Thompson Sampling

Fact

A decision method using uncertainty samples to balance new tries and likely winners.

In Plain Words

Imagine three arcade claw machines. Try each one, then feed more quarters to the less cursed one.

It keeps testing while favoring the current favorite. Ads and recommendation feeds use it to send more traffic to what works.

Related Concepts

• Exploration-Exploitation Tradeoff
• Reinforcement Learning

Exploration-Exploitation Tradeoff
Thompson Sampling balances trying new choices with using likely winners.

RL
Thompson Sampling can guide online decisions as the system learns by acting.