{"total":25,"rows":[{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36,"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":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"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":"2301.08632","title":"Generative Slate Recommendation with Reinforcement Learning","created":"2023-01-20","cited_by_count":13,"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":"2307.10524","title":"Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2105.00822","title":"Generative Adversarial Reward Learning for Generalized Behavior Tendency Inference","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2206.01341","title":"Equipping Black-Box Policies with Model-Based Advice for Stable Nonlinear Control","created":"2022-06-02","cited_by_count":6,"area":null},{"id":"2312.07392","title":"ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning","created":"2023-12-12","cited_by_count":6,"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":"2412.18296","title":"Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies","created":"2024-12-24","cited_by_count":4,"area":null},{"id":"2302.06916","title":"Effective Dimension in Bandit Problems under Censorship","created":"2023-02-14","cited_by_count":2,"area":null},{"id":"2108.05618","title":"Conditional Sequential Slate Optimization","created":"2021-08-12","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":"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":"2310.04483","title":"Reward Dropout Improves Control: Bi-objective Perspective on Reinforced LM","created":"2023-10-06","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":"2403.04875","title":"Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning","created":"2024-03-07","cited_by_count":0,"area":null},{"id":"2405.04026","title":"Federated Control in Markov Decision Processes","created":"2024-05-07","cited_by_count":0,"area":null},{"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":"2602.20403","title":"Risk-Averse Wasserstein Distributionally Robust Online Learning","created":"2026-02-23","cited_by_count":0,"area":null}],"next_cursor":null}