{"total":24,"rows":[{"id":"2109.01165","title":"Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction","created":"2021-09-01","cited_by_count":37,"area":null},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2109.02444","title":"Top-N Recommendation with Counterfactual User Preference Simulation","created":"2021-09-02","cited_by_count":21,"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":"2101.04526","title":"Measuring Recommender System Effects with Simulated Users","created":"2021-01-12","cited_by_count":20,"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":"2106.00517","title":"Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment","created":"2021-06-01","cited_by_count":12,"area":null},{"id":"2108.09141","title":"Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation","created":"2021-08-20","cited_by_count":9,"area":null},{"id":"2205.10759","title":"Sequential/Session-based Recommendations: Challenges, Approaches, Applications and Opportunities","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2310.07745","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2110.11073","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2301.02807","title":"RLAS-BIABC: A Reinforcement Learning-Based Answer Selection Using the BERT Model Boosted by an Improved ABC Algorithm","created":"2023-01-07","cited_by_count":3,"area":null},{"id":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2408.04251","title":"Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2111.03340","title":"FINN.no Slates Dataset: A new Sequential Dataset Logging Interactions, allViewed Items and Click Responses/No-Click for Recommender Systems Research","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2202.00245","title":"Sequential Search with Off-Policy Reinforcement Learning","created":"2022-02-01","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":"2511.14768","title":"Causally-Informed Reinforcement Learning for Adaptive Emotion-Aware Social Media Recommendation","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2102.00333","title":"Deep Reinforcement Learning-Based Product Recommender for Online Advertising","created":"2021-01-30","cited_by_count":0,"area":null},{"id":"2110.15089","title":"D2RLIR : an improved and diversified ranking function in interactive recommendation systems based on deep reinforcement learning","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2210.15451","title":"Fine-Grained Session Recommendations in E-commerce using Deep Reinforcement Learning","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2310.04483","title":"Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2402.10381","title":"UMAIR-FPS: User-aware Multi-modal Animation Illustration Recommendation Fusion with Painting Style","created":"2024-02-16","cited_by_count":0,"area":null}],"next_cursor":null}