检索结果-南通市图书馆

A survey on model-based reinforcement learning

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第2期67卷 59-84页

作者： Fan-Ming LUO Tian XU Hang LAI Xiong-Hui CHEN weinan ZHANG Yang yu National Key Laboratory for Novel Software Technology Nanjing University Polixir. ai Department of Computer Science and Engineering Shanghai Jiao Tong University

Reinforcement learning(RL) interacts with the environment to solve sequential decision-making problems via a trial-and-error approach. Errors are always undesirable in real-world applications, even though RL excels at playing complex video games that permit several trial-and-error attempts. To improve sample efficiency and thus reduce errors, model-based reinforcement learning(MBRL) is believed to be a promising direction, as it constructs environment models in which trial-and-errors can occur without incurring actual costs. In this survey, we investigate MBRL with a particular focus on the recent advancements in deep RL. There is a generalization error between the learned model of a non-tabular environment and the actual environment. Consequently, it is crucial to analyze the disparity between policy training in the environment model and that in the actual environment, guiding algorithm design for improved model learning, model utilization, and policy training. In addition, we discuss the recent developments of model-based techniques in other forms of RL, such as offline RL, goal-conditioned RL, multi-agent RL, and meta-RL. Furthermore,we discuss the applicability and benefits of MBRL for real-world tasks. Finally, this survey concludes with a discussion of the promising future development prospects for MBRL. We believe that MBRL has great unrealized potential and benefits in real-world applications, and we hope this survey will encourage additional research on MBRL.

关键词： reinforcement learning model-based reinforcement learning planning model learning model learning with reduced error model usage

基于医联体分级教育干预2型糖尿病心血管疾病风险研究

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

现代医学 2024年第6期52卷 852-857页

作者：王小清李庆胡文俞伟男刘子瑜郝海荣陈艳张勇徐州医科大学附属淮安医院内分泌科江苏淮安223002

目的:探索三级医院-紧密型医联体-家庭医生分级教育的干预新模式对2型糖尿病心血管疾病风险的影响。方法:从2014—2015年市社保中心管理离退休人群中,选取本院紧密型医联体签约的2型糖尿病(type 2 diabetes mellitus, T2DM)患者,分干预... 详细信息

目的:探索三级医院-紧密型医联体-家庭医生分级教育的干预新模式对2型糖尿病心血管疾病风险的影响。方法:从2014—2015年市社保中心管理离退休人群中,选取本院紧密型医联体签约的2型糖尿病(type 2 diabetes mellitus, T2DM)患者,分干预组和对照组,干预组在社区家庭医生管理基础上由专科医师及护士给予一年系统个体化生活方式干预,对照组只接受常规社区管理,社区家庭医生接受三级医院专科团队一年2次的培训。4年后,共记录数据完整的T2DM患者456例,其中女282例,男174例,平均年龄(61.82±0.35)岁,干预组168例,对照组288例,比较两组随访干预前后生化指标及心血管疾病情况。结果:(1)干预后,所有患者血糖、血脂、收缩压等较基线下降(P<0.05);(2)与对照组相比,干预组LDL-C无明显升高;(3)对照组冠心病的风险是干预组的2.53倍(P<0.05);(4)干预组的肾功能无明显下降,矫正混杂因素后,生活方式干预是肾功能下降的独立保护因素(P<0.05)。结论:基于紧密型医联体-家庭医生签约制度,三级医院专业团队介入,对2型糖尿病患者进行综合管理干预的新模式,可有效降低2型糖尿病患者心血管疾病风险。

关键词：家庭医生签约管理紧密型医联体糖尿病生活方式干预心血管疾病

Effective strategies to promote Z(S)-scheme photocatalytic water splitting

在线全文

学校读者我要写书评

暂无评论

Chinese Chemical Letters 2024年第3期35卷 27-39页

作者： Ye yuan Junan Pan weinan Yin Haoxuan yu Fengshun Wang Weifeng Hu Longlu Wang Dafeng Yan College of Electronic and Optical Engineering&College of Flexible Electronics(Future Technology) Nanjing University of Posts&Telecommunications(NUPT)Nanjing 210023China College of Chemistry and Chemical Engineering Hubei UniversityWuhan 430062China

Artificial Z(S)-scheme photocatalytic water splitting systems have attracted extensive attention due to their advantages such as wide light absorption range,high charge separation efficiency and strong carrier redox ***,it is still challenging to design and prepare Z(S)-scheme photocatalysts with low-cost and highly stability for efficiently photocatalytic overall water splitting using solar *** review mainly introduces various strategies to improve the photocatalytic water splitting performance of Z(S)-scheme *** strategies mainly focus on enhancing or extending the range of light absorption,promoting charge separation,and enhancing surface redox reaction in Z(S)-scheme ***,the main challenges of Z(S)-scheme photocatalytic water splitting systems and their future development directions are pointed *** review would be beneficial to understanding the challenges and opportunities faced by the research field of Z(S)-scheme photocatalytic systems,and has important guiding significance for the development and utilization of high-performance Z(S)-scheme photocatalytic reaction system in the future.

