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 151–160 of 265 papers

TitleStatusHype
Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making—0
On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation—0
Off-Policy Evaluation Using Information Borrowing and Context-Based SwitchingCode0
Optimal discharge of patients from intensive care via a data-driven policy learning framework—0
Subgaussian and Differentiable Importance Sampling for Off-Policy Evaluation and LearningCode0
Weighted model estimation for offline model-based reinforcement learning—0
Loss Functions for Discrete Contextual Pricing with Observational Data—0
A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision ProcessesCode0
SOPE: Spectrum of Off-Policy EstimatorsCode0
Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision ProcessesCode0
Show:102550
← PrevPage 16 of 27Next →

No leaderboard results yet.