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

Showing 201210 of 265 papers

TitleStatusHype
Confident Off-Policy Evaluation and Selection through Self-Normalized Importance WeightingCode0
Minimum Empirical Divergence for Sub-Gaussian Linear BanditsCode0
Off-Policy Evaluation of Slate Bandit Policies via Optimizing AbstractionCode0
Model-Free and Model-Based Policy Evaluation when Causality is UncertainCode0
Distributional Off-Policy Evaluation for Slate RecommendationsCode0
Distributional Off-policy Evaluation with Bellman Residual MinimizationCode0
Counterfactual-Augmented Importance Sampling for Semi-Offline Policy EvaluationCode0
DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current EffectsCode0
SOPE: Spectrum of Off-Policy EstimatorsCode0
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision ProcessesCode0
Show:102550
← PrevPage 21 of 27Next →

No leaderboard results yet.