CPS: Small: Neuro-Symbolic Learning and Control with High-Level Knowledge Inference

CPS：小型：具有高级知识推理的神经符号学习和控制

• 批准号: 2304863
• 负责人: Zhe Xu
• 金额: $ 50万
• 依托单位: Arizona State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-01 至 2026-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2304863&HistoricalAwards=false
• 关键词: CPS; Small; Neuro; Symbolic; Learning

The use of artificial intelligence in cyber-physical systems is limited by challenges such as data availability, task environment complexity, and the need for expressive and interpretable high-level knowledge representations. To address these challenges, this project aims to develop a set of neuro-symbolic learning and control tools by integrating machine learning, control theory, and formal methods. The results are expected to find application across cyber-physical systems such as robotic systems, autonomous systems, and networked cyber-physical systems. Validation in a testbed environments should facilitate safe deployments in real-world physical environments with provable guarantees and robustness against potential adversaries.The research tasks mainly focus on improving the data efficiency, interpretability, scalability, and resiliency of the neuro-symbolic approaches in cyber-physical systems, with special focus on cyber-physical systems where extensive online interactions may not be safe or feasible, but high-level knowledge can be useful in completing tasks in complex and adversarial environments with provable correctness guarantees. Specifically, the neuro-symbolic learning and control algorithms offer the following three key features. Firstly, they incorporate template-free inference of high-level knowledge (e.g., temporal logic formulas) from uncertain data into neuro-symbolic learning to enable data-efficient reinforcement learning with both offline training and online fine-tuning. Secondly, the approaches are capable of achieving scalable and resilient reinforcement learning in multi-agent adversarial environments where high-level knowledge can be inferred for expediting the agents' learning processes. Lastly, the algorithms provide provable guarantees on complex task specifications using neuro-symbolic learning-based adaptive control with unknown dynamics. The results of this research will be shared through a range of educational activities, including undergraduate and graduate courses, as well as research workshops. Additionally, outreach programs will be implemented to engage K-12 students and diverse groups in the scientific and engineering communities and broaden their participation.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

人工智能在网络物理系统中的使用受到数据可用性、任务环境复杂性以及对表达性和可解释性高级知识表示的需求等挑战的限制。为了应对这些挑战，该项目旨在通过整合机器学习、控制理论和形式化方法来开发一套神经符号学习和控制工具。研究结果预计将在机器人系统、自主系统和网络网络物理系统等网络物理系统中得到应用。测试台环境中的验证应促进在现实物理环境中的安全部署，并提供可证明的保证和针对潜在对手的稳健性。研究任务主要集中于提高网络中神经符号方法的数据效率、可解释性、可扩展性和弹性。物理系统，特别关注网络物理系统，其中广泛的在线交互可能不安全或不可行，但高级知识可用于在复杂和对抗性环境中完成任务，并具有可证明的正确性保证。具体来说，神经符号学习和控制算法提供以下三个关键特征。首先，他们将不确定数据的高级知识（例如时态逻辑公式）的无模板推理纳入神经符号学习中，以通过离线训练和在线微调实现数据高效的强化学习。其次，这些方法能够在多智能体对抗环境中实现可扩展且有弹性的强化学习，在该环境中可以推断出高级知识以加快智能体的学习过程。最后，这些算法使用基于神经符号学习的自适应控制和未知动态，为复杂的任务规范提供了可证明的保证。这项研究的结果将通过一系列教育活动分享，包括本科生和研究生课程以及研究研讨会。此外，还将实施外展计划，以吸引 K-12 学生和科学和工程界的不同群体，并扩大他们的参与范围。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优势和更广泛的影响进行评估，被认为值得支持审查标准。

项目成果

Reinforcement Learning with Temporal-Logic-Based Causal Diagrams

使用基于时间逻辑的因果图进行强化学习

• DOI: 10.48550/arxiv.2306.13732
• 发表时间: 2023-06-23
• 期刊: ArXiv
• 作者: Yashi Paliwal;Rajarshi Roy;Jean;Nasim Baharisangari;D. Neider;Xiaoming Duan;U. Topcu;Zhe Xu
• 通讯作者: Zhe Xu

Decentralized graph-based multi-agent reinforcement learning using reward machines

使用奖励机器的基于分散图的多智能体强化学习

• DOI: 10.1016/j.neucom.2023.126974
• 发表时间: 2024-01
• 期刊: Neurocomputing
• 影响因子: 6
• 作者: Hu, Jueming;Xu, Zhe;Wang, Weichang;Qu, Guannan;Pang, Yutian;Liu, Yongming
• 通讯作者: Liu, Yongming