{"total":90,"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":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2203.16582","title":"Factored Adaptation for Non-Stationary Reinforcement Learning","created":"2022-03-30","cited_by_count":30,"area":null},{"id":"2105.13623","title":"Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation","created":"2021-05-28","cited_by_count":28,"area":null},{"id":"2308.15651","title":"Ensuring User-side Fairness in Dynamic Recommender Systems","created":"2023-08-29","cited_by_count":27,"area":null},{"id":"2207.10307","title":"Knowledge-enhanced Black-box Attacks for Recommendations","created":"2022-07-21","cited_by_count":26,"area":null},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2208.04560","title":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","created":"2022-08-09","cited_by_count":22,"area":"offlinerl"},{"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":"2212.02779","title":"PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement","created":"2022-12-06","cited_by_count":21,"area":null},{"id":"2310.00678","title":"A General Offline Reinforcement Learning Framework for Interactive Recommendation","created":"2023-10-01","cited_by_count":18,"area":"offlinerl"},{"id":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17,"area":null},{"id":"2307.09943","title":"Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay","created":"2023-07-19","cited_by_count":17,"area":null},{"id":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"area":"offlinerl"},{"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":"2110.15097","title":"Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning","created":"2021-10-28","cited_by_count":14,"area":null},{"id":"2301.08632","title":"Generative Slate Recommendation with Reinforcement Learning","created":"2023-01-20","cited_by_count":13,"area":null},{"id":"2106.08414","title":"On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control","created":"2021-06-15","cited_by_count":12,"area":null},{"id":"2201.12332","title":"On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2106.01674","title":"JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu","created":"2021-06-03","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":"2108.09141","title":"Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation","created":"2021-08-20","cited_by_count":9,"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":"2202.03867","title":"Offline Reinforcement Learning for Mobile Notifications","created":"2022-02-04","cited_by_count":8,"area":"offlinerl"},{"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":"2202.08812","title":"Should I send this notification? Optimizing push notifications decision making by modeling the future","created":"2022-02-17","cited_by_count":6,"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":"2305.04832","title":"Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems","created":"2023-05-03","cited_by_count":5,"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":"2404.14961","title":"Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems","created":"2024-04-23","cited_by_count":5,"area":"deeprl"},{"id":"2104.02981","title":"Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation","created":"2021-04-07","cited_by_count":4,"area":"wm"},{"id":"2207.03029","title":"Multi-objective Optimization of Notifications Using Offline Reinforcement Learning","created":"2022-07-07","cited_by_count":4,"area":"offlinerl"},{"id":"2405.03082","title":"Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning","created":"2024-05-05","cited_by_count":4,"area":"deeprl"},{"id":"2407.13163","title":"ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems","created":"2024-07-18","cited_by_count":4,"area":"alignment"},{"id":"2503.12222","title":"Evaluation-Time Policy Switching for Offline Reinforcement Learning","created":"2025-03-15","cited_by_count":4,"area":"offlinerl"},{"id":"2510.01609","title":"AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence","created":"2025-10-02","cited_by_count":4,"area":"agents"},{"id":"2302.09248","title":"Machine Love","created":"2023-02-18","cited_by_count":3,"area":null},{"id":"2305.02605","title":"Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy","created":"2023-05-04","cited_by_count":3,"area":null},{"id":"2410.11833","title":"Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions","created":"2024-10-15","cited_by_count":3,"area":"deeprl"},{"id":"2505.16298","title":"Flow Matching based Sequential Recommender Model","created":"2025-05-22","cited_by_count":3,"area":"diffusion"},{"id":"2508.00201","title":"RecoMind: A Reinforcement Learning Framework for Optimizing In-Session User Satisfaction in Recommendation Systems","created":"2025-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2512.13726","title":"Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commerce","created":"2025-12-13","cited_by_count":3,"area":"deeprl"},{"id":"2603.08938","title":"AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2105.01620","title":"Data-Efficient Reinforcement Learning for Malaria Control","created":"2021-05-04","cited_by_count":2,"area":null},{"id":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2404.17589","title":"UnifiedRL: A Reinforcement Learning Algorithm Tailored for Multi-Task Fusion in Large-Scale Recommender Systems","created":"2024-04-19","cited_by_count":2,"area":"offlinerl"},{"id":"2405.01847","title":"A