{"total":9,"rows":[{"id":"2410.10460","title":"Compositional Shielding and Reinforcement Learning for Multi-Agent Systems","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2502.11896","title":"CAMEL: Continuous Action Masking Enabled by Large Language Models for Reinforcement Learning","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2605.10888","title":"Shields to Guarantee Probabilistic Safety in MDPs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2606.22278","title":"X-Safe: Embodiment-Agnostic Safeguarding for Robot Arm Manipulation Policies via Action Masking","created":"2026-06-21","cited_by_count":2,"area":null},{"id":"2412.00033","title":"Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2502.14043","title":"Safe Learning Under Irreversible Dynamics via Asking for Help","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2510.14884","title":"Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2511.17765","title":"LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2609.07618","title":"Decentralized Safe Multi-Agent Reinforcement Learning via Predictive Shielding","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}