The Nonstochastic Multiarmed Bandit Problem¶
Auer, P., Cesa-Bianchi, N., Freund, Y., & Schapire, R. E. (2002). The Nonstochastic Multiarmed Bandit Problem. SIAM Journal on Computing, 32(1), 48-77.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Mechanisms¶
- Adversarial Bandit Exploration Policy
- Its strength is a worst-case guarantee bought without an opponent model: against a non-stationary or unknown adversary, the adversarial bandit's regret bound keeps long-run loss provably close to the minimax value, and the residual randomization is a free by-product rather than a bolt-on.
This sourceProvides adversarial-bandit guarantees without a statistical opponent model, including regret bounds that approach the minimax payoff of an unknown repeated game.
- Its strength is a worst-case guarantee bought without an opponent model: against a non-stationary or unknown adversary, the adversarial bandit's regret bound keeps long-run loss provably close to the minimax value, and the residual randomization is a free by-product rather than a bolt-on.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Not recorded. The single citation of this work carries no recorded support check.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:ebed2737bcf1 · see in the full table