KDD 2025 - CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies

About this video

Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video

CSPI-MT: calibrated safe policy improvement with multiple testing for thresholds. Teaches safe reinforcement learning and statistical testing methodology.

Video by Association for Computing Machinery (ACM), played through YouTube's embedded player.