咨询与建议

限定检索结果

文献类型

  • 53 篇 期刊文献
  • 25 篇 会议
  • 1 篇 学位论文

馆藏范围

  • 79 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 74 篇 工学
    • 41 篇 计算机科学与技术...
    • 31 篇 电气工程
    • 23 篇 控制科学与工程
    • 18 篇 信息与通信工程
    • 7 篇 交通运输工程
    • 5 篇 软件工程
    • 3 篇 机械工程
    • 3 篇 仪器科学与技术
    • 2 篇 测绘科学与技术
    • 1 篇 土木工程
    • 1 篇 化学工程与技术
    • 1 篇 航空宇航科学与技...
  • 17 篇 管理学
    • 13 篇 管理科学与工程(可...
    • 2 篇 工商管理
    • 2 篇 图书情报与档案管...
  • 12 篇 理学
    • 10 篇 数学
    • 6 篇 系统科学
    • 1 篇 地球物理学
    • 1 篇 统计学(可授理学、...
  • 3 篇 医学
    • 3 篇 临床医学
    • 1 篇 基础医学(可授医学...
  • 1 篇 经济学
    • 1 篇 理论经济学
    • 1 篇 应用经济学
  • 1 篇 教育学
    • 1 篇 教育学

主题

  • 79 篇 actor-critic alg...
  • 31 篇 reinforcement le...
  • 18 篇 deep reinforceme...
  • 5 篇 deep learning
  • 5 篇 reinforcement le...
  • 4 篇 input constraint...
  • 3 篇 dynamic path pla...
  • 3 篇 task analysis
  • 3 篇 transfer learnin...
  • 3 篇 differential gam...
  • 3 篇 trajectory
  • 3 篇 active hypothesi...
  • 3 篇 sequential sensi...
  • 3 篇 multi-agent rein...
  • 2 篇 vehicle dynamics
  • 2 篇 quickest state e...
  • 2 篇 sample efficienc...
  • 2 篇 nonzero-sum stoc...
  • 2 篇 transformer
  • 2 篇 industry 4.0

机构

  • 4 篇 syracuse univ de...
  • 4 篇 indian inst sci ...
  • 3 篇 menoufia univ fa...
  • 3 篇 school of contro...
  • 2 篇 lebanese amer un...
  • 2 篇 concordia univ m...
  • 2 篇 harokopio univ a...
  • 2 篇 huazhong univ sc...
  • 2 篇 lakehead univ th...
  • 2 篇 nile univ sesc r...
  • 2 篇 jilin univ key l...
  • 2 篇 univ elect sci &...
  • 2 篇 shenzhen univ co...
  • 2 篇 texas a&m univ d...
  • 2 篇 jilin univ coll ...
  • 1 篇 univ calif berke...
  • 1 篇 zhongguancun lab...
  • 1 篇 univ texas austi...
  • 1 篇 hanoi univ sci &...
  • 1 篇 texas a&m univ c...

作者

  • 3 篇 joseph geethu
  • 3 篇 chronis christos
  • 3 篇 shalaby raafat
  • 3 篇 bhatnagar shalab...
  • 3 篇 varlamis iraklis
  • 3 篇 varshney pramod ...
  • 3 篇 politi elena
  • 3 篇 gursoy m. cenk
  • 3 篇 mahmoud tarek a.
  • 3 篇 abo-zalam belal
  • 3 篇 dimitrakopoulos ...
  • 3 篇 el-hossainy moha...
  • 2 篇 wang bing-chang
  • 2 篇 assi chadi
  • 2 篇 wang yanzhi
  • 2 篇 zhang zhicai
  • 2 篇 lu shuai
  • 2 篇 qiu qinru
  • 2 篇 qu hong
  • 2 篇 parizs richard d...

