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 231–240 of 265 papers

TitleStatusHype
Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation—0
Adaptive Trade-Offs in Off-Policy Learning—0
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling—0
Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning—0
Off-Policy Evaluation in Partially Observable Environments—0
Efron-Stein PAC-Bayesian Inequalities—0
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision ProcessesCode0
Doubly robust off-policy evaluation with shrinkage—0
Task Selection Policies for Multitask Learning—0
Expected Sarsa(λ) with Control Variate for Variance Reduction—0
Show:102550
← PrevPage 24 of 27Next →

No leaderboard results yet.