关键词： Z(S)-scheme Overall water splitting Light absorption Charge separation Loading co-catalyst

双碳目标下考虑电氢互补的智慧园区多楼宇协调调度

在线全文

学校读者我要写书评

暂无评论

电力系统自动化 2022年第21期46卷 42-51页

作者：范宏于伟南柳璐窦真兰上海电力大学电气工程学院上海市200090 电力传输与功率变换控制教育部重点实验室(上海交通大学) 上海市200240 国网上海综合能源服务有限公司上海市200023

氢能是中国未来能源发展战略规划中承担加速实现“碳达峰·碳中和”使命的重要角色,在电力需求侧考虑氢储能系统能够提高终端用户的灵活性和协调性。但电力终端用户容量小、用能行为各异,传统的调度方法难以应对其动态变化的特性。针对... 详细信息

氢能是中国未来能源发展战略规划中承担加速实现“碳达峰·碳中和”使命的重要角色,在电力需求侧考虑氢储能系统能够提高终端用户的灵活性和协调性。但电力终端用户容量小、用能行为各异,传统的调度方法难以应对其动态变化的特性。针对这一问题,提出了一种分布式的智慧园区多楼宇协调调度方法。首先,根据实际工程建立了由含氢储能系统的多个楼宇组成的智慧园区典型场景;其次,制定了考虑可再生能源制氢的智慧园区调度策略,并将该分布式协调调度问题转换至深度强化学习架构中;然后,采用多智能体深度确定性策略梯度算法联合智能楼宇的高维历史用能数据库进行智慧园区的分布式实时调度;最后,通过算例分析和比较验证了所提方法的有效性。

关键词：双碳目标智慧园区多楼宇氢储能系统协调调度多智能体深度强化学习

政府信任视角下的公众感知评价研究进展与趋势

在线全文

学校读者我要写书评

暂无评论

财经论丛 2018年第8期 106-112页

作者：郭剑鸣汤彪俞薇楠浙江财经大学公共管理学院浙江杭州310018

本文采用主题文献挖掘方法,以政府信任提升为核心线索,对近半个世纪来国内外关于公众感知评价的内涵、应用领域、机制及方法、缺陷及发展趋势等内容的相关研究文献进行系统梳理,比较分析在新公共行政-新公共管理-新公共服务范式演变中,... 详细信息

本文采用主题文献挖掘方法,以政府信任提升为核心线索,对近半个世纪来国内外关于公众感知评价的内涵、应用领域、机制及方法、缺陷及发展趋势等内容的相关研究文献进行系统梳理,比较分析在新公共行政-新公共管理-新公共服务范式演变中,学术界对公众感知价值及其获得方式的认知差异,归纳一条"公众感知评价-政府价值与流程再造-政府信任提升"的学术演进逻辑。文章是以单一主题管窥学术范式演变的一种尝试。

关键词：政府信任公众感知评价进展与趋势

Application Research of PETD Combined with MRI Nerve Root Water Imaging in the Minimally Invasive Treatment of LDH

在线全文

学校读者我要写书评

暂无评论

International Journal of Clinical Medicine 2024年第4期15卷 167-176页

作者： Guanhua Wang Zhe Shen Jinben yu Shengjie Xu weinan Xu Bing Xu Xiaoyu Ye Wenzhou Combined Traditional Chinese and Western Medicine Hospital of Zhejiang Chinese Medicine University Wenzhou China The Third Clinical Medical College Zhejiang Chinese Medical University Hangzhou China

