{"total":35,"rows":[{"id":"2503.24289","title":"Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning","created":"2025-03-31","cited_by_count":33,"area":null},{"id":"2109.04200","title":"Double-Scale Self-Supervised Hypergraph Learning for Group Recommendation","created":"2021-09-09","cited_by_count":32,"area":null},{"id":"2108.11333","title":"Lightweight Self-Attentive Sequential Recommendation","created":"2021-08-25","cited_by_count":22,"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":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2306.04039","title":"Revisiting Neural Retrieval on Accelerators","created":"2023-06-06","cited_by_count":14,"area":null},{"id":"2109.03150","title":"Recommendation Fairness: From Static to Dynamic","created":"2021-09-05","cited_by_count":10,"area":null},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2111.03474","title":"Supervised Advantage Actor-Critic for Recommender Systems","created":"2021-11-05","cited_by_count":8,"area":null},{"id":"2302.03561","title":"Optimizing Audio Recommendations for the Long-Term: A Reinforcement Learning Perspective","created":"2023-02-07","cited_by_count":8,"area":null},{"id":"2504.10507","title":"PinRec: Unified Generative Retrieval for Pinterest Recommender Systems","created":"2025-04-09","cited_by_count":8,"area":null},{"id":"2305.13747","title":"Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learning","created":"2023-05-23","cited_by_count":6,"area":null},{"id":"2312.14447","title":"On the Effectiveness of Unlearning in Session-Based Recommendation","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2108.01442","title":"Sequence Adaptation via Reinforcement Learning in Recommender Systems","created":"2021-07-31","cited_by_count":1,"area":null},{"id":"2306.01476","title":"Hierarchical Reinforcement Learning for Modeling User Novelty-Seeking Intent in Recommender Systems","created":"2023-06-02","cited_by_count":1,"area":null},{"id":"2308.13246","title":"Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems","created":"2023-08-25","cited_by_count":1,"area":null},{"id":"2403.20250","title":"Optimal Policy Learning with Observational Data in Multi-Action Scenarios: Estimation, Risk Preference, and Potential Failures","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2410.12086","title":"Comparative Performance of Collaborative Bandit Algorithms: Effect of Sparsity and Exploration Intensity","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2412.08911","title":"Goal-Conditioned Supervised Learning for Multi-Objective Recommendation","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2106.10305","title":"Multi-Task Learning for User Engagement and Adoption in Live Video Streaming Events","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2110.10205","title":"MultiHead MultiModal Deep Interest Recommendation Network","created":"2021-10-19","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":"2211.06370","title":"Intent-aware Multi-source Contrastive Alignment for Tag-enhanced Recommendation","created":"2022-11-11","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":"2305.18820","title":"Robust Reinforcement Learning Objectives for Sequential Recommender Systems","created":"2023-05-30","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":"2309.08622","title":"Representation Learning in Low-rank Slate-based Recommender Systems","created":"2023-09-10","cited_by_count":0,"area":null},{"id":"2310.19519","title":"A General Neural Causal Model for Interactive Recommendation","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2311.02938","title":"Contrastive Multi-Level Graph Neural Networks for Session-based Recommendation","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2403.04875","title":"Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning","created":"2024-03-07","cited_by_count":0,"area":null},{"id":"2409.08733","title":"Multi-intent Aware Contrastive Learning for Sequential Recommendation","created":"2024-09-13","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},{"id":"2511.16248","title":"Revisiting Fairness-aware Interactive Recommendation: Item Lifecycle as a Control Knob","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2603.03094","title":"Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2605.24155","title":"An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation","created":"2026-05-22","cited_by_count":0,"area":null}],"next_cursor":null}