Reinforcement learning

After millions of games, machine learning algorithms found creative solutions and unexpected new strategies that could transfer to the real world.

The latest artificial intelligence systems start from zero knowledge of a game and grow to world-beating in a matter of hours. But researchers are struggling to apply these systems beyond the arcade.

A new version of AlphaGo needed no human instruction to figure out how to clobber the best Go player in the world — itself.

Computer scientists are finding ways to code curiosity into intelligent machines.

The Go-playing program teaches itself to replicate something very much like human intuition, an advance that promises far-reaching consequences.