AI engineering glossary · Reinforcement learning
What is model-based?
Model-based: Describes methods that learn or are given a model of how the world responds to choices, and use it to plan, simulate or generate extra experience. They can need far less real interaction, but errors in the model can mislead the learner.
Model-based: an example
A robot learns a physics model from 1,000 real steps and then tests thousands of imagined moves inside it.
Related terms
More Reinforcement learning terms
- Model-free
- Monte Carlo methods (reinforcement learning)
- Monte Carlo tree search
- Multi-agent reinforcement learning
- Multi-armed bandit
- MuZero
- n-step return
- Nash equilibrium
Where you learn it
Model-based is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.