{"total":10,"rows":[{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2406.14169","title":"Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learning","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2306.12165","title":"Post-hoc Selection of Pareto-Optimal Solutions in Search and Recommendation","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2401.12593","title":"MOReGIn: Multi-Objective Recommendation at the Global and Individual Levels","created":"2024-01-23","cited_by_count":1,"area":null},{"id":"2412.08911","title":"Goal-Conditioned Supervised Learning for Multi-Objective Recommendation","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2606.24042","title":"Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation","created":"2026-06-23","cited_by_count":1,"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":"2507.21274","title":"Large Language Model-Enhanced Reinforcement Learning for Diverse and Novel Recommendations","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2605.28810","title":"Affective Music Recommendation: A Rollout-Based World Model for Offline Preference Optimization","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}