48 courses · The first chapter of every course is free to read
Understand how AI learns from rewards, step by step
Understand how machines learn from rewards, step by step
Understand how AI improves through simple trial and error
Understand reinforcement learning from zero to real-world use
Understand how AI learns from rewards, choices, and mistakes
Understand how machines learn by trying, failing, and improving
Understand how AI learns by trial and error without coding
Understand how machines learn from rewards, step by step
Learn reinforcement learning from zero in clear, simple steps
Learn RL from zero and build a simple reward-based agent
Learn how machines get better through simple trial and error
Learn how AI improves through rewards, step by step
Learn how robots and game agents improve through trial and error
Learn reinforcement learning from zero, one clear step at a time
Learn how an agent learns by rewards—and build your first simple policy.
Build a habit coach that improves its advice using rewards and feedback.
Build a to‑do helper that learns your habits and gets better every day.
Understand reinforcement learning by following simple stories—no math needed.
Go from zero to a working recommendation bot using simple RL ideas.
Train a virtual pet with rewards and learn reinforcement learning from scratch.
Design, train, and ship robust multi-agent RL systems end to end.
Train, debug, and ship RL game agents in OpenAI Gym end to end.
Go from tabular Q-learning to stable policy gradients, end-to-end.
Build RL agents from first principles to deep Q-networks in Python.