{"total":188,"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":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2306.02552","title":"User Behavior Simulation with Large Language Model based Agents","created":"2023-06-05","cited_by_count":140,"area":"agents"},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2310.10108","title":"On Generative Agents in Recommendation","created":"2023-10-16","cited_by_count":90,"area":"agents"},{"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":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2110.14770","title":"TRAIL: Near-Optimal Imitation Learning with Suboptimal Data","created":"2021-10-27","cited_by_count":39,"area":"offlinerl"},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2405.17713","title":"AI Alignment with Changing and Influenceable Reward Functions","created":"2024-05-28","cited_by_count":33,"area":"alignment"},{"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":"2502.14662","title":"iAgent: LLM Agent as a Shield between User and Recommender Systems","created":"2025-02-20","cited_by_count":23,"area":"agents"},{"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":"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":"2212.04607","title":"Confidence-Conditioned Value Functions for Offline Reinforcement Learning","created":"2022-12-08","cited_by_count":20,"area":"offlinerl"},{"id":"2310.18608","title":"Embedding in Recommender Systems: A Survey","created":"2023-10-28","cited_by_count":20,"area":null},{"id":"2602.10226","title":"Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents","created":"2026-02-10","cited_by_count":19,"area":"agents"},{"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":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","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":"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":"2401.14758","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","created":"2024-01-26","cited_by_count":14,"area":"deeprl"},{"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":"2308.11336","title":"On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems","created":"2023-08-22","cited_by_count":10,"area":"offlinerl"},{"id":"2310.02505","title":"Learning to Reach Goals via Diffusion","created":"2023-10-04","cited_by_count":10,"area":"diffusion"},{"id":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"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":"2411.05234","title":"Performative Reinforcement Learning with Linear Markov Decision Process","created":"2024-11-07","cited_by_count":9,"area":"deeprl"},{"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":"2310.20663","title":"Offline RL with Observation Histories: Analyzing and Improving Sample Complexity","created":"2023-10-31","cited_by_count":7,"area":"offlinerl"},{"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":"2405.12094","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","created":"2024-05-20","cited_by_count":7,"area":"ssm"},{"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":"2401.01084","title":"Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance Reduction","created":"2024-01-02","cited_by_count":6,"area":"deeprl"},{"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":"2506.19235","title":"RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1","created":"2025-06-24","cited_by_count":6,"area":"lr"},{"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":"2408.12136","title":"Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samples","created":"2024-08-22","cited_by_count":5,"area":"offlinerl"},{"id":"2505.15143","title":"Filtering Learning Histories Enhances In-Context Reinforcement Learning","created":"2025-05-21","cited_by_count":5,"area":"deeprl"},{"id":"2505.16429","title":"Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems","created":"2025-05-22","cited_by_count":5,"area":"agents"},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"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":"2403.07916","title":"Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization","created":"2024-02-27","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":"2509.14218","title":"Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2510.16132","title":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","created":"2025-10-17","cited_by_count":4,"area":"deeprl"},{"id":"2102.05612","title":"Personalization for Web-based Services using Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":3,"area":"offlinerl"},{"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":"2306.08364","title":"Provably Efficient Offline Reinforcement Learning with Perturbed Data Sources","created":"2023-06-14","cited_by_count":3,"area":"offlinerl"},{"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":"2403.17634","title":"Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning based Recommendation Systems","created":"2024-03-26","cited_by_count":3,"area":"offlinerl"},{"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":"2501.10548","title":"Diffusion Models in Recommendation Systems: A Survey","created":"2025-01-17","cited_by_count":3,"area":"diffusion"},{"id":"2506.21044","title":"Efficient Skill Discovery via Regret-Aware Optimization","created":"2025-06-26","cited_by_count":3,"area":"deeprl"},{"id":"2507.00518","title":"Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling","created":"2025-07-01","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":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2303.02265","title":"Learning to Influence Human Behavior with Offline Reinforcement Learning","created":"2023-03-03","cited_by_count":2,"area":"offlinerl"},{"id":"2305.01147","title":"Ripple Knowledge Graph Convolutional Networks For Recommendation Systems","created":"2023-05-02","cited_by_count":2,"area":null}],"next_cursor":"100"}