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

Showing 8190 of 265 papers

TitleStatusHype
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy EvaluationCode0
Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement LearningCode0
Off-policy Evaluation with Deeply-abstracted StatesCode0
From Importance Sampling to Doubly Robust Policy GradientCode0
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health InterventionsCode0
Off-Policy Evaluation and Learning for External Validity under a Covariate ShiftCode0
Future-Dependent Value-Based Off-Policy Evaluation in POMDPsCode0
Off-policy Evaluation in Doubly Inhomogeneous EnvironmentsCode0
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision ProcessesCode0
Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy EvaluationCode0
Show:102550
← PrevPage 9 of 27Next →

No leaderboard results yet.