{"total":182,"rows":[{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2205.04507","title":"PinnerFormer: Sequence Modeling for User Representation at Pinterest","created":"2022-05-09","cited_by_count":57,"area":null},{"id":"2105.08318","title":"Zero-Shot Recommender Systems","created":"2021-05-18","cited_by_count":46,"area":null},{"id":"2401.06081","title":"Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint","created":"2024-01-11","cited_by_count":39,"area":null},{"id":"2103.14077","title":"Nearly Horizon-Free Offline Reinforcement Learning","created":"2021-03-25","cited_by_count":36,"area":"offlinerl"},{"id":"2206.13102","title":"Modeling Content Creator Incentives on Algorithm-Curated Platforms","created":"2022-06-27","cited_by_count":35,"area":null},{"id":"2510.07784","title":"PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations","created":"2025-10-09","cited_by_count":30,"area":null},{"id":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","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":"2205.13026","title":"Preference Dynamics Under Personalized Recommendations","created":"2022-05-25","cited_by_count":25,"area":null},{"id":"2110.04156","title":"Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters","created":"2021-10-08","cited_by_count":24,"area":"offlinerl"},{"id":"2305.15498","title":"Large Language Models for User Interest Journeys","created":"2023-05-24","cited_by_count":24,"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":"2101.04526","title":"Measuring Recommender System Effects with Simulated Users","created":"2021-01-12","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":"2310.00678","title":"A General Offline Reinforcement Learning Framework for Interactive Recommendation","created":"2023-10-01","cited_by_count":18,"area":"offlinerl"},{"id":"2312.15910","title":"Reinforcement Unlearning","created":"2023-12-26","cited_by_count":17,"area":"safety"},{"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":"2405.14335","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2405.16363","title":"LLMs for User Interest Exploration in Large-scale Recommendation Systems","created":"2024-05-25","cited_by_count":15,"area":null},{"id":"2106.14979","title":"On component interactions in two-stage recommender systems","created":"2021-06-28","cited_by_count":14,"area":null},{"id":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"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":"2106.07914","title":"Control Variates for Slate Off-Policy Evaluation","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2206.00177","title":"On Gap-dependent Bounds for Offline Reinforcement Learning","created":"2022-06-01","cited_by_count":13,"area":"offlinerl"},{"id":"2301.08632","title":"Generative Slate Recommendation with Reinforcement Learning","created":"2023-01-20","cited_by_count":13,"area":null},{"id":"2307.15053","title":"On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation","created":"2023-07-27","cited_by_count":13,"area":null},{"id":"2405.05736","title":"Optimal Baseline Corrections for Off-Policy Contextual Bandits","created":"2024-05-09","cited_by_count":13,"area":null},{"id":"2503.06242","title":"LapSum -- One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection","created":"2025-03-08","cited_by_count":13,"area":null},{"id":"2309.11518","title":"Ad-load Balancing via Off-policy Learning in a Content Marketplace","created":"2023-09-19","cited_by_count":12,"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":"2109.03150","title":"Recommendation Fairness: From Static to Dynamic","created":"2021-09-05","cited_by_count":10,"area":null},{"id":"2112.02862","title":"SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2205.15436","title":"Uncertainty Quantification for Fairness in Two-Stage Recommender Systems","created":"2022-05-30","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":"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":"2405.02141","title":"Multi-Objective Recommendation via Multivariate Policy Learning","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2105.02377","title":"Towards Content Provider Aware Recommender Systems: A Simulation Study on the Interplay between User and Provider Utilities","created":"2021-05-06","cited_by_count":9,"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":"2309.15293","title":"Maximum diffusion reinforcement learning","created":"2023-09-26","cited_by_count":9,"area":null},{"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":"2405.10024","title":"$\\Delta\\text{-}{\\rm OPE}$: Off-Policy Estimation with Pairs of Policies","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2107.00833","title":"Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability","created":"2021-06-30","cited_by_count":8,"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":"2208.06263","title":"Probabilistic Rank and Reward: A Scalable Model for Slate Recommendation","created":"2022-08-10","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":"2402.10033","title":"Neural Network Approaches for Parameterized Optimal Control","created":"2024-02-15","cited_by_count":8,"area":"deeprl"},{"id":"2112.03210","title":"Contextual Bandit Applications in Customer Support