{"total":10,"rows":[{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2510.08539","title":"On the optimization dynamics of RLVR: Gradient gap and step size thresholds","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2504.02324","title":"Dynamic Assortment Selection and Pricing with Censored Preference Feedback","created":"2025-04-03","cited_by_count":2,"area":null},{"id":"2505.11983","title":"Online Iterative Self-Alignment for Radiology Report Generation","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2606.27082","title":"Finding Stationary Points by Comparisons","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2310.05871","title":"Dynamic value alignment through preference aggregation of multiple objectives","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2512.19057","title":"Efficient Personalization of Generative Models via Optimal Experimental Design","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2604.02349","title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","created":"2026-02-19","cited_by_count":0,"area":null}],"next_cursor":null}