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 31–40 of 265 papers

TitleStatusHype
Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization—0
Concept-driven Off Policy Evaluation—0
Confident Natural Policy Gradient for Local Planning in q_π-realizable Constrained MDPs—0
Conformal Off-Policy Prediction in Contextual Bandits—0
Automated Off-Policy Estimator Selection via Supervised Learning—0
A Unified Off-Policy Evaluation Approach for General Value Function—0
A maximum-entropy approach to off-policy evaluation in average-reward MDPs—0
A Fast Convergence Theory for Offline Decision Making—0
Characterization of Efficient Influence Function for Off-Policy Evaluation Under Optimal Policies—0
Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning—0
Show:102550
← PrevPage 4 of 27Next →

No leaderboard results yet.