AI engineering glossary · Reinforcement learning
What is action-value function?
Action-value function (also called Q-function, Q-value): A function giving the expected return from taking a chosen action in a situation and then following a given decision rule. Comparing its values across actions shows which is best, so it allows picking choices without knowing how the world works.
Action-value function: an example
Q(s, up) = 6.2 and Q(s, down) = 3.5 means going up is expected to be worth 2.7 more than going down.
Related terms
More Reinforcement learning terms
- Actor-critic
- Agent
- AlphaGo
- AlphaZero
- Baseline (policy gradient)
- Behavioural cloning
- Belief state
- Bellman backup
Where you learn it
Action-value function is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.