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 131–140 of 265 papers

TitleStatusHype
Optimal Mixture Weights for Off-Policy Evaluation with Multiple Behavior Policies—0
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling—0
Practical Marginalized Importance Sampling with the Successor Representation—0
Primal-Dual Spectral Representation for Off-policy Evaluation—0
Privacy Preserving Off-Policy Evaluation—0
Probabilistic Offline Policy Ranking with Approximate Bayesian Computation—0
Quantile Off-Policy Evaluation via Deep Conditional Generative Learning—0
Reliable Off-policy Evaluation for Reinforcement Learning—0
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation—0
Debiased Off-Policy Evaluation for Recommendation Systems—0
Show:102550
← PrevPage 14 of 27Next →

No leaderboard results yet.