咨询与建议

限定检索结果

文献类型

  • 81 篇 期刊文献
  • 28 篇 会议
  • 2 篇 学位论文

馆藏范围

  • 111 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 87 篇 工学
    • 53 篇 计算机科学与技术...
    • 36 篇 电气工程
    • 30 篇 控制科学与工程
    • 8 篇 交通运输工程
    • 7 篇 石油与天然气工程
    • 5 篇 软件工程
    • 4 篇 信息与通信工程
    • 3 篇 动力工程及工程热...
    • 2 篇 仪器科学与技术
    • 2 篇 土木工程
    • 1 篇 电子科学与技术(可...
    • 1 篇 化学工程与技术
    • 1 篇 船舶与海洋工程
    • 1 篇 环境科学与工程(可...
  • 28 篇 管理学
    • 28 篇 管理科学与工程(可...
    • 3 篇 工商管理
  • 24 篇 理学
    • 22 篇 数学
    • 4 篇 系统科学
    • 1 篇 物理学
    • 1 篇 统计学(可授理学、...
  • 11 篇 经济学
    • 7 篇 理论经济学
    • 3 篇 应用经济学
  • 3 篇 医学
    • 3 篇 临床医学
    • 2 篇 基础医学(可授医学...

主题

  • 111 篇 value function a...
  • 37 篇 reinforcement le...
  • 18 篇 approximate dyna...
  • 12 篇 dynamic programm...
  • 7 篇 dynamic vehicle ...
  • 7 篇 temporal differe...
  • 6 篇 q-learning
  • 5 篇 function approxi...
  • 5 篇 markov decision ...
  • 4 篇 markov decision ...
  • 4 篇 neural networks
  • 4 篇 optimal control
  • 4 篇 policy iteration
  • 3 篇 rate of converge...
  • 3 篇 actor-critic
  • 3 篇 policy evaluatio...
  • 3 篇 polynomial basis...
  • 3 篇 reinforcement le...
  • 3 篇 energy managemen...
  • 3 篇 off-policy learn...

机构

  • 2 篇 beijing univ che...
  • 2 篇 hefei univ techn...
  • 2 篇 missouri univ sc...
  • 2 篇 univ massachuset...
  • 2 篇 tokyo inst techn...
  • 2 篇 northeastern uni...
  • 2 篇 univ sci & techn...
  • 2 篇 tech univ carolo...
  • 2 篇 natl univ def te...
  • 2 篇 georgia inst tec...
  • 2 篇 chinese acad sci...
  • 2 篇 otto von guerick...
  • 2 篇 rice univ dept e...
  • 1 篇 polish acad sci ...
  • 1 篇 shanghai engn re...
  • 1 篇 tsinghua univ de...
  • 1 篇 univ sydney sch ...
  • 1 篇 inria nancy gran...
  • 1 篇 univ southern ca...
  • 1 篇 univ twente ind ...

作者

  • 6 篇 ulmer marlin w.
  • 5 篇 song tianheng
  • 5 篇 li dazi
  • 4 篇 xu xin
  • 4 篇 mattfeld dirk c.
  • 3 篇 soeffker ninja
  • 3 篇 hachiya hirotaka
  • 2 篇 tutsoy onder
  • 2 篇 huang zhenhua
  • 2 篇 savelsbergh mart...
  • 2 篇 montoya juan m.
  • 2 篇 lewis frank l.
  • 2 篇 pietquin olivier
  • 2 篇 jin qibing
  • 2 篇 sickles robin c.
  • 2 篇 geist matthieu
  • 2 篇 li ping
  • 2 篇 chapman archie c...
  • 2 篇 zuo lei
  • 2 篇 cervellera crist...

