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 51–60 of 265 papers

TitleStatusHype
An Instrumental Variable Approach to Confounded Off-Policy Evaluation—0
Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning—0
Counterfactual Analysis in Dynamic Latent State Models—0
Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation—0
Data Poisoning Attacks on Off-Policy Policy Evaluation Methods—0
Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains—0
Counterfactual Learning with General Data-generating Policies—0
Bayesian Counterfactual Mean Embeddings and Off-Policy Evaluation—0
A Spectral Approach to Off-Policy Evaluation for POMDPs—0
A Review of Off-Policy Evaluation in Reinforcement Learning—0
Show:102550
← PrevPage 6 of 27Next →

No leaderboard results yet.