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 31–40 of 265 papers

TitleStatusHype
Off-policy Evaluation with Deeply-abstracted StatesCode0
Confident Natural Policy Gradient for Local Planning in q_π-realizable Constrained MDPs—0
Automated Off-Policy Estimator Selection via Supervised Learning—0
Off-Policy Evaluation from Logged Human Feedback—0
A Fast Convergence Theory for Offline Decision Making—0
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation—0
Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL PoliciesCode0
OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators—0
Cross-Validated Off-Policy EvaluationCode0
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and LearningCode0
Show:102550
← PrevPage 4 of 27Next →

No leaderboard results yet.