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 161–170 of 265 papers

TitleStatusHype
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach—0
Towards Robust Off-Policy Evaluation via Human Inputs—0
Triply Robust Off-Policy Evaluation—0
Unbiased Offline Evaluation for Learning to Rank with Business Rules—0
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling—0
Variance-Aware Off-Policy Evaluation with Linear Function Approximation—0
Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits—0
Weighted model estimation for offline model-based reinforcement learning—0
Why Should I Trust You, Bellman? Evaluating the Bellman Objective with Off-Policy Data—0
Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation—0
Show:102550
← PrevPage 17 of 27Next →

No leaderboard results yet.