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.