Finite-time analysis of the multiarmed bandit problem

Auer, P., Cesa-Bianchi, & Fischer, P. (2002). Finite-time analysis of the multiarmed bandit problem. Machine Learning, 47(2–3), 2-3.

Type

Journal article

Intellectual base

Primary research

Year

2002

Link

https://doi.org/10.1023/A:1013689704352verified

Cited from

biology_ecology

Cited by

1 citation across 1 artifact.

Each citation links to the sentence it supports in the citing article.

Primes

• Variation Strategies
  • The bandit framework balances exploitation (continuing with the best-known option) against exploration (testing alternatives), a problem Auer, Cesa-Bianchi, and Fischer (2002) solved with the UCB algorithm by quantifying the optimal exploration premium as a logarithmic function of regret.

    This sourceEstablishes the UCB algorithm and proves logarithmic regret bounds, providing the canonical formal treatment of the exploration–exploitation trade-off in sequential decision-making.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:5907ff79c386 · see in the full table