EAGER: Real-Time: Reinforcement, Meta, and Episodic Learning for Control under Uncertainty

EAGER:实时:不确定性下控制的强化、元和情景学习

基本信息

  • 批准号:
    1839429
  • 负责人:
  • 金额:
    $ 29.93万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2018
  • 资助国家:
    美国
  • 起止时间:
    2018-10-01 至 2021-09-30
  • 项目状态:
    已结题

项目摘要

Machine learning and artificial intelligence are among the most important general purpose technologies for the coming decades, with potential to transform all aspects of society from health, to manufacturing, to business, to education, and to security. In the last decade, there have been very important and impressive advances in machine learning driven by the use of deep neural networks, innovative training algorithms, computational resources including specialized hardware (graphics processors, tensor processing units), and large datasets. Some of these developments have connections to emerging understanding from neuroscience on how the human brain learns to makes decisions in real-time. However, there are major challenges in the use of these techniques in real-time control and decision making for engineering systems where stability, reliability, and safety are paramount concerns. This project aims to connect major advances in machine learning and neuroscience to control systems and thereby advance myriad application domains. Modern engineered systems are increasingly complicated. They comprise large heterogeneous distributed networks of (IoT) connected devices, systems, and human/social agents, e.g., transportation, energy, water, manufacturing, health and agriculture. A major challenge is performance, stability and reliability of these systems under large uncertainties. The goal is to expand our understanding and integration of learning and control to derive principles and algorithms for the development of learning-based control systems for a variety of engineering applications. While there are significant historical connections between reinforcement learning and stochastic dynamic control, the potential for leveraging ongoing and future advances in machine learning for control remains significantly under- explored. The field of control systems has deep and solid theoretical and mathematical foundations with comprehensive and well-established frameworks for linear, nonlinear, robust, adaptive, stochastic, distributed, and model-predictive control systems. Equally importantly, control systems have applications in multiple domains, such as aerospace, automotive, manufacturing, energy, transportation, agriculture, water, and many other engineered and socio-technical systems. Despite this rich spectrum of theoretical foundations and important applications, the domain of applicability of traditional control techniques is limited to situations where good mathematical models of the underlying systems are available, and where the environmental uncertainty is not too large. This exploratory research project is aimed at overcoming these limitations via novel problem formulations in systems and control inspired by new insights coming from recent developments in machine learning. A key focus will be on novel control architectures inspired by neuroscience and reinforcement learning. Besides architectural innovations, the project will explore questions of stability, performance, and uncertainty by integrating ideas from rapid (one-shot) learning, meta-learning, and episodic control into control algorithms. The ideas from this project will be at the core of a new graduate level course in learning for control which will be taught at the University of California, Irvine. The resulting course materials will be made available to the research community and will benefit interested graduate students across the nation. In addition, short courses will be offered at major professional conferences, e. g., American Control Conference, IEEE Conference on Decision and Control.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.
机器学习和人工智能是未来几十年最重要的通用技术之一,有可能改变社会的各个方面,从健康到制造业,到商业,到教育和安全。在过去的十年中,机器学习取得了非常重要和令人印象深刻的进步,这是由深度神经网络、创新训练算法、包括专用硬件(图形处理器、张量处理单元)在内的计算资源和大型数据集的使用驱动的。其中一些发展与神经科学对人类大脑如何学习实时决策的新兴理解有关。然而,在工程系统的稳定性,可靠性和安全性是最重要的问题,在实时控制和决策中使用这些技术存在重大挑战。该项目旨在将机器学习和神经科学的重大进展与控制系统联系起来,从而推动无数应用领域的发展。现代工程系统越来越复杂。它们包括(IoT)连接设备、系统和人类/社会代理的大型异构分布式网络,例如,交通、能源、水、制造业、卫生和农业。一个主要的挑战是这些系统在大的不确定性下的性能,稳定性和可靠性。我们的目标是扩大我们对学习和控制的理解和整合,以获得各种工程应用的基于学习的控制系统开发的原理和算法。 虽然强化学习和随机动态控制之间存在着重要的历史联系,但利用机器学习进行控制的持续和未来进展的潜力仍显着不足。控制系统领域有着深厚而坚实的理论和数学基础,为线性、非线性、鲁棒、自适应、随机、分布式和模型预测控制系统提供了全面而完善的框架。同样重要的是,控制系统在多个领域中有应用,例如航空航天、汽车、制造、能源、运输、农业、水以及许多其他工程和社会技术系统。尽管有丰富的理论基础和重要的应用,传统控制技术的适用范围仅限于底层系统的良好数学模型可用的情况下,以及环境的不确定性不是太大。这个探索性的研究项目旨在通过系统和控制中的新问题公式来克服这些限制,这些问题公式受到机器学习最近发展的新见解的启发。 一个关键的重点将是受神经科学和强化学习启发的新型控制架构。除了架构创新之外,该项目还将通过将快速(一次性)学习,元学习和情景控制的想法整合到控制算法中来探索稳定性,性能和不确定性问题。从这个项目的想法将在一个新的研究生水平的课程,在学习控制,将在加州大学欧文分校教授的核心。由此产生的课程材料将提供给研究界,并将有利于全国各地感兴趣的研究生。此外,短期课程将在主要的专业会议上提供,如。例如,在一个实施例中,该奖项反映了NSF的法定使命,并通过使用基金会的知识价值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

