课题基金 / 基金详情

ITR: Representation and Learning in Computational Game Theory

ITR: Representation and Learning in Computational Game Theory
ITR:计算博弈论中的表示和学习
批准号:
0325363
负责人:
Manfred Warmuth
金额:
$39.0万
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2003
资助国家:
美国
项目状态:
已结题
起止时间:
2003-09-15 至 2009-07-31

项目摘要

项目成果

Manfred Warmuth的其他基金

相似基金

相关文献

中文摘要
翻译
计算博弈论是计算机科学、经济学和相关领域交叉的一门新兴学科。它正在成为理解和设计复杂的多主体环境(如Internet、自治主体系统和电子经济)的基本工具。该计划的目标是为复杂的博弈论和经济推理问题开发强大的新表示,以及调整其参数的战略学习算法。特别强调的是允许在大量参与者之间的相互作用中规范自然网络结构的模型,以及概括金融市场精神的模型,其中相互作用通过全球中间量发生。最近强大的机器学习方法(如提升和指数更新)也被应用于游戏中更微妙和复杂的学习设置。该计划的预期结果是为博弈论应用提供了一套丰富的新建模方法,以及用于推理的计算高效算法,包括纳什均衡,相关均衡和其他均衡的计算,以及具有已知收敛特性的高效学习方法。本书将特别强调形式分析,由此产生的方法将为经济学、社会科学、进化生物学和其他博弈论方法常用的领域的研究人员提供一个新的工具箱。该项目的研究结果将通过国际会议和期刊以及更多专门研讨会广泛传播,这些研讨会有意将来自不同相关学科的研究人员聚集在一起。
英文摘要
Computational Game Theory is a rapidly emerging discipline at the intersection of computer science, economics, and related fields. It is becoming a fundamental tool for understanding and designing complex multiagent environments such as the Internet, systems of autonomous agents, and electronic economies. The objective of this program is the development of powerful new representations for complex game-theoretic and economic reasoning problems, and strategic learning algorithms for adjusting their parameters.Special emphasis is being given to models permitting the specification of natural network structure in the interactions within a large population of players, and models generalizing the spirit of financial markets, in which interactions take place via global intermediate quantities. Powerful recent machine learning methods such as boosting and exponential updates are also being applied to the more subtle and complex setting of learning in games.The expected results of the program are a rich set of new modeling methods for game-theoretic applications, and computationally efficient algorithms for reasoning with them, including the computation of Nash, correlated, and other equilibria, as well as efficient learning methods with known convergence properties. Special emphasis will be given to formal analysis, and the resulting methods will provide a new toolbox for researchers in economics, social science, evolutionary biology, and other fields in which game-theoretic approaches are common. The findings of the program will be widely disseminated through international conferences and journals, as well as more specialized workshops deliberately bringing together researchers from the different relevant disciplines.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
BIGDATA: Collaborative Research: F: Nomadic Algorithms for Machine Learning in the Cloud
  • 批准号:
    1546459
  • 项目类别:
    Standard Grant
  • 资助金额:
    $59.63万
  • 财政年份:
    2016
  • 负责人:
    Manfred Warmuth
  • 依托单位:
RI: Small: Collaborative Research: On-Line Learning Algorithms for Path Experts with Non-Additive Losses
  • 批准号:
    1619271
  • 项目类别:
    Standard Grant
  • 资助金额:
    $17.5万
  • 财政年份:
    2016
  • 负责人:
    Manfred Warmuth
  • 依托单位:
The 2012 Machine Learning Summer School at UC Santa Cruz
  • 批准号:
    1239963
  • 项目类别:
    Standard Grant
  • 资助金额:
    $3.0万
  • 财政年份:
    2012
  • 负责人:
    Manfred Warmuth
  • 依托单位:
III: Small: Collaborative Research: Probabilistic Models using Generalized Exponential Families
  • 批准号:
    1118028
  • 项目类别:
    Standard Grant
  • 资助金额:
    $25.0万
  • 财政年份:
    2011
  • 负责人:
    Manfred Warmuth
  • 依托单位:
海外基金