Greedy AI Agents Learn to Cooperate

In this example, three rovers must reach a target for it to be counted. Our system [right] can handle this challenging task, but others failed at it. Intel AI… Read more


Training an AI for the card game Dominion

I'm fascinated by stories in the news of how the world's best AIs for chess and Go were trained by playing against themselves. It seems like a wonderful tool for learning more about the strategy of a game, as well as a useful tool for designing new games. (more…)

Read more »