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 171–180 of 265 papers

TitleStatusHype
Accountable Off-Policy Evaluation via a Kernelized Bellman Statistics—0
Accountable Off-Policy Evaluation With Kernel Bellman Statistics—0
Adaptive Trade-Offs in Off-Policy Learning—0
A maximum-entropy approach to off-policy evaluation in average-reward MDPs—0
An Instrumental Variable Approach to Confounded Off-Policy Evaluation—0
A Practical Guide of Off-Policy Evaluation for Bandit Problems—0
A Principled Path to Fitted Distributional Evaluation—0
A Review of Off-Policy Evaluation in Reinforcement Learning—0
A Spectral Approach to Off-Policy Evaluation for POMDPs—0
Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning—0
Show:102550
← PrevPage 18 of 27Next →

No leaderboard results yet.