Machine learning

How a computer learns from rewards and examples instead of step-by-step instructions. Play first, then read how it works.

Game

Train a virtual puppy to find its treat. You set the rewards and penalties, and watch it learn by trial and error. Five missions plus a maze builder.

Short reads with pictures. Many have a live experiment built in.

Computers that learn from examples and experience, instead of following instructions step by step. The big idea in plain words.

Trial, error and rewards. See how a computer can learn a maze with nobody telling it the way.

Why AI does what you ask, not what you meant, and how a puppy found a loophole.

Hands-on activities for home, class or self-study.

A no-computer activity where one person is the puppy and another is the trainer. Learn reinforcement learning by doing it.