AI engineering glossary · Reinforcement learning
What is muZero?
MuZero: A DeepMind method that learns its own internal model of the world, predicting only the quantities needed for planning: reward, value and action probabilities. It plans with tree search inside this learned model, without being told the game rules.
MuZero: an example
It reached strong play in board games and Atari without a rules simulator.
Related terms
More Reinforcement learning terms
- n-step return
- Nash equilibrium
- Natural policy gradient
- Noisy networks
- Off-policy
- Off-policy evaluation
- Offline reinforcement learning
- On-policy
Where you learn it
MuZero is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.