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 11–20 of 265 papers

TitleStatusHype
Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol—0
Trajectory World Models for Heterogeneous EnvironmentsCode1
Off-policy Evaluation for Payments at Adyen—0
Off-Policy Evaluation and Counterfactual Methods in Dynamic Auction Environments—0
CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation—0
Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement LearningCode0
Concept-driven Off Policy Evaluation—0
Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect—0
Off-policy estimation with adaptively collected data: the power of online learning—0
Minimum Empirical Divergence for Sub-Gaussian Linear BanditsCode0
Show:102550
← PrevPage 2 of 27Next →

No leaderboard results yet.