Reinforcement Learning · Level 3 of 5
Q-Function
An estimate of expected return for taking an action in a state and then following a policy.
It distinguishes the value of different immediate choices.
Example
A game agent scores moving left versus moving right.
Listen to the definition and example
Audio transcript
Q-Function. An estimate of expected return for taking an action in a state and then following a policy. It distinguishes the value of different immediate choices. For example: A game agent scores moving left versus moving right.
Explore this concept
Why it matters
This helps you separate what an agent observes, chooses, and optimizes.
Start with
Related concepts
Quick recall question
Try answering before looking back at the definition.