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 11–20 of 265 papers

TitleStatusHype
COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction EstimationCode1
Off-Policy Evaluation of Ranking Policies under Diverse User BehaviorCode1
Anytime-valid off-policy inference for contextual banditsCode1
A Policy-Guided Imitation Approach for Offline Reinforcement LearningCode1
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor RepresentationCode1
Counterfactual Evaluation of Slate Recommendations with Sequential Reward InteractionsCode1
Evaluating the Robustness of Off-Policy EvaluationCode1
Doubly Robust Distributionally Robust Off-Policy Evaluation and LearningCode1
Active Offline Policy SelectionCode1
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy EvaluationCode1
Show:102550
← PrevPage 2 of 27Next →

No leaderboard results yet.