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 61–70 of 265 papers

TitleStatusHype
A Review of Off-Policy Evaluation in Reinforcement Learning—0
Data-Driven Off-Policy Estimator Selection: An Application in User Marketing on An Online Content Delivery Service—0
CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation—0
Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation—0
Accountable Off-Policy Evaluation With Kernel Bellman Statistics—0
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference—0
Designing an Interpretable Interface for Contextual Bandits—0
A Principled Path to Fitted Distributional Evaluation—0
Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions—0
Defining Admissible Rewards for High Confidence Policy Evaluation—0
Show:102550
← PrevPage 7 of 27Next →

No leaderboard results yet.