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 261265 of 265 papers

TitleStatusHype
Off-policy evaluation for slate recommendationCode0
Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis0
Emphatic TD Bellman Operator is a Contraction0
Off-policy evaluation for MDPs with unknown structure0
On Minimax Optimal Offline Policy Evaluation0
Show:102550
← PrevPage 27 of 27Next →

No leaderboard results yet.