{"total":114,"rows":[{"id":"2307.02046","title":"Recommender Systems in the Era of Large Language Models (LLMs)","created":"2023-07-05","cited_by_count":189,"area":null},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"id":"2209.15090","title":"Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments","created":"2022-09-29","cited_by_count":60,"area":null},{"id":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2202.06385","title":"Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost","created":"2022-02-13","cited_by_count":32,"area":null},{"id":"2209.06257","title":"A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledge","created":"2022-09-13","cited_by_count":31,"area":null},{"id":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2205.13619","title":"Fairness in Recommendation: Foundations, Methods and Applications","created":"2022-05-26","cited_by_count":27,"area":null},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2205.13026","title":"Preference Dynamics Under Personalized Recommendations","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2109.04083","title":"User Tampering in Reinforcement Learning Recommender Systems","created":"2021-09-09","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":"2305.19562","title":"Replicability in Reinforcement Learning","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","cited_by_count":20,"area":null},{"id":"2310.18608","title":"Embedding in Recommender Systems: A Survey","created":"2023-10-28","cited_by_count":20,"area":null},{"id":"2311.09018","title":"On the Foundation of Distributionally Robust Reinforcement Learning","created":"2023-11-15","cited_by_count":18,"area":null},{"id":"2212.04680","title":"Near-Optimal Differentially Private Reinforcement Learning","created":"2022-12-09","cited_by_count":16,"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":"2112.11921","title":"Variational Quantum Soft Actor-Critic","created":"2021-12-20","cited_by_count":15,"area":null},{"id":"2203.10591","title":"Policy Gradients using Variational Quantum Circuits","created":"2022-03-20","cited_by_count":15,"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":"2302.06834","title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","created":"2023-02-14","cited_by_count":15,"area":null},{"id":"2202.13446","title":"The Unfairness of Popularity Bias in Book Recommendation","created":"2022-02-27","cited_by_count":14,"area":null},{"id":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14,"area":null},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2210.00701","title":"Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2403.07939","title":"Dynamic Policy-Driven Adaptive Multi-Instance Learning for Whole Slide Image Classification","created":"2024-03-09","cited_by_count":12,"area":null},{"id":"2302.02061","title":"Reinforcement Learning with History-Dependent Dynamic Contexts","created":"2023-02-04","cited_by_count":11,"area":null},{"id":"2302.06064","title":"Provably Safe Reinforcement Learning with Step-wise Violation Constraints","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2406.01631","title":"SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems","created":"2024-06-01","cited_by_count":11,"area":null},{"id":"2210.13623","title":"Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2205.14842","title":"Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning","created":"2022-05-30","cited_by_count":9,"area":null},{"id":"2302.12456","title":"Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs","created":"2023-02-24","cited_by_count":9,"area":null},{"id":"2309.15293","title":"Maximum diffusion reinforcement learning","created":"2023-09-26","cited_by_count":9,"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":"2111.10625","title":"Explainable Biomedical Recommendations via Reinforcement Learning Reasoning on Knowledge Graphs","created":"2021-11-20","cited_by_count":7,"area":null},{"id":"2312.08751","title":"Improve Robustness of Reinforcement Learning against Observation Perturbations via $l_\\infty$ Lipschitz Policy Networks","created":"2023-12-14","cited_by_count":7,"area":null},{"id":"2406.05255","title":"Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers","created":"2024-06-07","cited_by_count":7,"area":null},{"id":"2212.06564","title":"Prescriptive Process Monitoring in Intelligent Process Automation with Chatbot Orchestration","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2305.16209","title":"C-MCTS: Safe Planning with Monte Carlo Tree Search","created":"2023-05-25","cited_by_count":6,"area":null},{"id":"2406.16782","title":"Confidence Aware Inverse Constrained Reinforcement Learning","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2502.04028","title":"Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2305.10681","title":"Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning","created":"2023-05-18","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":"2207.12217","title":"Finite-Time Analysis of Asynchronous Q-learning under Diminishing Step-Size from Control-Theoretic View","created":"2022-07-25","cited_by_count":4,"area":null},{"id":"2210.05355","title":"Multi-User Reinforcement Learning with Low Rank Rewards","created":"2022-10-11","cited_by_count":4,"area":null},{"id":"2306.01121","title":"Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2310.09123","title":"Automatic Music