Eluder-Dimension-Free Regret for Stage-Wise Constrained Contextual Bandits via Offline Regression
Contextual bandits with stage-wise constraints model decisions that must control risk while learning from their outcomes. We study this problem when only the selected action's reward and cost are observed, with a general reward class and a convex class of nonlinear cost functions.
By Haichen Hu, David Simchi-Levi, Navid AzizanarXiv - stat.ML
Read the full story
Originally published by arXiv - stat.ML on Oct 23, 2026.
Comments
Sign in to join the discussion.