Balancing trying new choices with using choices that already work.
It is the ice-cream problem. Do you order trusty chocolate, or risk pickle swirl?
You meet it in RL, recommendation feeds, and online ads. It decides if a system sticks with a winner or tries a new path.
RL
This is one of RL's classic choices.
Q-Learning
Q-Learning balances top-scoring actions with new actions to test.
Temperature
Temperature changes randomness, so it changes how much the system explores.
Policy Gradient
Policy Gradient must chase steady rewards and keep room for trial and error.