{"total":19,"rows":[{"id":"2106.06713","title":"AutoLoss: Automated Loss Function Search in Recommendations","created":"2021-06-12","cited_by_count":31,"area":null},{"id":"2504.14587","title":"Generative Auto-Bidding with Value-Guided Explorations","created":"2025-04-20","cited_by_count":23,"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":"2109.04353","title":"Cross DQN: Cross Deep Q Network for Ads Allocation in Feed","created":"2021-09-09","cited_by_count":19,"area":null},{"id":"2101.02342","title":"User Response Prediction in Online Advertising","created":"2021-01-07","cited_by_count":15,"area":null},{"id":"2203.13423","title":"Modeling Attrition in Recommender Systems with Departing Bandits","created":"2022-03-25","cited_by_count":11,"area":null},{"id":"2109.03150","title":"Recommendation Fairness: From Static to Dynamic","created":"2021-09-05","cited_by_count":10,"area":null},{"id":"2206.02620","title":"ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor","created":"2022-06-01","cited_by_count":10,"area":null},{"id":"2204.00377","title":"Deep Page-Level Interest Network in Reinforcement Learning for Ads Allocation","created":"2022-04-01","cited_by_count":8,"area":null},{"id":"2205.15759","title":"Hierarchically Constrained Adaptive Ad Exposure in Feeds","created":"2022-05-31","cited_by_count":6,"area":null},{"id":"2204.11589","title":"Hybrid Transfer in Deep Reinforcement Learning for Ads Allocation","created":"2022-04-02","cited_by_count":5,"area":null},{"id":"2204.00888","title":"Learning List-wise Representation in Reinforcement Learning for Ads Allocation with Multiple Auxiliary Tasks","created":"2022-04-02","cited_by_count":3,"area":null},{"id":"2401.01369","title":"RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems","created":"2023-12-27","cited_by_count":3,"area":null},{"id":"2304.09087","title":"MDDL: A Framework for Reinforcement Learning-based Position Allocation in Multi-Channel Feed","created":"2023-04-17","cited_by_count":1,"area":null},{"id":"2210.08338","title":"Fair Effect Attribution in Parallel Online Experiments","created":"2022-10-15","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":"2512.24325","title":"MaRCA: Multi-Agent Reinforcement Learning for Dynamic Computation Allocation in Large-Scale Recommender Systems","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2603.22231","title":"One Model, Two Markets: Bid-Aware Generative Recommendation","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2606.09623","title":"Constrained user-item allocation for e-commerce marketing campaigns","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}