SOTAVerified

Off-policy evaluation

Off-policy Evaluation (OPE), or offline evaluation in general, evaluates the performance of hypothetical policies leveraging only offline log data. It is particularly useful in applications where the online interaction involves high stakes and expensive setting such as precision medicine and recommender systems.

Papers

Showing 41–50 of 265 papers

TitleStatusHype
Deeply-Debiased Off-Policy Interval EstimationCode0
Distributional Off-Policy Evaluation for Slate RecommendationsCode0
DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current EffectsCode0
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision ProcessesCode0
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingCode0
Doubly Robust Estimator for Off-Policy Evaluation with Large Action SpacesCode0
Conformal Off-policy PredictionCode0
A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided MarketsCode0
Balanced Off-Policy Evaluation for Personalized PricingCode0
Counterfactual Mean EmbeddingsCode0
Show:102550
← PrevPage 5 of 27Next →

No leaderboard results yet.