tries many solutions at once.