{"total":9,"rows":[{"id":"2310.09144","title":"Goodhart's Law in Reinforcement Learning","created":"2023-10-13","cited_by_count":41,"area":null},{"id":"2309.15257","title":"STARC: A General Framework For Quantifying Differences Between Reward Functions","created":"2023-09-26","cited_by_count":15,"area":null},{"id":"2310.15288","title":"Active teacher selection for reward learning","created":"2023-10-23","cited_by_count":7,"area":null},{"id":"2311.17165","title":"(Ir)rationality in AI: State of the Art, Research Challenges and Open Questions","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2312.03881","title":"FoMo Rewards: Can we cast foundation models as reward functions?","created":"2023-12-06","cited_by_count":4,"area":null},{"id":"2503.01885","title":"Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2506.02923","title":"The Limits of Predicting Agents from Behaviour","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2407.09809","title":"Preserving the Privacy of Reward Functions in MDPs through Deception","created":"2024-07-13","cited_by_count":1,"area":null},{"id":"2502.18447","title":"Supervised Reward Inference","created":"2025-02-25","cited_by_count":0,"area":null}],"next_cursor":null}