{"total":12,"rows":[{"id":"2110.01834","title":"Thinking Fast and Slow in AI: the Role of Metacognition","created":"2021-10-05","cited_by_count":11,"area":null},{"id":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2505.13355","title":"Survey: Multi-Armed Bandits Meet Large Language Models","created":"2025-05-19","cited_by_count":7,"area":null},{"id":"2106.15808","title":"Optimal Epidemic Control as a Contextual Combinatorial Bandit with Budget","created":"2021-06-30","cited_by_count":5,"area":null},{"id":"2201.07763","title":"When Is It Acceptable to Break the Rules? Knowledge Representation of Moral Judgement Based on Empirical Data","created":"2022-01-19","cited_by_count":5,"area":null},{"id":"2209.12618","title":"Survey on Applications of Neurosymbolic Artificial Intelligence","created":"2022-09-08","cited_by_count":5,"area":null},{"id":"2203.16275","title":"Reinforcement Learning Guided by Provable Normative Compliance","created":"2022-03-30","cited_by_count":3,"area":null},{"id":"2202.10407","title":"Learning Behavioral Soft Constraints from Demonstrations","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2209.14035","title":"Advising Autonomous Cars about the Rules of the Road","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2302.10924","title":"A Reinforcement Learning Framework for Online Speaker Diarization","created":"2023-02-21","cited_by_count":1,"area":null},{"id":"2101.00001","title":"Etat de l'art sur l'application des bandits multi-bras","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2505.15011","title":"HAVA: Hybrid Approach to Value-Alignment through Reward Weighing for Reinforcement Learning","created":"2025-05-21","cited_by_count":0,"area":null}],"next_cursor":null}