Bot","created":"2021-12-06","cited_by_count":7,"area":null},{"id":"2207.00632","title":"Offline Policy Optimization with Eligible Actions","created":"2022-07-01","cited_by_count":7,"area":"offlinerl"},{"id":"2304.02572","title":"Evaluating Online Bandit Exploration In Large-Scale Recommender System","created":"2023-04-05","cited_by_count":7,"area":null},{"id":"2305.05586","title":"RLocator: Reinforcement Learning for Bug Localization","created":"2023-05-09","cited_by_count":7,"area":null},{"id":"2308.12256","title":"Learning from Negative User Feedback and Measuring Responsiveness for Sequential Recommenders","created":"2023-08-23","cited_by_count":7,"area":null},{"id":"2309.06375","title":"Modeling Recommender Ecosystems: Research Challenges at the Intersection of Mechanism Design, Reinforcement Learning and Generative Models","created":"2023-09-08","cited_by_count":7,"area":null},{"id":"2406.03102","title":"DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays","created":"2024-06-05","cited_by_count":7,"area":"deeprl"},{"id":"2406.12606","title":"Not Everything is All You Need: Toward Low-Redundant Optimization for Large Language Model Alignment","created":"2024-06-18","cited_by_count":7,"area":"alignment"},{"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":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2209.15166","title":"Reward Shaping for User Satisfaction in a REINFORCE Recommender","created":"2022-09-30","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":"2506.07085","title":"State Entropy Regularization for Robust Reinforcement Learning","created":"2025-06-08","cited_by_count":6,"area":"deeprl"},{"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":"2211.09832","title":"Latent User Intent Modeling for Sequential Recommenders","created":"2022-11-17","cited_by_count":5,"area":null},{"id":"2302.06014","title":"Online Recommendations for Agents with Discounted Adaptive Preferences","created":"2023-02-12","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":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"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":"2207.03029","title":"Multi-objective Optimization of Notifications Using Offline Reinforcement Learning","created":"2022-07-07","cited_by_count":4,"area":"offlinerl"},{"id":"2208.05327","title":"Fast Offline Policy Optimization for Large Scale Recommendation","created":"2022-08-08","cited_by_count":4,"area":"offlinerl"},{"id":"2211.02533","title":"A Transformer-Based Substitute Recommendation Model Incorporating Weakly Supervised Customer Behavior Data","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2301.05492","title":"Disentangled Representation for Diversified Recommendations","created":"2023-01-13","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":"2408.06512","title":"Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction","created":"2024-08-12","cited_by_count":4,"area":null},{"id":"2410.17538","title":"Primal-Dual Spectral Representation for Off-policy Evaluation","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2503.01490","title":"Improving Retrospective Language Agents via Joint Policy Gradient Optimization","created":"2025-03-03","cited_by_count":4,"area":"lr"},{"id":"2506.06521","title":"Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2606.17952","title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs","created":"2026-06-16","cited_by_count":4,"area":"moe"},{"id":"2103.00098","title":"Reducing Conservativeness Oriented Offline Reinforcement Learning","created":"2021-02-27","cited_by_count":3,"area":"offlinerl"},{"id":"2201.11016","title":"Recency Dropout for Recurrent Recommender Systems","created":"2022-01-26","cited_by_count":3,"area":null},{"id":"2208.01148","title":"Boosted Off-Policy Learning","created":"2022-08-01","cited_by_count":3,"area":null},{"id":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2305.10978","title":"Client Selection for Federated Policy Optimization with Environment Heterogeneity","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2308.01566","title":"Fast Slate Policy Optimization: Going Beyond Plackett-Luce","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2409.17436","title":"Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies","created":"2024-09-26","cited_by_count":3,"area":null},{"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":"2507.21117","title":"A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges","created":"2025-07-17","cited_by_count":3,"area":null},{"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":"2508.00751","title":"Harnessing the Power of Interleaving and Counterfactual Evaluation for Airbnb Search Ranking","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2105.03733","title":"Generative Actor-Critic: An Off-policy Algorithm Using the Push-forward Model","created":"2021-05-08","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":"2206.01011","title":"Policy Gradient Algorithms with Monte Carlo Tree Learning for Non-Markov Decision Processes","created":"2022-06-02","cited_by_count":2,"area":null},{"id":"2206.02593","title":"Pessimistic Off-Policy Optimization for Learning to Rank","created":"2022-06-06","cited_by_count":2,"area":null}],"next_cursor":"100"}