AI engineering glossary · Reinforcement learning
What is function approximation?
Function approximation: Representing values or decision rules with a parameterised function, such as a linear model or neural network, rather than a table. It lets the learner generalise to unseen situations and handle huge or continuous state spaces, at the cost of possible instability.
Function approximation: an example
Instead of a table with a row for each of 10^20 board states, a network takes the board as input and outputs a value.
Related terms
More Reinforcement learning terms
- Goal-conditioned reinforcement learning
- Greedy policy
- Hierarchical reinforcement learning
- Hindsight experience replay
- Horizon
- Imitation learning
- Importance sampling ratio
- Intrinsic motivation
Where you learn it
Function approximation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.