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 241–250 of 265 papers

TitleStatusHype
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement LearningCode0
Balanced off-policy evaluation in general action spaces—0
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling—0
Off-Policy Evaluation via Off-Policy Classification—0
Defining Admissible Rewards for High Confidence Policy Evaluation—0
Semi-Parametric Efficient Policy Learning with Continuous ActionsCode0
Combining Parametric and Nonparametric Models for Off-Policy Evaluation—0
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal ModelsCode0
Privacy Preserving Off-Policy Evaluation—0
Off-Policy Evaluation of Probabilistic Identity Data in Lookalike Modeling—0
Show:102550
← PrevPage 25 of 27Next →

No leaderboard results yet.