{"total":11,"rows":[{"id":"2301.08491","title":"Modeling Moral Choices in Social Dilemmas with Multi-Agent Reinforcement Learning","created":"2023-01-20","cited_by_count":10,"area":null},{"id":"2407.16312","title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2410.23630","title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2410.15557","title":"How to Find the Exact Pareto Front for Multi-Objective MDPs?","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2310.06176","title":"Factual and Personalized Recommendations using Language Models and Reinforcement Learning","created":"2023-10-09","cited_by_count":4,"area":null},{"id":"2410.11221","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2507.20728","title":"Learning the Value Systems of Societies from Preferences","created":"2025-07-28","cited_by_count":2,"area":null},{"id":"2507.16430","title":"Beyond Algorethics: Addressing the Ethical and Anthropological Challenges of AI Recommender Systems","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2606.32027","title":"Freeform Preference Learning for Robotic Manipulation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2410.21882","title":"Building Altruistic and Moral AI Agent with Brain-inspired Emotional Empathy Mechanisms","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2504.16093","title":"Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Model","created":"2025-04-06","cited_by_count":0,"area":null}],"next_cursor":null}