CAREER: Toward Artificial General Intelligence for Complex Adaptive Systems: A Natural Concurrent “Learning-in-Learning” Control Paradigm

职业:走向复杂自适应系统的通用人工智能:自然并发“学习中学习”控制范式

基本信息

  • 批准号:
    2047064
  • 负责人:
  • 金额:
    $ 50.01万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2021
  • 资助国家:
    美国
  • 起止时间:
    2021-03-15 至 2026-02-28
  • 项目状态:
    未结题

项目摘要

Artificial intelligence (AI) technologies are transforming nearly every aspect of our lives and reinforcement learning (RL) is viewed as one of next big research topics in the current AI wave. While the existing AI and RL achievements are exciting, the fundamental research of data aggregation, learning and approximation capability, and the performance generalization during uncertainties, is not fully yet developed. There is still a gap from the current state-of-the-art techniques to the artificial general intelligence that can bring good performance in learning speed, data efficiency, and generalization of the optimization performance.Inspired by this observation, the PI proposes a natural concurrent RL framework that carries three major advantages over traditional RL methods, namely the i) advantages of simultaneously learning multimodal properties of the complex system; ii) structural advantages of using a personalized learning scheme; and iii) implementation advantages of the data-driven sample-efficient design. Within this framework, the PI proposes to design two concurrent RL methods to consolidate past experiences and anticipatory knowledge and build the “learning-in-learning” control paradigm. The theoretical results will certify that the proposed RL framework can be deployed with high confidence for complex adaptive systems under uncertain environments. The applications on smart energy community will support the novel learning framework and theoretical results.Beyond the scientific impacts, the proposed research has broader impacts for a wide range of research disciplines including transportation, rehabilitation, and robotics. The integration of research and education activities will also positively impact the institutions regionally and nationally. A proposed workshop will bring world renown experts to engage (state college) students and young researchers with limited financial supports to attend professional conferences. The collaboration with the industry and the national laboratory provides the students the opportunity to get external training, which can lead to competitive job offers. The proposed take-home AI/RL projects will promote interactive distance learning for schools with limited research capacity (e.g., rural community college) and for students with the preference of remote studying during the current pandemic. These activities will vigorously contribute to the nation’s AI workforce development.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(AI)技术正在改变我们生活的几乎每个方面,强化学习(RL)被视为当前AI浪潮中的下一个重大研究课题之一。虽然现有的AI和RL成就令人兴奋,但数据聚合,学习和近似能力以及不确定性下的性能泛化的基础研究尚未完全发展。从目前最先进的技术到人工通用智能,在学习速度,数据效率和优化性能的泛化方面仍然存在差距。受此启发,PI提出了一种自然并发RL框架,该框架与传统RL方法相比具有三大优势,即i)同时学习复杂系统的多模态特性的优点; ii)使用个性化学习方案的结构优点;以及iii)数据驱动的样本高效设计的实现优点。在此框架内,PI提出设计两种并行RL方法,以巩固过去的经验和预期的知识,并建立“学习中学习”的控制范式。理论结果将证明,所提出的RL框架可以部署在不确定环境下的复杂自适应系统的高置信度。智能能源社区的应用将支持新的学习框架和理论成果。除了科学影响,拟议的研究对广泛的研究学科,包括交通,康复和机器人技术具有更广泛的影响。研究和教育活动的一体化也将对区域和国家的机构产生积极影响。一个拟议的讲习班将使世界知名的专家参与(州立大学)学生和年轻的研究人员与有限的财政支持,参加专业会议。与行业和国家实验室的合作为学生提供了获得外部培训的机会,这可能会导致有竞争力的工作机会。拟议的带回家的AI/RL项目将促进研究能力有限的学校的互动式远程学习(例如,农村社区学院)和在当前大流行期间倾向于远程学习的学生。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(8)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
A Modified Maximum Entropy Inverse Reinforcement Learning Approach for Microgrid Energy Scheduling
一种改进的微电网能量调度最大熵逆强化学习方法
A new deep Q-learning method with dynamic epsilon adjustment and path planner assisted techniques for Turtlebot mobile robot
  • DOI:
    10.1117/12.2663695
  • 发表时间:
    2023-06
  • 期刊:
  • 影响因子:
    0
  • 作者:
    W. Cheng;Zhengbin Ni;Xiangnan Zhong
  • 通讯作者:
    W. Cheng;Zhengbin Ni;Xiangnan Zhong
Approximate dynamic programming with policy-based exploration for microgrid dispatch under uncertainties
A Neural-Reinforcement-Learning-based Guaranteed Cost Control for Perturbed Tracking Systems
基于神经强化学习的扰动跟踪系统保证成本控制
Multi-Virtual-Agent Reinforcement Learning for a Stochastic Predator-Prey Grid Environment
{{ 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 }}

