{"total":31,"rows":[{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2106.06713","title":"AutoLoss: Automated Loss Function Search in Recommendations","created":"2021-06-12","cited_by_count":31,"area":null},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"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":"2302.13137","title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","created":"2023-02-25","cited_by_count":15,"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":"2401.01656","title":"Deep Automated Mechanism Design for Integrating Ad Auction and Allocation in Feed","created":"2024-01-03","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":"2101.07312","title":"Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2402.00390","title":"DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems","created":"2024-02-01","cited_by_count":4,"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":"2308.05471","title":"Provably Efficient Algorithm for Nonstationary Low-Rank MDPs","created":"2023-08-10","cited_by_count":2,"area":null},{"id":"2410.12799","title":"Ads Supply Personalization via Doubly Robust Learning","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2202.00245","title":"Sequential Search with Off-Policy Reinforcement Learning","created":"2022-02-01","cited_by_count":1,"area":null},{"id":"2301.03043","title":"XDQN: Inherently Interpretable DQN through Mimicking","created":"2023-01-08","cited_by_count":1,"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":"2308.06965","title":"AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation","created":"2023-08-14","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":"2312.14129","title":"WellFactor: Patient Profiling using Integrative Embedding of Healthcare Data","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2502.17693","title":"Predictive Response Optimization: Using Reinforcement Learning to Fight Online Social Network Abuse","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2503.12801","title":"BLIA: Detect model memorization in binary classification model through passive Label Inference attack","created":"2025-03-17","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":"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":"2604.24073","title":"FreeScale: Distributed Training for Sequence Recommendation Models with Minimal Scaling Cost","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.16344","title":"A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems","created":"2026-05-08","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}