Skip to content

Model Training & Adaptation

Q-learning

AI learning which actions are likely to lead to useful rewards in different situations.

Example

An agent learns which moves tend to produce higher future rewards.

Why people use it

It helps an agent learn which choices tend to lead to better later rewards.

What you'll hear

“Which move seems most promising from here?”

What this means for you

Judge the learned behavior under relevant conditions and limits.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Does Q-learning need a complete map of the environment?
Not necessarily. It can learn from experience without an explicit transition AI system.
Can a choice with no immediate reward still be useful?
Yes. It may lead to better rewards later in the sequence.
Does the agent have to try unfamiliar choices?
Some exploration is usually needed to discover useful actions it has not yet experienced.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice