{"total":21,"rows":[{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"id":"2110.14770","title":"TRAIL: Near-Optimal Imitation Learning with Suboptimal Data","created":"2021-10-27","cited_by_count":39,"area":"offlinerl"},{"id":"2208.04560","title":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","created":"2022-08-09","cited_by_count":22,"area":"offlinerl"},{"id":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"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":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"id":"2310.20663","title":"Offline RL with Observation Histories: Analyzing and Improving Sample Complexity","created":"2023-10-31","cited_by_count":7,"area":"offlinerl"},{"id":"2408.12136","title":"Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samples","created":"2024-08-22","cited_by_count":5,"area":"offlinerl"},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"id":"2102.05612","title":"Personalization for Web-based Services using Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":3,"area":"offlinerl"},{"id":"2306.08364","title":"Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources","created":"2023-06-14","cited_by_count":3,"area":"offlinerl"},{"id":"2403.17634","title":"Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning based Recommendation Systems","created":"2024-03-26","cited_by_count":3,"area":"offlinerl"},{"id":"2303.02265","title":"Learning to Influence Human Behavior with Offline Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":"offlinerl"},{"id":"2502.02327","title":"Policy-Guided Causal State Representation for Offline Reinforcement Learning Recommendation","created":"2025-02-04","cited_by_count":2,"area":"offlinerl"},{"id":"2506.23090","title":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems","created":"2025-06-29","cited_by_count":2,"area":"offlinerl"},{"id":"2301.01298","title":"Contextual Conservative Q-Learning for Offline Reinforcement Learning","created":"2023-01-03","cited_by_count":1,"area":"offlinerl"},{"id":"2502.11480","title":"Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective","created":"2025-02-17","cited_by_count":1,"area":"offlinerl"},{"id":"2503.02311","title":"Target Return Optimizer for Multi-Game Decision Transformer","created":"2025-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2602.17312","title":"LexiSafe: Offline Safe Reinforcement Learning with Lexicographic Safety-Reward Hierarchy","created":"2026-02-19","cited_by_count":0,"area":"offlinerl"},{"id":"2606.09115","title":"Counterfactual Transport Flows for Offline Conservative Trajectory Refinement","created":"2026-06-08","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}