Model-based Multi-Agent Personalized Short-Video Recommender System","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2405.13238","title":"Dynamic User Interest Augmentation via Stream Clustering and Memory Networks in Large-Scale Recommender Systems","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2406.01611","title":"System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes","created":"2024-05-29","cited_by_count":2,"area":null},{"id":"2504.07307","title":"Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2106.07854","title":"Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning","created":"2021-06-15","cited_by_count":1,"area":null},{"id":"2209.05042","title":"On the Optimization Landscape of Dynamic Output Feedback: A Case Study for Linear Quadratic Regulator","created":"2022-09-12","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":"2308.06965","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":"2406.04553","title":"Better Late Than Never: Formulating and Benchmarking Recommendation Editing","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2409.07416","title":"Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendation","created":"2024-09-11","cited_by_count":1,"area":"deeprl"},{"id":"2409.14872","title":"FedSlate:A Federated Deep Reinforcement Learning Recommender System","created":"2024-09-23","cited_by_count":1,"area":"deeprl"},{"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":"2607.14192","title":"Long-term User Engagement Optimization through Model-agnostic Downstream Rewards Learning","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2105.02589","title":"Bandit based centralized matching in two-sided markets for peer to peer lending","created":"2021-05-06","cited_by_count":0,"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":"2108.01455","title":"FEBR: Expert-Based Recommendation Framework for beneficial and personalized content","created":"2021-07-17","cited_by_count":0,"area":null},{"id":"2108.02572","title":"SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.02725","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2109.05778","title":"Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation","created":"2021-09-13","cited_by_count":0,"area":null},{"id":"2202.02830","title":"Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors","created":"2022-02-06","cited_by_count":0,"area":null},{"id":"2203.11011","title":"Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2205.08335","title":"Explanation-Guided Fairness Testing through Genetic Algorithm","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2207.14648","title":"Using Graph Neural Networks for Program Termination","created":"2022-07-28","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":"2303.09664","title":"Tribe or Not? Critical Inspection of Group Differences Using TribalGram","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2309.01453","title":"Interactive Graph Convolutional Filtering","created":"2023-09-04","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":"2401.11632","title":"What Are We Optimizing For? A Human-centric Evaluation of Deep Learning-based Movie Recommenders","created":"2024-01-21","cited_by_count":0,"area":null},{"id":"2405.04026","title":"Federated Control in Markov Decision Processes","created":"2024-05-07","cited_by_count":0,"area":null},{"id":"2408.00997","title":"A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments","created":"2024-08-02","cited_by_count":0,"area":"deeprl"},{"id":"2409.11678","title":"EnhancedRL: An Enhanced-State Reinforcement Learning Algorithm for Multi-Task Fusion in Recommender Systems","created":"2024-09-18","cited_by_count":0,"area":"deeprl"},{"id":"2412.10381","title":"Supervised Learning-enhanced Multi-Group Actor Critic for Live Stream Allocation in Feed","created":"2024-11-28","cited_by_count":0,"area":"deeprl"},{"id":"2504.21383","title":"FAST-Q: Fast-track Exploration with Adversarially Balanced State Representations for Counterfactual Action Estimation in Offline Reinforcement Learning","created":"2025-04-30","cited_by_count":0,"area":"offlinerl"},{"id":"2507.21397","title":"Enabling Pareto-Stationarity Exploration in Multi-Objective Reinforcement Learning: A Multi-Objective Weighted-Chebyshev Actor-Critic Approach","created":"2025-07-29","cited_by_count":0,"area":"deeprl"},{"id":"2512.10963","title":"Emotion-Driven Personalized Recommendation for AI-Generated Content Using Multi-Modal Sentiment and Intent Analysis","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2602.15752","title":"Beyond Match Maximization and Fairness: Retention-Optimized Two-Sided Matching","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.14936","title":"Bridging the Intention-Expression Gap: Aligning Multi-Dimensional Preferences via Hierarchical Relevance Feedback in Text-to-Image Diffusion","created":"2026-03-16","cited_by_count":0,"area":"diffusion"},{"id":"2608.01949","title":"A Self-Triggered Agentic Push Recommendation System","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.04421","title":"Generative Optimization for Incentivized Advertising with Global Level Constraints","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.06186","title":"Spectral Prioritized Sweeping in Nonstationary Reinforcement Learning","created":"2026-09-05","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}