AI and Machine Learning Explained Rapid-Fire

Reinforcement Learning in 100 Seconds

Take a quick tour of reinforcement learning in just 100 seconds! See how AI agents reach decisions by trial and error, relying on rewards and penalties to get the hang of demanding tasks.

We’ll cover the core building blocks of reinforcement learning systems, unpack the exploration-versus-exploitation trade-off, and look at real-world cases such as AlphaGo and robotic hands that solve Rubik’s cubes. It’s an ideal starting point if you want to grasp how machines learn from experience instead of from examples. Be sure to watch our deep learning video next to understand the neural networks driving today’s reinforcement learning!