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 21–30 of 265 papers

TitleStatusHype
Offline RL Without Off-Policy EvaluationCode1
Optimal Off-Policy Evaluation from Multiple Logging PoliciesCode1
Bayesian Off-Policy Evaluation and Learning for Large Action Spaces—0
Adaptive Trade-Offs in Off-Policy Learning—0
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference—0
Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation—0
An Instrumental Variable Approach to Confounded Off-Policy Evaluation—0
Bayesian Counterfactual Mean Embeddings and Off-Policy Evaluation—0
Accountable Off-Policy Evaluation via a Kernelized Bellman Statistics—0
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization—0
Show:102550
← PrevPage 3 of 27Next →

No leaderboard results yet.