Zhen Ni其他文献

Modulations of input-output properties of corticospinal tract neurons by repetitive dynamic index finger abductions.
通过重复动态食指外展调节皮质脊髓束神经元的输入输出特性。
  • DOI:
  • 发表时间:
    2004
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yahagi S.;Takeda Y;Zhen Ni;Takahashi M;Tsuji T.;Komiyama T.;Maruishi M.;Muranaka H.;Kasai T.
  • 通讯作者:
    Kasai T.
Mechanistic insights into effects of the electronic configurations and crystal structures of iron sulfides on the two-stage Fenton degradation for benzene
铁硫化物的电子构型和晶体结构对苯的两阶段芬顿降解影响的机理见解
  • DOI:
    10.1016/j.cej.2025.163030
  • 发表时间:
    2025-06-01
  • 期刊:
  • 影响因子:
    13.200
  • 作者:
    Cong Liang;Lei Yang;Jing Li;Lu Han;Yudong Feng;Mengfang Chen;Hangyu Li;Zhen Ni;Zhenyu Kang;Hongtao Sheng;Linbo Qian
  • 通讯作者:
    Linbo Qian
SNHG9 promotes Hepatoblastoma Tumorigenesis via miR-23a-5p/Wnt3a Axis
SNHG9 通过 miR-23a-5p/Wnt3a 轴促进肝母细胞瘤肿瘤发生
  • DOI:
    10.21203/rs.3.rs-335750/v1
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    3.9
  • 作者:
    Sun Gui Feng;Rajeev Bh;ari;Liu Ya;Bian Zhixuan;Pan Quihui;Zhu Jiabei;Mao Sewi;Zhen Ni;Wang Jing;Ma Ji;Ramesh Bh;ari
  • 通讯作者:
    ari
A fast federated reinforcement learning approach with phased weight-adjustment technique
一种具有分阶段权重调整技术的快速联邦强化学习方法
  • DOI:
    10.1016/j.neucom.2025.129550
  • 发表时间:
    2025-04-14
  • 期刊:
  • 影响因子:
    6.500
  • 作者:
    Yiran Pang;Zhen Ni;Xiangnan Zhong
  • 通讯作者:
    Xiangnan Zhong
The predictive accuracy of machine learning for the risk of death in HIV patients: a systematic review and meta-analysis
  • DOI:
    10.1186/s12879-024-09368-z
  • 发表时间:
    2024-05-06
  • 期刊:
  • 影响因子:
    3.000
  • 作者:
    Yuefei Li;Ying Feng;Qian He;Zhen Ni;Xiaoyuan Hu;Xinhuan Feng;Mingjian Ni
  • 通讯作者:
    Mingjian Ni

Zhen Ni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('Zhen Ni', 18)}}的其他基金

