{"total":77,"rows":[{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"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":"2108.13703","title":"Evaluating the Robustness of Off-Policy Evaluation","created":"2021-08-31","cited_by_count":32,"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":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2302.13960","title":"Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"area":"offlinerl"},{"id":"2306.15098","title":"Off-Policy Evaluation of Ranking Policies under Diverse User Behavior","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2201.12909","title":"Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times","created":"2022-01-30","cited_by_count":13,"area":null},{"id":"2307.15053","title":"On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation","created":"2023-07-27","cited_by_count":13,"area":null},{"id":"2311.18207","title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2402.06151","title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition","created":"2024-02-09","cited_by_count":13,"area":"deeprl"},{"id":"2405.05736","title":"Optimal Baseline Corrections for Off-Policy Contextual Bandits","created":"2024-05-09","cited_by_count":13,"area":null},{"id":"2309.11518","title":"Ad-load Balancing via Off-policy Learning in a Content Marketplace","created":"2023-09-19","cited_by_count":12,"area":null},{"id":"2305.01522","title":"Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization","created":"2023-04-26","cited_by_count":11,"area":null},{"id":"2302.01223","title":"Practical Bandits: An Industry Perspective","created":"2023-02-02","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":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"area":"deeprl"},{"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":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2305.03954","title":"Learning Action Embeddings for Off-Policy Evaluation","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","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":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"id":"2505.02069","title":"Neural Logistic Bandits","created":"2025-05-04","cited_by_count":6,"area":null},{"id":"2206.11338","title":"Synthetic Data-Based Simulators for Recommender Systems: A Survey","created":"2022-06-22","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":"2311.14110","title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","created":"2023-11-23","cited_by_count":4,"area":"alignment"},{"id":"2504.04395","title":"Human-Level Competitive Pok\\'emon via Scalable Offline Reinforcement Learning with Transformers","created":"2025-04-06","cited_by_count":4,"area":"offlinerl"},{"id":"2605.09168","title":"CIVeX: Causal Intervention Verification for Language Agents","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2609.22819","title":"Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints","created":"2026-09-19","cited_by_count":3,"area":null},{"id":"2209.04147","title":"Extending Open Bandit Pipeline to Simulate Industry Challenges","created":"2022-09-09","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":"2310.16819","title":"CATE Lasso: Conditional Average Treatment Effect Estimation with High-Dimensional Linear Regression","created":"2023-10-25","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":"2502.21304","title":"Clustering Context in Off-Policy Evaluation","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2605.12840","title":"Decision Support for Marketplace Policies under Incomplete Evidence: From Replay to Launch Readiness","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2304.09088","title":"A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits","created":"2023-04-16","cited_by_count":1,"area":null},{"id":"2308.03443","title":"Doubly Robust Estimator for Off-Policy Evaluation with Large Action Spaces","created":"2023-08-07","cited_by_count":1,"area":null},{"id":"2504.02646","title":"Prompt Optimization with Logged Bandit Data","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2510.22654","title":"Managing Self-Learning Experts under Per-Round Budget Constraints","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2511.04541","title":"Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2601.15552","title":"BanditLP: Large-Scale Stochastic Optimization for Personalized Recommendations","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2603.18702","title":"Off-Policy Learning with Limited Supply","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2605.20269","title":"Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.25290","title":"Choosing Online Experiment Designs under Interference in Ads, Recommendations, and Member-Experience Systems","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2112.09865","title":"Off-Policy Evaluation Using Information Borrowing and Context-Based Switching","created":"2021-12-18","cited_by_count":0,"area":null},{"id":"2211.06365","title":"Situating Recommender Systems in Practice: Towards Inductive Learning and Incremental Updates","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2408.04531","title":"AExGym: Benchmarks and Environments for Adaptive Experimentation","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2408.13484","title":"IntOPE: Off-Policy Evaluation in the Presence of Interference","created":"2024-08-24","cited_by_count":0,"area":null},{"id":"2409.09819","title":"A Simpler Alternative to Variational Regularized Counterfactual Risk Minimization","created":"2024-09-15","cited_by_count":0,"area":null},{"id":"2501.19401","title":"DAL: A Practical Prior-Free Black-Box Framework for Piecewise Stationary Bandits","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2504.08773","title":"Counterfactual Inference under Thompson Sampling","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2506.00446","title":"Off-Policy Evaluation of Ranking Policies via Embedding-Space User Behavior Modeling","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2507.18756","title":"Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2508.07914","title":"Meta Off-Policy Estimation","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2510.07635","title":"Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.15483","title":"Fast Best-in-Class Regret for Contextual Bandits","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2511.00802","title":"GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM Agents","created":"2025-11-02","cited_by_count":0,"area":"agents"},{"id":"2511.19240","title":"Empirical Comparison of Forgetting Mechanisms for UCB-based Algorithms on a Data-Driven Simulation Platform","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2604.23022","title":"CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.00193","title":"OTSS: Output-Targeted Soft Segmentation for Contextual Decision-Weight Learning","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.13346","title":"Contextual Bandits for Resource-Constrained Devices using Probabilistic Learning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.18509","title":"Offline Contextual Bandits in the Presence of New Actions","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.10187","title":"Decision-Calibrated Conformal Uncertainty for Pacing Decisions in Streaming Advertising","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.22510","title":"Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.23015","title":"Counterfactual learning of new adaptive instructional policies using logged data","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.14604","title":"Accelerating A/B-Tests with Counterfactual Estimation: Reducing Variance through Policy Overlap","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.10182","title":"From Prediction to Incrementality: Causal Optimization for Large-Scale Targeting and Recommendation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.11560","title":"When Offline Evaluation Misleads: A Diagnostic Protocol for Reward and Policy Selection in Delayed-Feedback Contextual Bandits","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.11675","title":"FunnelCausalNet: Funnel-aware Joint Conversion-Revenue Uplift for Multi-tier Coupon Allocation","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.12489","title":"When Can You Trust Offline Evaluation of Equal-Cost Top-k Allocation? A Controlled, Reproducible Benchmark and Practitioner's Guide","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.19709","title":"Odds-Ratio Thompson Sampling: A Specification and Design Guide for Contrast-Based Multi-Armed Bandits","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.30273","title":"Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.32962","title":"Clipped or Unclipped? Finite-Sample Trade-offs for Averaged SGD under Heavy-Tailed Noise","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35034","title":"Recommendation Ranking Off-Policy Evaluation under Ranking-Dependent Examination via Examination-Relevance Decomposition","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}