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 121–130 of 265 papers

TitleStatusHype
Conformal Off-Policy Prediction in Contextual Bandits—0
Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks—0
Markovian Interference in Experiments—0
Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning—0
Counterfactual Analysis in Dynamic Latent State Models—0
COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction EstimationCode1
Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems—0
Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments—0
Model-Free and Model-Based Policy Evaluation when Causality is UncertainCode0
Marginalized Operators for Off-policy Reinforcement Learning—0
Show:102550
← PrevPage 13 of 27Next →

No leaderboard results yet.