Multi-Armed Bandit
The multi-armed bandit (MAB) is an adaptive experimental framework that allocates trials sequentially across competing arms to minimise cumulative regret while simultaneously learning which arm performs best. Formalised by Robbins in 1952 and given finite-time guarantees by Auer et al. (2002), it balances exploration of uncertain options against exploitation of currently known best options — outperforming classical A/B testing whenever early stopping or cost-sensitive allocation matters.
Source record
Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.
- Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002). Finite-Time Analysis of the Multiarmed Bandit Problem. Machine Learning, 47(2–3), 235–256. · DOI 10.1023/A:1013689704352
- Russo, D., Van Roy, B., Kazerouni, A., Osband, I., & Wen, Z. (2018). A Tutorial on Thompson Sampling. Foundations and Trends in Machine Learning, 11(1), 1–96. · DOI 10.1561/2200000070
Curated claims
Claims persisted in the evidence ledger, each with its own assessment.
This view does not invent a claim assessment when the ledger has none.
Related methods
Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.