{"total":21,"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":"2204.11966","title":"Estimating and Penalizing Induced Preference Shifts in Recommender Systems","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2205.13026","title":"Preference Dynamics Under Personalized Recommendations","created":"2022-05-25","cited_by_count":25,"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":"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":"2102.13302","title":"Variation Control and Evaluation for Generative SlateRecommendations","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2203.08248","title":"Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling","created":"2022-03-15","cited_by_count":10,"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":"2310.07745","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","created":"2023-10-11","cited_by_count":7,"area":null},{"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":"2310.09123","title":"Automatic Music Playlist Generation via Simulation-based Reinforcement Learning","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2201.07681","title":"Learning to Rank For Push Notifications Using Pairwise Expected Regret","created":"2022-01-19","cited_by_count":3,"area":null},{"id":"2602.10699","title":"Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2111.03340","title":"FINN.no Slates Dataset: A new Sequential Dataset Logging Interactions, allViewed Items and Click Responses/No-Click for Recommender Systems Research","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2210.10638","title":"Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning","created":"2022-10-06","cited_by_count":0,"area":null},{"id":"2211.09986","title":"Pandering in a Flexible Representative Democracy","created":"2022-11-18","cited_by_count":0,"area":null},{"id":"2303.02075","title":"Adaptive Interventions for Global Health: A Case Study of Malaria","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2309.08622","title":"Representation Learning in Low-rank Slate-based Recommender Systems","created":"2023-09-10","cited_by_count":0,"area":null},{"id":"2310.03043","title":"A Deep Reinforcement Learning Approach for Interactive Search with Sentence-level Feedback","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2310.17915","title":"Lifting the Veil: Unlocking the Power of Depth in Q-learning","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2604.23022","title":"CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems","created":"2026-04-24","cited_by_count":0,"area":null}],"next_cursor":null}