Google's Deepmind AI unit releases new version of AlphaGo that learns on its own

Deepmind, the artificial intelligence research organization owned by Google, announced some stunning results Wednesday from research into the next generation of its AlphaGo system: the machines are getting smarter. AlphaGo Zero, the new version of the AlphaGo system that defeated the world's best Go players in competitions over the past few years, was able to teach itself how to play the ancient board game as well as its predecessors in a matter of days with no other input than the basic rules of the game, Deepmind said in a blog post Wednesday. Previous versions of AlphaGo built to compete against human masters of the game required hours and hours of training on Go gameplay, but AlphaGo Zero was able to teach itself to play using a technique called reinforcement learning. Reinforcement learning involves training a system to figure out the best reward outcome from a series of actions, unlike supervised learning, in which the system is taught which outcomes are desired and trained over and over to recognize the factors that lead to those outcomes. Deepmind set up a neural network that played games of Go against itself until it learned how to formulate a winning strategy for a game in which capturing as many stones as possible can be satisfying in early stages, but can lead to big problems as the game plays out.