期刊论文数量(18)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions
  • DOI:
    10.1109/tits.2021.3074854
  • 发表时间:
    2020-08
  • 期刊:
  • 影响因子:
    8.5
  • 作者:
    S. Yu;A. Malawade;Deepan Muthirayan;P. Khargonekar;M. A. Faruque
  • 通讯作者:
    S. Yu;A. Malawade;Deepan Muthirayan;P. Khargonekar;M. A. Faruque
Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games
  • DOI:
  • 发表时间:
    2020-06
  • 期刊:
  • 影响因子:
    0
  • 作者:
    S. McAleer;John Lanier;Roy Fox;P. Baldi
  • 通讯作者:
    S. McAleer;John Lanier;Roy Fox;P. Baldi
Learning in the machine: To share or not to share?
机器学习:分享还是不分享?
  • DOI:
    10.1016/j.neunet.2020.03.016
  • 发表时间:
    2020
  • 期刊:
  • 影响因子:
    7.8
  • 作者:
    Ott, Jordan;Linstead, Erik;LaHaye, Nicholas;Baldi, Pierre
  • 通讯作者:
    Baldi, Pierre
Classifying shoulder implants in X-ray images using deep learning
Online Algorithms for Dynamic Matching Markets in Power Distribution Systems
  • DOI:
    10.1109/lcsys.2020.3008084
  • 发表时间:
    2020-03
  • 期刊:
  • 影响因子:
    3
  • 作者:
    Deepan Muthirayan;M. Parvania;P. Khargonekar
  • 通讯作者:
    Deepan Muthirayan;M. Parvania;P. Khargonekar
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Pramod Khargonekar其他文献

Offline first-fit decreasing height scheduling of power loads
  • DOI:
    10.1007/s10951-017-0528-y
  • 发表时间:
    2017-06-21
  • 期刊:
  • 影响因子:
    1.800
  • 作者:
    Anshu Ranjan;Pramod Khargonekar;Sartaj Sahni
  • 通讯作者:
    Sartaj Sahni
AI Engineering: A Strategic Research Framework to Benefit Society
人工智能工程:造福社会的战略研究框架
  • DOI:
    10.2139/ssrn.4778388
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Pramod Khargonekar;Engineering Research Visioning Alliance
  • 通讯作者:
    Engineering Research Visioning Alliance

Pramod Khargonekar的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Pramod Khargonekar', 18)}}的其他基金

Collaborative Research: Integrating Random Energy Into the Smart Grid
合作研究:将随机能源集成到智能电网中
  • 批准号:
    1723849
  • 财政年份:
    2016
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
CPS: Synergy: Collaborative Research: Coordinated Resource Management of Cyber-Physical-Social Power Systems
CPS:协同:协作研究:网络-物理-社会电力系统的协调资源管理
  • 批准号:
    1723856
  • 财政年份:
    2016
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
CPS: Synergy: Collaborative Research: Coordinated Resource Management of Cyber-Physical-Social Power Systems
CPS:协同:协作研究:网络-物理-社会电力系统的协调资源管理
  • 批准号:
    1239274
  • 财政年份:
    2012
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
Collaborative Research: Integrating Random Energy Into the Smart Grid
合作研究:将随机能源集成到智能电网中
  • 批准号:
    1129061
  • 财政年份:
    2011
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
Feedback Control In Semiconductor Manufacturing: Reactive Ion Etching
半导体制造中的反馈控制:反应离子蚀刻
  • 批准号:
    9312134
  • 财政年份:
    1993
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
Algebraic and Analytic Aspects of Decentralized and Noninteracting Control Problems (U.S.-Turkey Cooperative Science; Science in Developing Countries).
分散和非交互控制问题的代数和分析方面(美国-土耳其合作科学;发展中国家的科学)。
  • 批准号:
    9101276
  • 财政年份:
    1991
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
Robust Control Theory
鲁棒控制理论
  • 批准号:
    9001371
  • 财政年份:
    1990
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
PYIA: Synthesis of Robust Controllers for Lumped and Distributed Parameter Systems
PYIA:集总和分布式参数系统的鲁棒控制器综合
  • 批准号:
    9096109
  • 财政年份:
    1989
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Continuing Grant
PYIA: Synthesis of Robust Controllers for Lumped and Distributed Parameter Systems
PYIA:集总和分布式参数系统的鲁棒控制器综合
  • 批准号:
    8451519
  • 财政年份:
    1985
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Continuing Grant

