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 61–70 of 265 papers

TitleStatusHype
From Importance Sampling to Doubly Robust Policy GradientCode0
Cross-Validated Off-Policy EvaluationCode0
Deep Proxy Causal Learning and its Application to Confounded Bandit Policy EvaluationCode0
Deeply-Debiased Off-Policy Interval EstimationCode0
Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment SettingsCode0
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy EvaluationCode0
Doubly Robust Estimator for Off-Policy Evaluation with Large Action SpacesCode0
Distributional Off-policy Evaluation with Bellman Residual MinimizationCode0
DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current EffectsCode0
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health InterventionsCode0
Show:102550
← PrevPage 7 of 27Next →

No leaderboard results yet.