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 241–250 of 265 papers

TitleStatusHype
Conformal Off-policy PredictionCode0
On the Reuse Bias in Off-Policy Reinforcement LearningCode0
Importance Sampling Policy Evaluation with an Estimated Behavior PolicyCode0
Variational Latent Branching Model for Off-Policy EvaluationCode0
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy EvaluationCode0
Towards Hyperparameter-free Policy Selection for Offline Reinforcement LearningCode0
Strictly Batch Imitation Learning by Energy-based Distribution MatchingCode0
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement LearningCode0
Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL PoliciesCode0
K-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic ControlCode0
Show:102550
← PrevPage 25 of 27Next →

No leaderboard results yet.