语言

  • 109 篇 英文
  • 2 篇 其他
检索条件"主题词=value function approximation"
111 条 记 录,以下是1-10 订阅
排序:
value function approximation for dynamic multi-period vehicle routing
收藏 引用
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2018年 第3期269卷 883-899页
作者: Ulmer, Marlin W. Soeffker, Ninja Mattfeld, Dirk C. Tech Univ Carolo Wilhelmina Braunschweig Inst Wirtschaftsinformat Carl Friedrich Gauss Fak Muhlenpfordtstr 23 D-38106 Braunschweig Germany
In practical applications like parcel or technician services, customers request service during the day. Service providers decide whether to accept a customer for same-day service or to defer a customer due to resource... 详细信息
来源: 评论
value function approximation in the presence of uncertainty and inequality constraints - An application to the demand for credit cards
收藏 引用
JOURNAL OF ECONOMIC DYNAMICS & CONTROL 1996年 第1-3期20卷 63-92页
作者: Hartley, PR AUSTRALIAN NATL UNIV DEPT ECONCANBERRAACT 0200AUSTRALIA
We present an algorithm for approximating the solution to discrete-time stochastic dynamic programs with inequality constraints. The algorithm exploits the state preference approach to choice under uncertainty to redu... 详细信息
来源: 评论
A Clustering-Based Graph Laplacian Framework for value function approximation in Reinforcement Learning
收藏 引用
IEEE TRANSACTIONS ON CYBERNETICS 2014年 第12期44卷 2613-2625页
作者: Xu, Xin Huang, Zhenhua Graves, Daniel Pedrycz, Witold Natl Univ Def Technol Coll Mechatron & Automat Changsha 410073 Hunan Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2V4 Canada King Abdulaziz Univ Fac Engn Dept Elect & Comp Engn Jeddah 21589 Saudi Arabia Polish Acad Sci Syst Res Inst PL-01447 Warsaw Poland
In order to deal with the sequential decision problems with large or continuous state spaces, feature representation and function approximation have been a major research topic in reinforcement learning (RL). In this ... 详细信息
来源: 评论
Adaptive importance sampling for value function approximation in off-policy reinforcement learning
收藏 引用
NEURAL NETWORKS 2009年 第10期22卷 1399-1410页
作者: Hachiya, Hirotaka Akiyama, Takayuki Sugiayma, Masashi Peters, Jan Tokyo Inst Technol Dept Comp Sci Meguro Ku Tokyo 1528552 Japan Max Planck Inst Biol Cybernet Dept Scholkopf D-72076 Tubingen Germany
Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for... 详细信息
来源: 评论
Geodesic Gaussian kernels for value function approximation
收藏 引用
AUTONOMOUS ROBOTS 2008年 第3期25卷 287-304页
作者: Sugiyama, Masashi Hachiya, Hirotaka Towell, Christopher Vijayakumar, Sethu Tokyo Inst Technol Dept Comp Sci Meguro Ku Tokyo 1528552 Japan Univ Edinburgh Sch Informat Edinburgh EH9 3JZ Midlothian Scotland
The least-squares policy iteration approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basi... 详细信息
来源: 评论
A tutorial on value function approximation for stochastic and dynamic transportation
收藏 引用
4OR-A QUARTERLY JOURNAL OF OPERATIONS RESEARCH 2024年 第1期22卷 145-173页
作者: Heinold, Arne Univ Kiel Sch Econ & Business Kiel Germany
This paper provides an introductory tutorial on value function approximation (VFA), a solution class from Approximate Dynamic Programming. VFA describes a heuristic way for solving sequential decision processes like a... 详细信息
来源: 评论
Optimized ensemble value function approximation for dynamic programming
收藏 引用
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2023年 第2期309卷 719-730页
作者: Cervellera, Cristiano Natl Res Council Italy Inst Marine Engn Via Marini 6 I-16149 Genoa Italy
Approximate dynamic programming (ADP) is the standard tool for the solution of multistage dynamic optimization problems under general conditions, such as nonlinear state equation and cost, and continuous state and con... 详细信息
来源: 评论
Robust Approximate Bilinear Programming for value function approximation
收藏 引用
JOURNAL OF MACHINE LEARNING RESEARCH 2011年 第10期12卷 3027-3063页
作者: Petrik, Marek Zilberstein, Shlomo IBM Corp Thomas J Watson Res Ctr Yorktown Hts NY 10598 USA Univ Massachusetts Dept Comp Sci Amherst MA 01003 USA
value function approximation methods have been successfully used in many applications, but the prevailing techniques often lack useful a priori error bounds. We propose a new approximate bilinear programming formulati... 详细信息
来源: 评论
Meso-parametric value function approximation for dynamic customer acceptances in delivery routing
收藏 引用
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2020年 第1期285卷 183-195页
作者: Ulmer, Marlin W. Thomas, Barrett W. Tech Univ Carolo Wilhelmina Braunschweig Carl Friedrich Gauss Fak Muhlenpfordtstr 23 D-38106 Braunschweig Germany Univ Iowa Tippie Coll Business 108 John Pappajohn Business Bldg Iowa City IA 52242 USA
The rise of mobile communication, ample computing power, and Amazon's training of customers has led to last-mile delivery challenges and created struggles for companies seeking to budget their limited delivery res... 详细信息
来源: 评论
High-Order Taylor Expansion-Based Nonlinear value function approximation for Stochastic Economic Dispatch of Active Distribution Network
收藏 引用
IEEE TRANSACTIONS ON SMART GRID 2024年 第5期15卷 4511-4521页
作者: Luo, Yuhao Zhu, Jianquan Chen, Jiajun Wu, Ruibing Huang, Haojiang Liu, Wenhao Liu, Mingbo South China Univ Technol Sch Elect Power Engn Guangzhou 510640 Peoples R China
The stochastic economic dispatch (SED) problem of active distribution network (ADN) is computationally intractable for traditional algorithms due to the randomness, nonlinearity, and nonconvexity. To solve this proble... 详细信息
来源: 评论