{"total":22,"rows":[{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2111.15139","title":"Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures","created":"2021-11-30","cited_by_count":19,"area":null},{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2302.01724","title":"Reinforcing User Retention in a Billion Scale Short Video Recommender System","created":"2023-02-03","cited_by_count":15,"area":null},{"id":"2111.10476","title":"Towards Return Parity in Markov Decision Processes","created":"2021-11-19","cited_by_count":13,"area":null},{"id":"2303.10227","title":"Conversational Tree Search: A New Hybrid Dialog Task","created":"2023-03-17","cited_by_count":7,"area":null},{"id":"2105.00822","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2410.09580","title":"SAPIENT: Mastering Multi-turn Conversational Recommendation with Strategic Planning and Monte Carlo Tree Search","created":"2024-10-12","cited_by_count":6,"area":null},{"id":"2310.03984","title":"AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2111.12262","title":"Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation","created":"2021-11-24","cited_by_count":4,"area":null},{"id":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2108.05618","title":"Conditional Sequential Slate Optimization","created":"2021-08-12","cited_by_count":1,"area":null},{"id":"2303.01042","title":"Reinforcement Learning Guided Multi-Objective Exam Paper Generation","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2308.06965","title":"AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2409.13175","title":"RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems","created":"2024-09-20","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":"2112.00973","title":"Adversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systems","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2202.09508","title":"Who Are the Best Adopters? User Selection Model for Free Trial Item Promotion","created":"2022-02-19","cited_by_count":0,"area":null},{"id":"2308.11137","title":"Towards Validating Long-Term User Feedbacks in Interactive Recommendation Systems","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2507.23459","title":"KLAN: Kuaishou Landing-page Adaptive Navigator","created":"2025-07-31","cited_by_count":0,"area":null}],"next_cursor":null}