Playlist Generation via Simulation-based Reinforcement Learning","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2509.14218","title":"Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2103.08458","title":"Deep Dynamic Neural Network to trade-off between Accuracy and Diversity in a News Recommender System","created":"2021-03-15","cited_by_count":3,"area":null},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","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":"2309.02669","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2309.04707","title":"Advantage Actor-Critic with Reasoner: Explaining the Agent's Behavior from an Exploratory Perspective","created":"2023-09-09","cited_by_count":3,"area":null},{"id":"2406.06475","title":"Survey for Landing Generative AI in Social and E-commerce Recsys -- the Industry Perspectives","created":"2024-06-10","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":"2305.01147","title":"Ripple Knowledge Graph Convolutional Networks For Recommendation Systems","created":"2023-05-02","cited_by_count":2,"area":null},{"id":"2305.09330","title":"Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluation","created":"2023-05-16","cited_by_count":2,"area":null},{"id":"2402.06388","title":"Convergence of a L2 regularized Policy Gradient Algorithm for the Multi Armed Bandit","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2403.00832","title":"Explainable Session-based Recommendation via Path Reasoning","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2511.18013","title":"Save, Revisit, Retain: A Scalable Framework for Enhancing User Retention in Large-Scale Recommender Systems","created":"2025-11-22","cited_by_count":2,"area":null},{"id":"2105.04888","title":"Hierarchical RNNs-Based Transformers MADDPG for Mixed Cooperative-Competitive Environments","created":"2021-05-11","cited_by_count":1,"area":null},{"id":"2106.07203","title":"Online Sub-Sampling for Reinforcement Learning with General Function Approximation","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2201.07203","title":"Emergent Instabilities in Algorithmic Feedback Loops","created":"2022-01-18","cited_by_count":1,"area":null},{"id":"2207.03091","title":"Online SuBmodular + SuPermodular (BP) Maximization with Bandit Feedback","created":"2022-07-07","cited_by_count":1,"area":null},{"id":"2209.03596","title":"An Empirical Evaluation of Posterior Sampling for Constrained Reinforcement Learning","created":"2022-09-08","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":"2308.07857","title":"Impression-Aware Recommender Systems","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2308.08650","title":"AdaptEx: A Self-Service Contextual Bandit Platform","created":"2023-08-08","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":"2308.16126","title":"CorrEmbed: Evaluating Pre-trained Model Image Similarity Efficacy with a Novel Metric","created":"2023-08-30","cited_by_count":1,"area":null},{"id":"2404.10876","title":"Course Recommender Systems Need to Consider the Job Market","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2407.04534","title":"Introducing 'Inside' Out of Distribution","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2409.13175","title":"RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2409.20055","title":"Neural Click Models for Recommender Systems","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2410.01822","title":"The Importance of Causality in Decision Making: A Perspective on Recommender Systems","created":"2024-09-16","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":"2506.10133","title":"Statistical Guarantees for Offline Domain Randomization","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2509.18186","title":"An Outcome-Based Educational Recommender System","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2606.24042","title":"Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2203.10629","title":"Explicit User Manipulation in Reinforcement Learning Based Recommender Systems","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2204.04892","title":"JORLDY: a fully customizable open source framework for reinforcement learning","created":"2022-04-11","cited_by_count":0,"area":null},{"id":"2205.05393","title":"CVTT: Cross-Validation Through Time","created":"2022-05-11","cited_by_count":0,"area":null},{"id":"2210.10638","title":"Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning","created":"2022-10-06","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":"2211.06365","title":"Situating Recommender Systems in Practice: Towards Inductive Learning and Incremental Updates","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":"2303.05648","title":"Pacos: Modeling Users' Interpretable and Context-Dependent Choices in Preference Reversals","created":"2023-03-10","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":"2306.15913","title":"DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spaces","created":"2023-06-28","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":"2309.15737","title":"Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2310.17915","title":"Lifting the Veil: Unlocking the Power of Depth in Q-learning","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2401.06683","title":"DQNC2S: DQN-based Cross-stream Crisis event Summarizer","created":"2024-01-12","cited_by_count":0,"area":null}],"next_cursor":"100"}