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
Stateful Offline Contextual Policy Evaluation and Learning—0
Statistical Bootstrapping for Uncertainty Estimation in Off-Policy Evaluation—0
Statistical Estimation of Confounded Linear MDPs: An Instrumental Variable Approach—0
Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning—0
STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation—0
Task Selection Policies for Multitask Learning—0
Taylor Expansion Policy Optimization—0
Cramming Contextual Bandits for On-policy Statistical Evaluation—0
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation—0
Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes—0
Show:102550
← PrevPage 16 of 27Next →

No leaderboard results yet.