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 101–125 of 265 papers

TitleStatusHype
Consistent On-Line Off-Policy Evaluation—0
Offline Policy Evaluation and Optimization under Confounding—0
Loss Functions for Discrete Contextual Pricing with Observational Data—0
Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making—0
A Principled Path to Fitted Distributional Evaluation—0
Off-policy estimation with adaptively collected data: the power of online learning—0
Counterfactual Analysis in Dynamic Latent State Models—0
HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare—0
Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation—0
Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning—0
Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions—0
Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It—0
Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect—0
Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm—0
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions—0
IntOPE: Off-Policy Evaluation in the Presence of Interference—0
Bayesian Counterfactual Mean Embeddings and Off-Policy Evaluation—0
Off-policy evaluation for learning-to-rank via interpolating the item-position model and the position-based model—0
Marginalized Operators for Off-policy Reinforcement Learning—0
Large-scale Validation of Counterfactual Learning Methods: A Test-Bed—0
Bayesian Off-Policy Evaluation and Learning for Large Action Spaces—0
Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments—0
Deep Jump Q-Evaluation for Offline Policy Evaluation in Continuous Action Space—0
Limit Order Book Simulation and Trade Evaluation with K-Nearest-Neighbor Resampling—0
Debiasing Samples from Online Learning Using Bootstrap—0
Show:102550
← PrevPage 5 of 11Next →

No leaderboard results yet.