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 51–75 of 265 papers

TitleStatusHype
Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap—0
Off-Policy Evaluation of Slate Bandit Policies via Optimizing AbstractionCode0
Distributional Off-policy Evaluation with Bellman Residual MinimizationCode0
Probabilistic Offline Policy Ranking with Approximate Bayesian Computation—0
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health InterventionsCode0
Marginal Density Ratio for Off-Policy Evaluation in Contextual BanditsCode0
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy EvaluationCode1
SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy EvaluationCode1
When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric PerspectiveCode0
Unbiased Offline Evaluation for Learning to Rank with Business Rules—0
Robust Offline Reinforcement learning with Heavy-Tailed RewardsCode0
State-Action Similarity-Based Representations for Off-Policy EvaluationCode0
Counterfactual-Augmented Importance Sampling for Semi-Offline Policy EvaluationCode0
Off-Policy Evaluation for Large Action Spaces via Policy Convolution—0
Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks—0
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization—0
Off-Policy Evaluation for Human Feedback—0
Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework—0
Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits—0
Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning—0
Distributional Off-Policy Evaluation for Slate RecommendationsCode0
Doubly Robust Estimator for Off-Policy Evaluation with Large Action SpacesCode0
On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-n RecommendationCode0
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation—0
Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement LearningCode0
Show:102550
← PrevPage 3 of 11Next →

No leaderboard results yet.