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 201–225 of 265 papers

TitleStatusHype
Distributional Off-Policy Evaluation for Slate RecommendationsCode0
Distributional Off-policy Evaluation with Bellman Residual MinimizationCode0
Robust Generalization despite Distribution Shift via Minimum Discriminating InformationCode0
DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current EffectsCode0
Robust Offline Reinforcement learning with Heavy-Tailed RewardsCode0
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision ProcessesCode0
Variational Latent Branching Model for Off-Policy EvaluationCode0
Off-Policy Evaluation with Out-of-Sample GuaranteesCode0
Counterfactual Learning with Multioutput Deep KernelsCode0
Doubly Robust Estimator for Off-Policy Evaluation with Large Action SpacesCode0
Doubly Robust Kernel Statistics for Testing Distributional Treatment EffectsCode0
Counterfactual Evaluation of Peer-Review Assignment PoliciesCode0
Doubly robust off-policy evaluation with shrinkageCode0
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation ApproachCode0
Conformal Off-policy PredictionCode0
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision ProcessesCode0
Safe Exploration for Optimizing Contextual BanditsCode0
Towards Hyperparameter-free Policy Selection for Offline Reinforcement LearningCode0
Adaptive Estimator Selection for Off-Policy EvaluationCode0
Off-Policy Evaluation and Learning for External Validity under a Covariate ShiftCode0
On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-n RecommendationCode0
Strictly Batch Imitation Learning by Energy-based Distribution MatchingCode0
Off-Policy Evaluation for Action-Dependent Non-Stationary EnvironmentsCode0
Counterfactual-Augmented Importance Sampling for Semi-Offline Policy EvaluationCode0
On the Reuse Bias in Off-Policy Reinforcement LearningCode0
Show:102550
← PrevPage 9 of 11Next →

No leaderboard results yet.