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 191–200 of 265 papers

TitleStatusHype
Bootstrapping Fitted Q-Evaluation for Off-Policy Inference—0
Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation—0
CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation—0
Causality and Batch Reinforcement Learning: Complementary Approaches To Planning In Unknown Domains—0
Characterization of Efficient Influence Function for Off-Policy Evaluation Under Optimal Policies—0
CoinDICE: Off-Policy Confidence Interval Estimation—0
Combining Parametric and Nonparametric Models for Off-Policy Evaluation—0
Concept-driven Off Policy Evaluation—0
Confidence Interval for Off-Policy Evaluation from Dependent Samples via Bandit Algorithm: Approach from Standardized Martingales—0
Confident Natural Policy Gradient for Local Planning in q_π-realizable Constrained MDPs—0
Show:102550
← PrevPage 20 of 27Next →

No leaderboard results yet.