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 251–265 of 265 papers

TitleStatusHype
Offline Comparison of Ranking Functions using Randomized Data—0
Efficient Counterfactual Learning from Bandit Feedback—0
Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy—0
Importance Sampling Policy Evaluation with an Estimated Behavior PolicyCode0
Counterfactual Mean EmbeddingsCode0
More Robust Doubly Robust Off-policy Evaluation—0
Consistent On-Line Off-Policy Evaluation—0
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits—0
Large-scale Validation of Counterfactual Learning Methods: A Test-Bed—0
Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation—0
Off-policy evaluation for slate recommendationCode0
Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis—0
Emphatic TD Bellman Operator is a Contraction—0
Off-policy evaluation for MDPs with unknown structure—0
On Minimax Optimal Offline Policy Evaluation—0
Show:102550
← PrevPage 6 of 6Next →

No leaderboard results yet.