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 71–80 of 265 papers

TitleStatusHype
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference—0
Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm—0
Discovering an Aid Policy to Minimize Student Evasion Using Offline Reinforcement Learning—0
CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation—0
A Spectral Approach to Off-Policy Evaluation for POMDPs—0
Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework—0
Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains—0
Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimation—0
Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation—0
A Principled Path to Fitted Distributional Evaluation—0
Show:102550
← PrevPage 8 of 27Next →

No leaderboard results yet.