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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 91–100 of 265 papers

TitleStatusHype
Importance Sampling Policy Evaluation with an Estimated Behavior PolicyCode0
On the Reuse Bias in Off-Policy Reinforcement LearningCode0
Policy-Adaptive Estimator Selection for Off-Policy EvaluationCode0
Post Reinforcement Learning InferenceCode0
Conformal Off-policy PredictionCode0
Minimum Empirical Divergence for Sub-Gaussian Linear BanditsCode0
Safe Exploration for Optimizing Contextual BanditsCode0
Data-Driven Off-Policy Estimator Selection: An Application in User Marketing on An Online Content Delivery Service—0
Bayesian Off-Policy Evaluation and Learning for Large Action Spaces—0
Counterfactual Learning with General Data-generating Policies—0
Show:102550
← PrevPage 10 of 27Next →

No leaderboard results yet.