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 111–120 of 265 papers

TitleStatusHype
Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis—0
Balanced off-policy evaluation in general action spaces—0
Consistent On-Line Off-Policy Evaluation—0
Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm—0
Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency—0
IntOPE: Off-Policy Evaluation in the Presence of Interference—0
Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning—0
Expected Sarsa(λ) with Control Variate for Variance Reduction—0
Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective—0
Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment—0
Show:102550
← PrevPage 12 of 27Next →

No leaderboard results yet.