The technique that taught AI to play Go still can't teach a car to drive

Reinforcement learning (RL), the category of machine learning that relies on penalties and rewards, can be a powerful technique for teaching machines to adapt to new environments. Deepmind's AlphaGo used it to defeat the world's best Go player despite never having played him before. It has also shown promise in the creation of robots that can perform under changing conditions. But the technique has its limitations. It requires a machine to blunder around as it slowly refines its actions over time.