Q-Learning on a Grid World

Reinforcement Learning Basics Intermediate 4 min read Published
In this lesson

Q-learning is the classic RL algorithm, and it fits in about 20 lines. The agent keeps a table of Q-values: for each state and action, “how much total reward can I expect if I take this action here and act well afterwards?”. Then it always picks the action with the highest Q.

🎬 Escaping the maze

🔒 This is a premium lesson

It is part of the Data Scientist career track.

🎬 Live animations · 🧪 Tested code · 💼 Projects · 🎓 Certificate

See the track

Already a member? Sign in

Progress is saved in this browser. Create a free account to keep it on every device.