Collaborative Research: CyberTraining: Implementation: Small: Multi-disciplinary Training of Learning, Optimization and Communications for Next Generation Power Engineers
协作研究:网络培训:实施:小型:下一代电力工程师的学习、优化和通信多学科培训
  • 批准号:
    1949921
  • 财政年份:
    2019
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Standard Grant
Collaborative Research: CyberTraining: Implementation: Small: Multi-disciplinary Training of Learning, Optimization and Communications for Next Generation Power Engineers
协作研究:网络培训:实施:小型:下一代电力工程师的学习、优化和通信多学科培训
  • 批准号:
    1924302
  • 财政年份:
    2019
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Standard Grant
RII Track-4: A Reflective Learning and Association Control Framework based on Adaptive Dynamic Programming: Architecture and Applications in Robotics
RII Track-4:基于自适应动态规划的反思性学习和关联控制框架:机器人技术的架构和应用
  • 批准号:
    1833005
  • 财政年份:
    2018
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Standard Grant

相似国自然基金

Toward a general theory of intermittent aeolian and fluvial nonsuspended sediment transport
  • 批准号:
  • 批准年份:
    2022
  • 资助金额:
    55 万元
  • 项目类别:

相似海外基金

Collaborative Research: Black Girls as Creators: an intersectional learning ecosystem toward gendered racial equity in Artificial Intelligence education
合作研究:黑人女孩作为创造者:人工智能教育中实现性别种族平等的交叉学习生态系统
  • 批准号:
    2315041
  • 财政年份:
    2023
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Continuing Grant
Collaborative Research: Black Girls as Creators: an intersectional learning ecosystem toward gendered racial equity in Artificial Intelligence education
合作研究:黑人女孩作为创造者:人工智能教育中实现性别种族平等的交叉学习生态系统
  • 批准号:
    2315043
  • 财政年份:
    2023
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Continuing Grant
Evolvable Self-Reproducing Minimal Cells: Toward Artificial Living Systems
可进化的自我复制最小细胞:走向人工生命系统
  • 批准号:
    23H00087
  • 财政年份:
    2023
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Grant-in-Aid for Scientific Research (A)
Development of artificial exosomes containing proteins toward cancer genome editing
开发含有蛋白质的人工外泌体用于癌症基因组编辑
  • 批准号:
    22K19920
  • 财政年份:
    2023
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Grant-in-Aid for Challenging Research (Exploratory)
Collaborative Research: Black Girls as Creators: an intersectional learning ecosystem toward gendered racial equity in Artificial Intelligence education
合作研究:黑人女孩作为创造者:人工智能教育中实现性别种族平等的交叉学习生态系统
  • 批准号:
    2315042
  • 财政年份:
    2023
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Continuing Grant
Challenge toward development an artificial tool for cellular liquid-liquid phase separation by using optical condensation
开发利用光凝聚进行细胞液-液相分离的人工工具的挑战
  • 批准号:
    22K20512
  • 财政年份:
    2022
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Grant-in-Aid for Research Activity Start-up
Collaborative Research: FW-HTF-R: Toward an Ecosystem of Artificial Intelligence-Powered Music Production (TEAMuP)
合作研究:FW-HTF-R:迈向人工智能驱动的音乐制作生态系统 (TEAMuP)
  • 批准号:
    2222129
  • 财政年份:
    2022
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Standard Grant
Collaborative Research: FW-HTF-R: Toward an Ecosystem of Artificial-intelligence-powered Music Production (TEAMuP)
合作研究:FW-HTF-R:迈向人工智能驱动的音乐制作生态系统 (TEAMuP)
  • 批准号:
    2222369
  • 财政年份:
    2022
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Standard Grant
Toward Synthetic Neutrophils: De Novo Engineering of Chemotactic Artificial Cells
走向合成中性粒细胞:趋化人工细胞的从头工程
  • 批准号:
    2148534
  • 财政年份:
    2022
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Continuing Grant
Development of an artificial light-responsive DNA repair enzyme toward deep light-dependent gene therapy
开发人工光响应 DNA 修复酶以实现深度光依赖性基因治疗
  • 批准号:
    21K19223
  • 财政年份:
    2021
  • 资助金额:
    $ 50.01万
  • 项目类别:
    Grant-in-Aid for Challenging Research (Exploratory)
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了