{"total":64,"rows":[{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242,"area":"agents"},{"id":"2110.01548","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","created":"2021-10-04","cited_by_count":302,"area":"offlinerl"},{"id":"2306.02552","title":"User Behavior Simulation with Large Language Model based Agents","created":"2023-06-05","cited_by_count":140,"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":"2404.00579","title":"A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)","created":"2024-03-31","cited_by_count":58,"area":null},{"id":"2406.07089","title":"RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent","created":"2024-06-11","cited_by_count":49,"area":"mllm"},{"id":"2411.02306","title":"On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback","created":"2024-11-04","cited_by_count":47,"area":"alignment"},{"id":"2407.14962","title":"Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives","created":"2024-07-20","cited_by_count":30,"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":"2406.06606","title":"Prototypical Reward Network for Data-Efficient RLHF","created":"2024-06-06","cited_by_count":22,"area":"alignment"},{"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":"2310.00678","title":"A General Offline Reinforcement Learning Framework for Interactive Recommendation","created":"2023-10-01","cited_by_count":18,"area":"offlinerl"},{"id":"2202.02468","title":"Rethinking ValueDice: Does It Really Improve Performance?","created":"2022-02-05","cited_by_count":15,"area":"offlinerl"},{"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":"2206.04890","title":"Adversarial Counterfactual Environment Model Learning","created":"2022-06-10","cited_by_count":12,"area":null},{"id":"2501.00083","title":"AI Agent for Education: von Neumann Multi-Agent System Framework","created":"2024-12-30","cited_by_count":12,"area":"agents"},{"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":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2111.03474","title":"Supervised Advantage Actor-Critic for Recommender Systems","created":"2021-11-05","cited_by_count":8,"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":"2303.02073","title":"How To Guide Your Learner: Imitation Learning with Active Adaptive Expert Involvement","created":"2023-03-03","cited_by_count":8,"area":"offlinerl"},{"id":"2105.00822","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2205.11788","title":"Meta Policy Learning for Cold-Start Conversational Recommendation","created":"2022-05-24","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":"2411.00610","title":"Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation","created":"2024-11-01","cited_by_count":6,"area":"offlinerl"},{"id":"2110.11073","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2206.11338","title":"Synthetic Data-Based Simulators for Recommender Systems: A Survey","created":"2022-06-22","cited_by_count":5,"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":"2311.01331","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","created":"2023-11-02","cited_by_count":5,"area":null},{"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":"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":"2210.09496","title":"CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations","created":"2022-10-18","cited_by_count":4,"area":null},{"id":"2311.03488","title":"Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems","created":"2023-11-06","cited_by_count":4,"area":"diffusion"},{"id":"2503.19752","title":"Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation","created":"2025-03-25","cited_by_count":4,"area":"agents"},{"id":"2601.04554","title":"Exploring Recommender System Evaluation: A Multi-Modal User Agent Framework for A/B Testing","created":"2026-01-08","cited_by_count":4,"area":"agents"},{"id":"2110.03276","title":"Inferring Substitutable and Complementary Products with Knowledge-Aware Path Reasoning based on Dynamic Policy Network","created":"2021-10-07","cited_by_count":3,"area":null},{"id":"2311.01329","title":"A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories","created":"2023-11-02","cited_by_count":3,"area":null},{"id":"2312.15965","title":"Efficient Reinforcement Learning via Decoupling Exploration and Utilization","created":"2023-12-26","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":"2302.09875","title":"Backstepping Temporal Difference Learning","created":"2023-02-20","cited_by_count":2,"area":null},{"id":"2302.10567","title":"Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2405.03967","title":"SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems","created":"2024-05-07","cited_by_count":2,"area":"deeprl"},{"id":"2412.00797","title":"Online Poisoning Attack Against Reinforcement Learning under Black-box Environments","created":"2024-12-01","cited_by_count":2,"area":"deeprl"},{"id":"2209.06128","title":"A Scalable Recommendation Engine for New Users and Items","created":"2022-09-06","cited_by_count":1,"area":null},{"id":"2305.14103","title":"Simulating News Recommendation Ecosystem for Fun and Profit","created":"2023-05-23","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":"2308.13246","title":"Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems","created":"2023-08-25","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":"2605.01778","title":"Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms","created":"2026-05-03","cited_by_count":1,"area":"offlinerl"},{"id":"2102.00333","title":"Deep Reinforcement Learning-Based Product Recommender for Online Advertising","created":"2021-01-30","cited_by_count":0,"area":null},{"id":"2107.01326","title":"SHORING: Design Provable Conditional High-Order Interaction Network via Symbolic Testing","created":"2021-07-03","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":"2201.09644","title":"Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models","created":"2022-01-24","cited_by_count":0,"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":"2206.03555","title":"A generative recommender system with GMM prior for cancer drug generation and sensitivity prediction","created":"2022-06-07","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":"2310.19519","title":"A General Neural Causal Model for Interactive Recommendation","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2310.19536","title":"Adversarial Batch Inverse Reinforcement Learning: Learn to Reward from Imperfect Demonstration for Interactive Recommendation","created":"2023-10-30","cited_by_count":0,"area":"offlinerl"},{"id":"2503.02311","title":"Target Return Optimizer for Multi-Game Decision Transformer","created":"2025-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2603.05440","title":"Latent Wasserstein Adversarial Imitation Learning","created":"2026-03-05","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}