语言

  • 79 篇 英文
检索条件"主题词=Actor-Critic Algorithm"
79 条 记 录,以下是1-10 订阅
排序:
A priority experience replay actor-critic algorithm using self-attention mechanism for strategy optimization of discrete problems
收藏 引用
PEERJ COMPUTER SCIENCE 2024年 10卷 e2161-e2161页
作者: Sun, Yuezhongyi Yang, Boyu Harbin Univ Sci & Technol Sch Comp Sci & Technol Harbin Heilongjiang Peoples R China
In the dynamic fi eld of deep reinforcement learning, the self -attention mechanism has been increasingly recognized. Nevertheless, its application in discrete problem domains has been relatively limited, presenting c... 详细信息
来源: 评论
Convergence of Decentralized actor-critic algorithm in General-Sum Markov Games
收藏 引用
IEEE CONTROL SYSTEMS LETTERS 2024年 8卷 2643-2648页
作者: Maheshwari, Chinmay Wu, Manxi Sastry, Shankar Univ Calif Berkeley Dept EECS Berkeley CA 94709 USA Univ Calif Berkeley Dept Civil & Environm Engn Berkeley CA 94709 USA
Markov games provide a powerful framework for modeling strategic multi-agent interactions in dynamic environments. Traditionally, convergence properties of decentralized learning algorithms in these settings have been... 详细信息
来源: 评论
Optimal fractional-order PID controller based on fractional-order actor-critic algorithm
收藏 引用
NEURAL COMPUTING & APPLICATIONS 2023年 第3期35卷 2347-2380页
作者: Shalaby, Raafat El-Hossainy, Mohammad Abo-Zalam, Belal Mahmoud, Tarek A. Menoufia Univ Fac Elect Engn Dept Ind Elect & Control Engn Menoufia 32952 Egypt Nile Univ Sch Engn & Appl Sci Dept Mechatron Engn Giza 12588 Egypt New Cairo Technol Univ Fac Ind & Energy Technol Dept New & Renewable Energy Cairo 11853 Egypt
In this paper, an online optimization approach of a fractional-order PID controller based on a fractional-order actor-critic algorithm (FOPID-FOAC) is proposed. The proposed FOPID-FOAC scheme exploits the advantages o... 详细信息
来源: 评论
An Adaptive Threshold for the Canny Edge With actor-critic algorithm
收藏 引用
IEEE ACCESS 2023年 11卷 67058-67069页
作者: Choi, Keong-Hun Ha, Jong-Eun Seoul Natl Univ Sci & Technol Grad Sch Automot Engn Seoul 01811 South Korea Seoul Natl Univ Sci & Technol Dept Mech & Automot Engn Seoul 01811 South Korea
We propose a method to automatically select proper values of three thresholds in the Canny edge algorithm. Edge detection is widely used for object recognition, detection, and segmentation. Due to its good performance... 详细信息
来源: 评论
A novel semi-supervised generative adversarial network based on the actor-critic algorithm for compound fault recognition
收藏 引用
NEURAL COMPUTING & APPLICATIONS 2022年 第13期34卷 10787-10805页
作者: Wang, Zisheng Xuan, Jianping Shi, Tielin Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China
Vibration signals can be used to extract effective fault features for fault diagnosis. However, traditional supervised learning requires considerable manpower and time to mark samples manually, and this process is dif... 详细信息
来源: 评论
Earth Observation Satellite Scheduling Based on actor-critic algorithm
Earth Observation Satellite Scheduling Based on Actor-Critic...
收藏 引用
2024 International Conference on Guidance, Navigation and Control
作者: Chen, Chao Wang, ZhiTao Wang, Nuan He, Rong Zeng, Dexian Space Engn Univ Beijing 101400 Peoples R China
The earth observation satellite(EOS) scheduling has problems such as complex constraints and difficulty in solving. For multi-orbit scheduling problem of the single EOS, this paper first describes the EOS scheduling p... 详细信息
来源: 评论
Evaluating Correctness of Reinforcement Learning based on actor-critic algorithm  13
Evaluating Correctness of Reinforcement Learning based on Ac...
收藏 引用
13th International Conference on Ubiquitous and Future Networks (ICUFN)
作者: Kim, Youngjae Hussain, Manzoor Suh, Jae-Won Hong, Jang-Eui Chungbuk Natl Univ Coll Elect & Comp Engn Cheongju South Korea
Deep learning is used for decision making and functional control in various fields, such as autonomous systems. However, rather than being developed by logical design, deep learning models are trained by itself throug... 详细信息
来源: 评论
Intelligent fault recognition framework by using deep reinforcement learning with one dimension convolution and improved actor-critic algorithm
收藏 引用
ADVANCED ENGINEERING INFORMATICS 2021年 49卷
作者: Wang, Zisheng Xuan, Jianping Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China
The quality of fault recognition part is one of the key factors affecting the efficiency of intelligent manufacturing. Many excellent achievements in deep learning (DL) have been realized recently as methods of fault ... 详细信息
来源: 评论
Episodic Memory-Double actor-critic Twin Delayed Deep Deterministic Policy Gradient
收藏 引用
NEURAL NETWORKS 2025年 187卷 107286页
作者: Shu, Man Lu, Shuai Gong, Xiaoyu An, Daolong Li, Songlin Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun 130012 Peoples R China Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys Changchun 130033 Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China Jilin Univ Coll Software Changchun 130012 Peoples R China
Existing deep reinforcement learning (DRL) algorithms suffer from the problem of low sample efficiency. Episodic memory allows DRL algorithms to remember and use past experiences with high return, thereby improving sa... 详细信息
来源: 评论
Energy-Efficient Content Fetching Strategies in Cache-Enabled D2D Networks via an actor-critic Reinforcement Learning Structure
收藏 引用
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年 第11期73卷 17485-17495页
作者: Yan, Ming Luo, Meiqi Chan, Chien Aun Gygax, Andre F. Li, Chunguo Chih-Lin, I Commun Univ China Sch Informat & Commun Engn Beijing 100024 Peoples R China Commun Univ China Key Lab Acoust Visual Technol & Intelligent Contro Beijing 100024 Peoples R China Univ Melbourne Dept Elect & Elect Engn Melbourne Vic 3010 Australia Univ Melbourne Fac Business & Econ Melbourne Vic 3010 Australia Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China China Mobile Res Inst Beijing 100053 Peoples R China
As one of the important complementary technologies of the fifth-generation (5G) wireless communication and beyond, mobile device-to-device (D2D) edge caching and computing can effectively reduce the pressure on backbo... 详细信息
来源: 评论