PASOT-HRL: probably approximate safety options verification with temporal properties of hierarchical reinforcement learning policy

• 主要作者: Toh, Jing Qiang
• 其他作者: Arvind Easwaran
• 格式: Final Year Project
• 語言: English
• 出版: Nanyang Technological University 2025
• 主題: Computer and Information Science; Hierarchical reinforcement learning; Safety verification; Scenario optimization; Options safety verification; Temporal safety properties
• 在線閱讀: https://hdl.handle.net/10356/184131
• 機構: Nanyang Technological University

As the deployment of Artificial Intelligence (AI) agents in real-world applications grows, ensuring their safety is increasingly important. One approach to ensure safety is via safety verification to evaluate the safety probability of an AI agent. This paper presents Probably Approximate Safety Opti...