{"total":80,"rows":[{"id":"2306.02552","title":"User Behavior Simulation with Large Language Model based Agents","created":"2023-06-05","cited_by_count":140,"area":"agents"},{"id":"2310.10108","title":"On Generative Agents in Recommendation","created":"2023-10-16","cited_by_count":90,"area":"agents"},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63,"area":"offlinerl"},{"id":"2102.11492","title":"DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning","created":"2021-02-23","cited_by_count":48,"area":"offlinerl"},{"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":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"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":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2103.08057","title":"RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems","created":"2021-03-14","cited_by_count":21,"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":"2201.12662","title":"Fair ranking: a critical review, challenges, and future directions","created":"2022-01-29","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":"2302.10897","title":"Learning to Simulate Daily Activities via Modeling Dynamic Human Needs","created":"2023-02-09","cited_by_count":20,"area":null},{"id":"2206.01474","title":"Offline Reinforcement Learning with Causal Structured World Models","created":"2022-06-03","cited_by_count":19,"area":"wm"},{"id":"2306.06563","title":"Provably Efficient Adversarial Imitation Learning with Unknown Transitions","created":"2023-06-11","cited_by_count":16,"area":"offlinerl"},{"id":"2102.05710","title":"Derivative-Free Reinforcement Learning: A Review","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2202.02468","title":"Rethinking ValueDice: Does It Really Improve Performance?","created":"2022-02-05","cited_by_count":15,"area":"offlinerl"},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2208.12483","title":"Dynamic Regret of Online Markov Decision Processes","created":"2022-08-26","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":"2310.05422","title":"Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning","created":"2023-10-09","cited_by_count":12,"area":"offlinerl"},{"id":"2304.07920","title":"Causal Decision Transformer for Recommender Systems via Offline Reinforcement Learning","created":"2023-04-17","cited_by_count":11,"area":"offlinerl"},{"id":"2402.00262","title":"Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspective","created":"2024-02-01","cited_by_count":11,"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":"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":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"area":"deeprl"},{"id":"2604.08362","title":"Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces","created":"2026-04-09","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":"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":"2211.03408","title":"RITA: Boost Driving Simulators with Realistic Interactive Traffic Flow","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"1909.03773","title":"Imitation Learning from Pixel-Level Demonstrations by HashReward","created":"2019-09-09","cited_by_count":6,"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":"2209.05530","title":"Model-based Reinforcement Learning with Multi-step Plan Value Estimation","created":"2022-09-12","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":"2105.14188","title":"We Know What You Want: An Advertising Strategy Recommender System for Online Advertising","created":"2021-05-25","cited_by_count":5,"area":null},{"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":"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":"2405.13362","title":"Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems","created":"2024-05-22","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":"2202.00805","title":"Context Uncertainty in Contextual Bandits with Applications to Recommender Systems","created":"2022-02-01","cited_by_count":4,"area":null},{"id":"2312.11214","title":"Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective","created":"2023-12-18","cited_by_count":4,"area":"offlinerl"},{"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":"2107.07693","title":"Imitate TheWorld: A Search Engine Simulation Platform","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2206.02000","title":"Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning","created":"2022-06-04","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":"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":"2209.04147","title":"Extending Open Bandit Pipeline to Simulate Industry Challenges","created":"2022-09-09","cited_by_count":2,"area":null},{"id":"2408.16032","title":"An Extremely Data-efficient and Generative LLM-based Reinforcement Learning Agent for Recommenders","created":"2024-08-28","cited_by_count":2,"area":"agents"},{"id":"2502.02327","title":"Policy-Guided Causal State Representation for Offline Reinforcement Learning Recommendation","created":"2025-02-04","cited_by_count":2,"area":"offlinerl"},{"id":"2503.19267","title":"NeoRL-2: Near Real-World Benchmarks for Offline Reinforcement Learning with Extended Realistic Scenarios","created":"2025-03-25","cited_by_count":2,"area":"offlinerl"},{"id":"2506.23090","title":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems","created":"2025-06-29","cited_by_count":2,"area":"offlinerl"},{"id":"2303.01297","title":"Creating Synthetic Datasets for Collaborative Filtering Recommender Systems using Generative Adversarial Networks","created":"2023-03-02","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":"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":"2309.01784","title":"INTAGS: Interactive Agent-Guided Simulation","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2310.16566","title":"Model-enhanced Contrastive Reinforcement Learning for Sequential Recommendation","created":"2023-10-25","cited_by_count":1,"area":"offlinerl"},{"id":"2407.13091","title":"On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems","created":"2024-07-18","cited_by_count":1,"area":"deeprl"},{"id":"2409.20055","title":"Neural Click Models for Recommender Systems","created":"2024-09-30","cited_by_count":1,"area":null},{"id":"2509.22807","title":"MTRec: Learning to Align with User Preferences via Mental Reward Models","created":"2025-09-26","cited_by_count":1,"area":"alignment"},{"id":"2510.12815","title":"Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation","created":"2025-10-09","cited_by_count":1,"area":"diffusion"},{"id":"2511.04541","title":"Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data","created":"2025-11-06","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":"2608.01204","title":"ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors","created":"2026-08-02","cited_by_count":1,"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":"2210.05662","title":"Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2304.10704","title":"Interactive System-wise Anomaly Detection","created":"2023-04-21","cited_by_count":0,"area":null},{"id":"2308.11924","title":"Diverse Policies Converge in Reward-free Markov Decision Processe","created":"2023-08-23","cited_by_count":0,"area":null},{"id":"2403.14593","title":"Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium Proof","created":"2024-03-21","cited_by_count":0,"area":"offlinerl"},{"id":"2409.12396","title":"ARTAI: An Evaluation Platform to Assess Societal Risk of Recommender Algorithms","created":"2024-09-19","cited_by_count":0,"area":null},{"id":"2410.07643","title":"On Reward Transferability in Adversarial Inverse Reinforcement Learning: Insights from Random Matrix Theory","created":"2024-10-10","cited_by_count":0,"area":"offlinerl"},{"id":"2501.12785","title":"On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration","created":"2025-01-22","cited_by_count":0,"area":"offlinerl"},{"id":"2504.04706","title":"AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2507.18756","title":"Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2601.22547","title":"PersonaAct: Simulating Short-Video Users with Personalized Agents for Counterfactual Filter Bubble Auditing","created":"2026-01-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}