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 1–25 of 265 papers

TitleStatusHype
Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior ModelCode2
Off-Policy Evaluation for Large Action Spaces via EmbeddingsCode2
Counterfactual Evaluation of Slate Recommendations with Sequential Reward InteractionsCode1
Off-Policy Evaluation via Adaptive Weighting with Data from Contextual BanditsCode1
Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy EvaluationCode1
SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy EvaluationCode1
Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy EvaluationCode1
Benchmarks for Deep Off-Policy EvaluationCode1
Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare SettingsCode1
Off-Policy Evaluation of Ranking Policies under Diverse User BehaviorCode1
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy EvaluationCode1
Trajectory World Models for Heterogeneous EnvironmentsCode1
Anytime-valid off-policy inference for contextual banditsCode1
A Policy-Guided Imitation Approach for Offline Reinforcement LearningCode1
A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor RepresentationCode1
Doubly Robust Distributionally Robust Off-Policy Evaluation and LearningCode1
Evaluating the Robustness of Off-Policy EvaluationCode1
BCORLE(): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce MarketCode1
Active Offline Policy SelectionCode1
COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction EstimationCode1
Offline RL Without Off-Policy EvaluationCode1
Optimal Off-Policy Evaluation from Multiple Logging PoliciesCode1
Counterfactual Learning with Multioutput Deep KernelsCode0
Adaptive Estimator Selection for Off-Policy EvaluationCode0
Balanced Off-Policy Evaluation for Personalized PricingCode0
Show:102550
← PrevPage 1 of 11Next →

No leaderboard results yet.