{"total":138,"rows":[{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2103.14029","title":"Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach","created":"2021-03-25","cited_by_count":44,"area":null},{"id":"2210.10768","title":"Anytime-valid off-policy inference for contextual bandits","created":"2022-10-19","cited_by_count":37,"area":null},{"id":"2305.08062","title":"Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling","created":"2023-05-14","cited_by_count":34,"area":null},{"id":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32,"area":null},{"id":"2108.13703","title":"Evaluating the Robustness of Off-Policy Evaluation","created":"2021-08-31","cited_by_count":32,"area":null},{"id":"2202.05436","title":"Minimax Regret Optimization for Robust Machine Learning under Distribution Shift","created":"2022-02-11","cited_by_count":31,"area":null},{"id":"2202.01562","title":"Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model","created":"2022-02-03","cited_by_count":30,"area":null},{"id":"2104.08977","title":"Off-Policy Risk Assessment in Contextual Bandits","created":"2021-04-18","cited_by_count":29,"area":null},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","cited_by_count":27,"area":null},{"id":"2206.04405","title":"Conformal Off-Policy Prediction in Contextual Bandits","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21,"area":null},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2203.17118","title":"Doubly-Robust Estimation for Correcting Position-Bias in Click Feedback for Unbiased Learning to Rank","created":"2022-03-31","cited_by_count":18,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2402.02171","title":"Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction","created":"2024-02-03","cited_by_count":17,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2112.01387","title":"Generalizing Off-Policy Learning under Sample Selection Bias","created":"2021-12-02","cited_by_count":16,"area":null},{"id":"2405.14335","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"area":null},{"id":"2303.01049","title":"Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2305.15877","title":"Exponential Smoothing for Off-Policy Learning","created":"2023-05-25","cited_by_count":15,"area":null},{"id":"2305.19742","title":"Reliable Off-Policy Learning for Dosage Combinations","created":"2023-05-31","cited_by_count":15,"area":null},{"id":"2310.15433","title":"Off-Policy Evaluation for Large Action Spaces via Policy Convolution","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2405.05736","title":"Optimal Baseline Corrections for Off-Policy Contextual Bandits","created":"2024-05-09","cited_by_count":13,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2204.12956","title":"Towards assessing agricultural land suitability with causal machine learning","created":"2022-04-27","cited_by_count":11,"area":null},{"id":"2106.01723","title":"Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning","created":"2021-06-03","cited_by_count":10,"area":null},{"id":"2309.08748","title":"Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits","created":"2023-09-15","cited_by_count":10,"area":null},{"id":"2405.02141","title":"Multi-Objective Recommendation via Multivariate Policy Learning","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2309.04470","title":"On the Actionability of Outcome Prediction","created":"2023-09-08","cited_by_count":9,"area":null},{"id":"2312.01457","title":"Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits","created":"2023-12-03","cited_by_count":9,"area":null},{"id":"2404.15691","title":"Long-term Off-Policy Evaluation and Learning","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2405.10024","title":"$\\Delta\\text{-}{\\rm OPE}$: Off-Policy Estimation with Pairs of Policies","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2208.06263","title":"Probabilistic Rank and Reward: A Scalable Model for Slate Recommendation","created":"2022-08-10","cited_by_count":8,"area":null},{"id":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2502.00225","title":"Should You Use Your Large Language Model to Explore or Exploit?","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2204.03140","title":"Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments","created":"2022-04-07","cited_by_count":7,"area":null},{"id":"2209.10444","title":"Off-Policy Risk Assessment in Markov Decision Processes","created":"2022-09-21","cited_by_count":7,"area":null},{"id":"2211.16110","title":"PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison","created":"2022-11-29","cited_by_count":7,"area":null},{"id":"2302.02944","title":"Learning Complementary Policies for Human-AI Teams","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2305.03954","title":"Learning Action Embeddings for Off-Policy Evaluation","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2106.04443","title":"Robust Generalization despite Distribution Shift via Minimum Discriminating Information","created":"2021-06-08","cited_by_count":6,"area":null},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2111.09933","title":"Loss Functions for Discrete Contextual Pricing with Observational Data","created":"2021-11-18","cited_by_count":6,"area":null},{"id":"2206.04907","title":"Efficient Heterogeneous Treatment Effect Estimation With Multiple Experiments and Multiple Outcomes","created":"2022-06-10","cited_by_count":6,"area":null},{"id":"2210.13373","title":"Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2302.12120","title":"Sequential Counterfactual Risk Minimization","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2310.06969","title":"Positivity-free Policy Learning with Observational