RI: Small: TIDES: Trustworthy Interactive DEcision-making Using Symbolic Planning

RI：小型：潮汐：使用符号规划进行值得信赖的交互式决策

• 批准号: 1910794
• 负责人: Levent Yilmaz
• 金额: $ 41.82万
• 依托单位: Auburn University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-10-01 至 2024-02-29
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1910794&HistoricalAwards=false
• 关键词: RI; Small; TIDES; Trustworthy; Interactive

Innovations in autonomy continue to produce systems that perceive, learn, decide, and act on their own. Many companies are now building self-driving vehicles and medical robots, and the development of advanced autonomous systems is already a billion-dollar industry. These new technologies offer oversight, advanced automation, and autonomous instruments, and they are adaptable to changing situations, knowledge, and constraints. However, introducing new technologies into our technical and social infrastructures has profound implications, and thus requires establishing confidence in their behavior to avoid potential harm. The effectiveness and broader acceptability of autonomous smart systems therefore rely on the ability of these systems to explain their decisions. Building trust in artificial intelligence (AI) systems is a critical requirement in human-robot interaction, and essential for realizing the full spectrum of societal and industrial benefits from AI. This proposal identifies two critical factors for establishing the trustworthiness of autonomous systems: explainability and risk-awareness. The proposed research will provide new algorithms and guidance to enable real-world applications, opening trustworthy reinforcement-learning techniques to a wide variety of practical applications such as control, robotics, e-commerce, and medical treatment. Overall, this research will produce, first, an explainable and data-efficient hierarchical sequential decision-making framework based on symbolic planning and hierarchical reinforcement learning; second, an explainable policy-search framework that can learn explainable policies via integrating inductive logic programming and reinforcement learning; and third, improved approaches to risk-sensitive policy search that are easy to use (for example, without the burden of tuning multi-timescale stepsizes). The theoretical contribution of this research is to significantly improve data-driven policy search in interactive sequential decision-making systems by developing a theory of trust that facilitates and informs smart interactive learning processes.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.

自主方面的创新继续产生感知、学习、决策和自主行动的系统。许多公司现在正在制造自动驾驶汽车和医疗机器人，先进自动驾驶系统的开发已经是一个价值数十亿美元的行业。这些新技术提供了监督、先进的自动化和自主工具，它们能够适应不断变化的情况、知识和限制。然而，将新技术引入我们的技术和社会基础设施具有深远的影响，因此需要对他们的行为建立信心，以避免潜在的伤害。因此，自主智能系统的有效性和更广泛的可接受性取决于这些系统解释其决策的能力。建立对人工智能(AI)系统的信任是人-机器人交互的关键要求，也是实现AI带来的全方位社会和工业好处的关键。该建议确定了建立自治系统的可信性的两个关键因素：可解释性和风险意识。拟议的研究将提供新的算法和指导，使真实世界的应用成为可能，将值得信赖的强化学习技术应用于广泛的实际应用，如控制、机器人、电子商务和医疗。总体而言，这项研究将产生，第一，基于符号规划和分层强化学习的可解释和数据高效的分层顺序决策框架；第二，可解释的策略搜索框架，可以通过整合归纳逻辑编程和强化学习来学习可解释的策略；以及第三，改进的风险敏感政策搜索方法，易于使用(例如，没有调整多时间尺度步长的负担)。这项研究的理论贡献是通过开发一种信任理论来显著改进交互式顺序决策系统中的数据驱动策略搜索，该信任理论促进并告知智能交互学习过程。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审查标准进行评估，被认为值得支持。

项目成果

TOPS: Transition-Based Volatility-Reduced Policy Search

TOPS：基于转型的波动性降低政策搜索

• 发表时间: 2022
• 期刊: Lecture notes in computer science
• 作者: Liangliang, X.;Daoming, L.;Yangchen, P.
• 通讯作者: Yangchen, P.

TDM: Trustworthy Decision-Making Via Interpretability Enhancement

TDM：通过增强可解释性做出值得信赖的决策

• DOI: 10.1109/tetci.2021.3084290
• 发表时间: 2021
• 期刊: IEEE Transactions on Emerging Topics in Computational Intelligence
• 影响因子: 5.3
• 作者: Lyu, Daoming;Yang, Fangkai;Kwon, Hugh;Dong, Wen;Yilmaz, Levent;Liu, Bo
• 通讯作者: Liu, Bo

Mean-Variance Policy Iteration for Risk-Averse Reinforcement Learning

• DOI: 10.1609/aaai.v35i12.17302
• 发表时间: 2020-04
• 作者: Shangtong Zhang;Bo Liu;Shimon Whiteson

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

• 发表时间: 2019-11
• 作者: Shangtong Zhang;Bo Liu;Hengshuai Yao;Shimon Whiteson

Principles and requirements for simulation-driven incremental learning of causal explanatory models

因果解释模型的模拟驱动增量学习的原则和要求

• 发表时间: 2022
• 期刊: Proceedings of the 2022 Winter Simulation Conference
• 作者: Levent Yilmaz