{"total":103,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"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":"2305.01738","title":"Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare","created":"2023-05-02","cited_by_count":42,"area":"offlinerl"},{"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":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","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":"2206.04405","title":"Conformal Off-Policy Prediction in Contextual Bandits","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"area":null},{"id":"2210.13132","title":"PAC-Bayesian Offline Contextual Bandits With Guarantees","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"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":"2306.15098","title":"Off-Policy Evaluation of Ranking Policies under Diverse User Behavior","created":"2023-06-26","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":"2106.14979","title":"On component interactions in two-stage recommender systems","created":"2021-06-28","cited_by_count":14,"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":"2106.07914","title":"Control Variates for Slate Off-Policy Evaluation","created":"2021-06-15","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":"2312.01624","title":"GVFs in the Real World: Making Predictions Online for Water Treatment","created":"2023-12-04","cited_by_count":13,"area":null},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2102.13302","title":"Variation Control and Evaluation for Generative SlateRecommendations","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2106.11560","title":"Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge","created":"2021-06-22","cited_by_count":10,"area":null},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"area":null},{"id":"2209.08860","title":"A Survey of Deep Causal Models and Their Industrial Applications","created":"2022-09-19","cited_by_count":10,"area":null},{"id":"2212.05778","title":"Instrumental Variables in Causal Inference and Machine Learning: A Survey","created":"2022-12-12","cited_by_count":10,"area":null},{"id":"2308.11336","title":"On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems","created":"2023-08-22","cited_by_count":10,"area":"offlinerl"},{"id":"2105.02377","title":"Towards Content Provider Aware Recommender Systems: A Simulation Study on the Interplay between User and Provider Utilities","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2107.00680","title":"A Map of Bandits for E-commerce","created":"2021-07-01","cited_by_count":9,"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":"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":"2102.07800","title":"Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2202.03867","title":"Offline Reinforcement Learning for Mobile Notifications","created":"2022-02-04","cited_by_count":8,"area":"offlinerl"},{"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":"2107.11533","title":"Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support","created":"2021-07-24","cited_by_count":7,"area":null},{"id":"2112.03210","title":"Contextual Bandit Applications in Customer Support Bot","created":"2021-12-06","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":"2311.02467","title":"Individualized Policy Evaluation and Learning under Clustered Network Interference","created":"2023-11-04","cited_by_count":6,"area":null},{"id":"2107.12455","title":"Combining Reward and Rank Signals for Slate Recommendation","created":"2021-07-26","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":"2406.10030","title":"Off-Policy Evaluation from Logged Human Feedback","created":"2024-06-14","cited_by_count":5,"area":"alignment"},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"id":"2110.15501","title":"Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning","created":"2021-10-29","cited_by_count":4,"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":"2204.07135","title":"Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems","created":"2022-04-14","cited_by_count":4,"area":null},{"id":"2209.08429","title":"Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems","created":"2022-09-17","cited_by_count":4,"area":null},{"id":"2302.02570","title":"Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation","created":"2023-02-06","cited_by_count":4,"area":null},{"id":"2303.04268","title":"On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples","created":"2023-03-07","cited_by_count":4,"area":"offlinerl"},{"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":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","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":"2405.18792","title":"Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies","created":"2024-05-29","cited_by_count":3,"area":"deeprl"},{"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":"2406.03434","title":"Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling","created":"2024-06-05","cited_by_count":3,"area":"offlinerl"},{"id":"2512.13726","title":"Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commerce","created":"2025-12-13","cited_by_count":3,"area":"deeprl"},{"id":"2101.02553","title":"Off-Policy Evaluation of Slate Policies under Bayes Risk","created":"2021-01-05","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":"2204.10936","title":"Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion","created":"2022-04-22","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":"2209.08642","title":"Offline Evaluation of Reward-Optimizing Recommender Systems: The Case of Simulation","created":"2022-09-18","cited_by_count":2,"area":null},{"id":"2212.14580","title":"Heterogeneous Synthetic Learner for Panel Data","created":"2022-12-30","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":"2309.01120","title":"Double Clipping: Less-Biased Variance Reduction in Off-Policy Evaluation","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2506.13163","title":"Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2511.03051","title":"No-Human in the Loop: Agentic Evaluation at Scale for Recommendation","created":"2025-11-04","cited_by_count":2,"area":"agents"},{"id":"2512.03354","title":"Breaking Determinism: Stochastic Modeling for Reliable Off-Policy Evaluation in Ad Auctions","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2602.14914","title":"Additive Control Variates Dominate Self-Normalisation in Off-Policy Evaluation","created":"2026-02-16","cited_by_count":2,"area":null},{"id":"2109.03747","title":"Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values","created":"2021-09-08","cited_by_count":1,"area":null},{"id":"2210.09512","title":"Off-policy evaluation for learning-to-rank via interpolating the item-position model and the position-based model","created":"2022-10-15","cited_by_count":1,"area":null},{"id":"2308.09248","title":"Active and Passive Causal Inference Learning","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2409.15753","title":"Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2410.01822","title":"The Importance of Causality in Decision Making: A Perspective on Recommender Systems","created":"2024-09-16","cited_by_count":1,"area":null},{"id":"2506.03324","title":"Optimization of Epsilon-Greedy Exploration","created":"2025-06-03","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":"2603.18702","title":"Off-Policy Learning with Limited Supply","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.17693","title":"COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.29500","title":"Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2608.01204","title":"ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2110.14874","title":"Sayer: Using Implicit Feedback to Optimize System Policies","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2112.05812","title":"Edge-Compatible Reinforcement Learning for Recommendations","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2208.14980","title":"Inverse Propensity Score based offline estimator for deterministic ranking lists using position bias","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2211.01518","title":"Bayesian Counterfactual Mean Embeddings and Off-Policy Evaluation","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2302.02579","title":"Recommender Systems: A Primer","created":"2023-02-06","cited_by_count":0,"area":null},{"id":"2302.13505","title":"Multi-Action Dialog Policy Learning from Logged User Feedback","created":"2023-02-27","cited_by_count":0,"area":null},{"id":"2305.10528","title":"Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational Systems","created":"2023-05-17","cited_by_count":0,"area":null},{"id":"2307.15858","title":"Multi-output Headed Ensembles for Product Item Classification","created":"2023-07-29","cited_by_count":0,"area":null},{"id":"2309.08622","title":"Representation Learning in Low-rank Slate-based Recommender Systems","created":"2023-09-10","cited_by_count":0,"area":null},{"id":"2404.01830","title":"Doubly-Robust Off-Policy Evaluation with Estimated Logging Policy","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2505.00961","title":"DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects","created":"2025-05-02","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":"2507.09566","title":"Identifying Offline Metrics that Predict Online Impact: A Pragmatic Strategy for Real-World Recommender Systems","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2507.13491","title":"Model-free Reinforcement Learning for Model-based Control: Towards Safe, Interpretable and Sample-efficient Agents","created":"2025-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2603.09436","title":"From Weighting to Modeling: A Nonparametric Estimator for Off-Policy Evaluation","created":"2026-03-10","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":"2605.18509","title":"Offline Contextual Bandits in the Presence of New Actions","created":"2026-05-18","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}],"next_cursor":"100"}