Data","created":"2023-10-10","cited_by_count":6,"area":null},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2106.13125","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","created":"2021-06-24","cited_by_count":5,"area":null},{"id":"2112.04461","title":"Enhancing Counterfactual Classification via Self-Training","created":"2021-12-08","cited_by_count":5,"area":null},{"id":"2402.14664","title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2404.15084","title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","cited_by_count":4,"area":null},{"id":"2202.10574","title":"A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2203.03303","title":"PAC-Bayesian Lifelong Learning For Multi-Armed Bandits","created":"2022-03-07","cited_by_count":4,"area":null},{"id":"2310.08824","title":"Confounding-Robust Policy Improvement with Human-AI Teams","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2401.11353","title":"Distributionally Robust Policy Evaluation under General Covariate Shift in Contextual Bandits","created":"2024-01-21","cited_by_count":4,"area":null},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2103.15933","title":"Learning Under Adversarial and Interventional Shifts","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2106.03934","title":"Offline Policy Comparison under Limited Historical Agent-Environment Interactions","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2202.12958","title":"Off-Policy Evaluation with Policy-Dependent Optimization Response","created":"2022-02-25","cited_by_count":3,"area":null},{"id":"2203.02473","title":"Interpretable Off-Policy Learning via Hyperbox Search","created":"2022-03-04","cited_by_count":3,"area":null},{"id":"2212.01925","title":"Counterfactual Learning with General Data-generating Policies","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2308.01566","title":"Fast Slate Policy Optimization: Going Beyond Plackett-Luce","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2403.00886","title":"Evaluating and Correcting Performative Effects of Decision Support Systems via Causal Domain Shift","created":"2024-03-01","cited_by_count":3,"area":null},{"id":"2405.15332","title":"Cross-Validated Off-Policy Evaluation","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2411.12786","title":"Off-policy estimation with adaptively collected data: the power of online learning","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2105.12898","title":"Stochastic Intervention for Causal Effect Estimation","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2105.13420","title":"Model Selection for Production System via Automated Online Experiments","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2203.02807","title":"Off-Policy Evaluation in Embedded Spaces","created":"2022-03-05","cited_by_count":2,"area":null},{"id":"2206.02593","title":"Pessimistic Off-Policy Optimization for Learning to Rank","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2209.07148","title":"Semi-supervised Batch Learning From Logged Data","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2301.13348","title":"A Reinforcement Learning Framework for Dynamic Mediation Analysis","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2303.04201","title":"DR-VIDAL -- Doubly Robust Variational Information-theoretic Deep Adversarial Learning for Counterfactual Prediction and Treatment Effect Estimation on Real World Data","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2303.10218","title":"An Empirical Evaluation of Federated Contextual Bandit Algorithms","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2303.16800","title":"Correcting for Selection Bias and Missing Response in Regression using Privileged Information","created":"2023-03-29","cited_by_count":2,"area":null},{"id":"2308.14165","title":"Distributional Off-Policy Evaluation for Slate Recommendations","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2310.18617","title":"Pessimistic Off-Policy Multi-Objective Optimization","created":"2023-10-28","cited_by_count":2,"area":null},{"id":"2404.00848","title":"Predictive Performance Comparison of Decision Policies Under Confounding","created":"2024-04-01","cited_by_count":2,"area":null},{"id":"2406.18022","title":"Automated Off-Policy Estimator Selection via Supervised Learning","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2407.17910","title":"Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2506.10677","title":"Exploiting Similarities in A/B Testing with Off-Policy Estimation","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2507.13608","title":"Off-Policy Evaluation and Learning for Matching Markets","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2507.18118","title":"A Two-armed Bandit Framework for A/B Testing","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2512.05267","title":"Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2605.01311","title":"The Partial Testimony of Logs: Evaluation of Language Model Generation under Confounded Model Choice","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2105.13514","title":"Stochastic Intervention for Causal Inference via Reinforcement Learning","created":"2021-05-28","cited_by_count":1,"area":null},{"id":"2201.12163","title":"Biases in In Silico Evaluation of Molecular Optimization Methods and Bias-Reduced Evaluation Methodology","created":"2022-01-28","cited_by_count":1,"area":null},{"id":"2202.13337","title":"Towards Robust Off-policy Learning for Runtime Uncertainty","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2205.07250","title":"A cGAN Ensemble-based Uncertainty-aware Surrogate Model for Offline Model-based Optimization in Industrial Control Problems","created":"2022-05-15","cited_by_count":1,"area":null},{"id":"2208.11747","title":"Entropy Regularization for Population Estimation","created":"2022-08-24","cited_by_count":1,"area":null}],"next_cursor":"100"}