Reinforcement learning

Reinforcement learning is like when you are playing a game and you learn how to play it better over time to get better rewards.

For example, if you have a game where you move a character around by pushing buttons, you start out by just pushing buttons and seeing where it takes you. But if you keep playing, you learn how to make the character move to certain places to get good rewards like coins or points. That's reinforcement learning!

Related topics others have asked about:

Active learning (machine learning), Apprenticeship learning, Error-driven learning, Model-free (reinforcement learning), Multi-agent reinforcement learning, Optimal control, Q-learning, Reinforcement learning from human feedback, State–action–reward–state–action, Temporal difference learning