conftrace_

off-policy selection

3 papers

Explore in graph

Also known as

OPS

Co-occurring keywords · papers mentioning both

confidence bound (2) contextual bandit (2) off-policy evaluation (2) self-normalized estimator (1) heterogeneous treatment (1) human-centric system (1) freezing (1) inverse propensity weight (1) variance-adaptive guarantee (1) self-normalized importance weighting (1)

Papers

Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing COLT 2025 Off-Policy Selection for Initiating Human-Centric Experimental Design NeurIPS 2024 Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting AISTATS 2021