相似国自然基金

Immuno-Real Time PCR法精确定量血清MG7抗原及在早期胃癌预警中的价值
  • 批准号:
    30600737
  • 批准年份:
    2006
  • 资助金额:
    22.0 万元
  • 项目类别:
    青年科学基金项目
无色ReAl3(BO3)4(Re=Y,Lu)系列晶体紫外倍频性能与器件研究
  • 批准号:
    60608018
  • 批准年份:
    2006
  • 资助金额:
    28.0 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

EAGER: Building a Provable Differentially Private Real-time Data-blind ML Algorithm: A case study on Enhancing STEM Student Engagement in Online Learning
EAGER:构建可证明的差分隐私实时数据盲机器学习算法:关于增强 STEM 学生在线学习参与度的案例研究
  • 批准号:
    2329919
  • 财政年份:
    2023
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
Collaborative Research: EAGER: Real-time Strategies and Synchronized Time Distribution Mechanisms for Enhanced Exascale Performance-Portability and Predictability
合作研究:EAGER:实时策略和同步时间分配机制,以增强百亿亿次性能-可移植性和可预测性
  • 批准号:
    2405142
  • 财政年份:
    2023
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
Collaborative Research: EAGER: Real-time Strategies and Synchronized Time Distribution Mechanisms for Enhanced Exascale Performance-Portability and Predictability
合作研究:EAGER:实时策略和同步时间分配机制,以增强百亿亿次性能-可移植性和可预测性
  • 批准号:
    2151021
  • 财政年份:
    2022
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
Collaborative Research: EAGER: Real-time Strategies and Synchronized Time Distribution Mechanisms for Enhanced Exascale Performance-Portability and Predictability
合作研究:EAGER:实时策略和同步时间分配机制,以增强百亿亿次性能-可移植性和可预测性
  • 批准号:
    2151022
  • 财政年份:
    2022
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
EAGER: DCL: SaTC: Enabling Interdisciplinary Collaboration: Inoculation vs. education: the role of real time alerts and end-user overconfidence
EAGER:DCL:SaTC:实现跨学科协作:接种与教育:实时警报和最终用户过度自信的作用
  • 批准号:
    2210198
  • 财政年份:
    2022
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
EAGER: Compact Field Portable Biophotonics Instrument for Real-Time Automated Analysis and Identification of Blood Cells Impact Impacted by COVID-19
EAGER:紧凑型现场便携式生物光子学仪器,用于实时自动分析和识别受 COVID-19 影响的血细胞
  • 批准号:
    2141473
  • 财政年份:
    2022
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
Collaborative Research: EAGER: Real-time Strategies and Synchronized Time Distribution Mechanisms for Enhanced Exascale Performance-Portability and Predictability
合作研究:EAGER:实时策略和同步时间分配机制,以增强百亿亿次性能-可移植性和可预测性
  • 批准号:
    2151020
  • 财政年份:
    2022
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
EAGER: MEMS Enabled Real Time Detection of Pathogens Viruses and Biomarkers
EAGER:MEMS 实现病原体病毒和生物标记物的实时检测
  • 批准号:
    2210471
  • 财政年份:
    2022
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
EAGER: Collaborative Research: Development of an Energy-Harvesting Real-time Under-ice Monitoring System in the Arctic Ocean
EAGER:合作研究:北冰洋能量收集实时冰下监测系统的开发
  • 批准号:
    2134146
  • 财政年份:
    2021
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
EAGER/Collaborative Research: High-throughput, Autonomous Real-time Monitoring of Tissue Mechanical Property Change via Impedimetric Sensor Arrays
EAGER/协作研究:通过阻抗传感器阵列高通量、自主实时监测组织机械性能变化
  • 批准号:
    2141008
  • 财政年份:
    2021
  • 资助金额:
    $ 29.93万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了