DeepMind has struck a critical new partnership with Unity Technologies, the game-development platform used by half the world's mobile games, including Temple Run and Hearthstone: Heroes of Warcraft, and it's one that could also help its nascent business. For now, it will take DeepMind's research on deep-reinforcement learning to the next level, says Danny Lange, vice president of AI at Unity, who spoke to Forbes from the sidelines of the O'Reilly AI conference in London on Wednesday. Deep-reinforcement learning is an approach to AI that trains an algorithm with positive and negative signals. Unity already has a freely available toolkit for training independent agents in a simulation (an approach to AI for training a neural network), but this partnership represents something more--a "deep collaboration between our teams," says Lange. "We are working with DeepMind to enable them to have [a virtual worlds] environment." "It opens the door for dealing with realistic and complex problems," he adds.