Tag
Adaptive Learning
2 findings
Methods & evidenceAdversarial Non-Stationarity Bounds in Multi-Armed BanditsProves that algorithms like the Tempered Thompson Algorithm achieve worst-case average regret on the order of $O(1/\sqrt{T})$ (up to logarithmic terms) relative to any fixed targeted assignment policy, guaranteeing robust participant welfare even under non-stationary outcome distributions.RCTEducationComputer-Assisted Learning ProgramComputer-assisted math learning increased mathematics test scores by 0.35 to 0.39 standard deviations in year 1 and 0.47 standard deviations in year 2 across all student achievement tiers.RCT