Reinforcement learning: how computers learn from experience
Reinforcement learning is a form of AI training that allows a program to explore an environment and learn from its experiences.
It's used in self-driving cars, wherein the software learns how to lane merge safely after driving the same simulated roads many, many times.
It's also used in games. Instead of writing complicated instructions, programmers set an AI loose to play itself inside board games like Go, Chess, and Bakgammon, and multiplayer games like Starcraft. In some instances, like OpenAI's quest to teach an AI to play the video game Dota 2, the AIs played an equivalent of 180 years per day in order to learn and play well.
In some cases, the best practices AIs develop through reinforcement look very different from human play.
If you want to see where human-machine competition is fiercest, look to games. Complex, rules-based games present the ideal environment to train AI systems, where the industry's top startups compete against the world's best players.