The Price of Current-Effect Inference in Nonstationary Multi-Armed Bandits
Adaptive experiments use bandit algorithms to favor interventions with higher expected rewards. However, decision-makers also require reliable inference on current treatment effects: differences between intervention and reference-arm mean rewards at the present time, rather than historical…
By Sharan Sahu, Martin T. WellsarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 22, 2026.
Comments
Sign in to join the discussion.