Objective: This study aims to evaluate the safety and efficacy of PETD combined with nerve root water imaging of MRI for the treatment of lumbar disc herniation. Methods: A retrospective review was performed on 62 patients with lumbar disc herniation from March 2019 to March 2021. The study included an experimental group of 30 patients and a control group of 32 patients. The experimental group underwent PETD combined with nerve root water imaging of MRI, while the control group received traditional PETD treatment. The visual analogue scoring method (VAS score), and JOA lumbar spine function score before and after surgery were compared between the two groups, and efficacy was assessed and compared using the MacNab score. Results: The mean operation time was significantly reduced in the experimental group (56.43 ±10.40 minutes) compared to the control group (65.69 ±14.12 minutes). The VAS score was compared between the two groups with preoperative (p = 0.624), one month after surgery (p = 0.325), three months after surgery (p = 0.676), one year after surgery (p = 0.341);The JOA score was compared between the two groups with preoperative (p = 0.961), one month after the surgery (p = 0.266), three months after surgery (p = 0.185), one year after surgery (p = 0.870), they were no significant statistical difference;The efficacy evaluation of the last follow-up Macnab showed that all the 30 patients in the experimental group were excellent, 31 of 32 patients in the control group were excellent, 1 case was good;There was no statistical difference in the comparison between the two groups (p > 0.05). Conclusion: The study concludes that the combined approach of PETD with nerve root water imaging of MRI is a safe, effective, and more efficient alternative to conventional PETD for treating lumbar disc herniation.

关键词： Lumbar Disc Herniation Nerve Root Water Imaging Percutaneous Interforaminal Endoscopy Minimally Invasive Spine Surgery Discectomy

考虑频率稳定约束的电-氢互补多楼宇协调优化调度

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

上海交通大学学报 2023年第12期57卷 1559-1570页

作者：范宏王兰坤邢梦晴田书欣于伟南上海电力大学电气工程学院上海200090 国网内蒙古东部电力有限公司电力科学研究院呼和浩特010020

为实现“碳达峰、碳中和”的双碳目标,电-氢互补综合能源系统的推进意义重大,但随着可再生能源的渗透率逐渐提高,系统的惯量水平下降,频率安全受到威胁.针对传统的优化调度方法无法保证系统的频率稳定性这一问题,提出了一种考虑频率稳... 详细信息

为实现“碳达峰、碳中和”的双碳目标,电-氢互补综合能源系统的推进意义重大,但随着可再生能源的渗透率逐渐提高,系统的惯量水平下降,频率安全受到威胁.针对传统的优化调度方法无法保证系统的频率稳定性这一问题,提出了一种考虑频率稳定约束的电-氢互补多楼宇协调优化调度方法.首先,建立了以楼宇为底层单元的电-氢综合能源系统架构,系统内的可再生能源发电机组采用虚拟同步发电机技术进行控制,以提高系统的惯量水平;其次,以调度周期内系统总运行成本最小为目标,并考虑了并网和孤岛不同运行模式下系统的惯量需求,建立了考虑系统频率稳定约束的优化调度模型;最后,通过算例仿真验证了所提方法对系统频率稳定的有效性、经济性和环保性.

关键词：双碳目标氢储能系统虚拟惯量频率稳定约束优化调度

在线全文

学校读者我要写书评

暂无评论

无损检测工作中的电磁辐射污染及其防范

当代化工研究 2017年第5期 68-69页

作者：鱼伟南九江检安石化工程有限公司江西332004

通过对无损检测特别是磁粉检测之中所存在着的电磁辐射污染问题进行了相应的计算,计算的结果也是直接的表明了磁粉检测设备导致电磁辐射的污染已经是超过了国家电磁辐射污染的允许限制,因此需要能引起无损检测人员以及政府部门对其引重... 详细信息

通过对无损检测特别是磁粉检测之中所存在着的电磁辐射污染问题进行了相应的计算,计算的结果也是直接的表明了磁粉检测设备导致电磁辐射的污染已经是超过了国家电磁辐射污染的允许限制,因此需要能引起无损检测人员以及政府部门对其引重视,并且也是需要采取相应的措施去保证无损检测人员和周围公众人员的安全。所以在本文之中,主要是针对了无损检测工作过程中的电磁辐射污染及其防范做出了全面的分析研究,在这个基础上提出了下文之中的一些内容,希望能够给与同行业工作的人员提供出一定价值的参考。

关键词：无损检测电磁辐射污染防范分析

Linear-Quadratic Pareto Cooperative Game for Mean-Field Backward Stochastic System

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第3期37卷 947-964页

作者： WANG yu School of Control Science and Engineering Shandong UniversityJinan 250061China

This paper focuses on a Pareto cooperative differential game with a linear mean-field backward stochastic system and a quadratic form cost functional. Based on a weighted sum optimality method, the Pareto game is equivalently converted to an optimal control problem. In the first place,the feedback form of Pareto optimal strategy is derived by virtue of decoupling technology, which is represented by four Riccati equations, a mean-field forward stochastic differential equation(MF-FSDE),and a mean-field backward stochastic differential equation(MF-BSDE). In addition, the corresponding Pareto optimal solution is further obtained. Finally, the author solves a problem in mathematical finance to illustrate the application of the theoretical results.

关键词： Backward stochastic differential equation linear-quadratic control mean-field Pareto optimality