A closed-loop human–agent learning framework to enhance decision making

用于增强决策的闭环人类代理学习框架

• 批准号: DE220100265
• 负责人: Dr Zehong Cao
• 金额: $ 30.42万
• 依托单位: University of South Australia
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Early Career Researcher Award
• 财政年份: 2022
• 资助国家: 澳大利亚
• 起止时间: 2022-10-01 至 2025-10-18
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DE220100265
• 关键词: closed; loop; human; agent; learning

This project aims to design a foundational human–agent learning framework to augment the decision making process, using reinforcement and closed-loop mechanisms to enable symbiosis between a human and an artificial-intelligence agent. It envisages significant new technologies to promote controllability and efficient and safe exploration of an environment for decision actions – drastically boosting learning effectiveness and interpretability in decision making. Expected outcomes will benefit national cybersecurity by improving our understanding of vulnerabilities and threats involving decision actions, and by ensuring that human feedback and evaluations can help prevent catastrophic events in explorations of dynamic and complex environments.

该项目旨在设计一个基本的人类智能体学习框架来增强决策过程，使用强化和闭环机制来实现人类和人工智能体之间的共生。它设想了重要的新技术，以促进决策行动环境的可控性、高效和安全的探索——大大提高决策的学习有效性和可解释性。预期结果将通过提高我们对涉及决策行动的漏洞和威胁的理解，并通过确保人类反馈和评估有助于防止动态和复杂环境探索中的灾难性事件，从而有利于国家网络安全。