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 21–30 of 265 papers

TitleStatusHype
Primal-Dual Spectral Representation for Off-policy Evaluation—0
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy EvaluationCode0
Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm—0
Designing an Interpretable Interface for Contextual Bandits—0
Limit Order Book Simulation and Trade Evaluation with K-Nearest-Neighbor Resampling—0
IntOPE: Off-Policy Evaluation in the Presence of Interference—0
Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits—0
Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment—0
Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal InterferencesCode0
Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation—0
Show:102550
← PrevPage 3 of 27Next →

No leaderboard results yet.