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 181–190 of 265 papers

TitleStatusHype
A Fast Convergence Theory for Offline Decision Making—0
A Unified Off-Policy Evaluation Approach for General Value Function—0
Automated Off-Policy Estimator Selection via Supervised Learning—0
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization—0
Balanced off-policy evaluation in general action spaces—0
Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation—0
Bayesian Counterfactual Mean Embeddings and Off-Policy Evaluation—0
Bayesian Off-Policy Evaluation and Learning for Large Action Spaces—0
Bellman Residual Orthogonalization for Offline Reinforcement Learning—0
Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions—0
Show:102550
← PrevPage 19 of 27Next →

No leaderboard results yet.