השוואת שיטות

	רב-זרועי (UCB, Thompson Sampling)	תכנון ניסויים קליניים אדפטיביים
תחום	תכנון ניסויים	תכנון ניסויים
משפחה	Hypothesis test	Hypothesis test
שנת המקור	1952	1994
הוגה השיטה	Robbins (1952); UCB1 by Auer et al. (2002); Thompson sampling by Thompson (1933)	Bauer & Köhne
סוג	Sequential decision / bandit algorithm	Adaptive hypothesis test with interim analyses
מקור מכונן	Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002). Finite-Time Analysis of the Multiarmed Bandit Problem. Machine Learning, 47(2–3), 235–256.	Bauer, P. & Köhne, K. (1994). Evaluation of Experiments with Adaptive Interim Analyses. Biometrics, 50(4), 1029–1041.
כינויים	MAB, bandit algorithm, UCB1, Thompson sampling	adaptive design, group sequential design, sample size re-estimation, platform trial
קשורות	4	3
תקציר	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.	Adaptive clinical trial design is a flexible experimental framework, formalised by Bauer and Köhne in 1994, in which pre-specified rules allow the trial to be modified mid-course — adjusting sample size, treatment arms, or randomisation ratios — based on accumulating interim data while rigorously controlling the Type I error rate.