ITR: Collaborative Research: Representation and Learning in Computational Game theory
ITR: Collaborative Research: Representation and Learning in Computational Game theory
批准号:
0325281
负责人:
Michael Littman
金额:
$37.0万
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
中文摘要
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,如互联网,自治代理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法,以及调整其参数的战略学习算法。特别强调允许在大量参与者之间的相互作用中指定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局中间量发生。最近强大的机器学习方法,如boosting和指数更新,也被应用于更微妙和更复杂的游戏学习环境。该计划的预期结果是为游戏理论应用提供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有效学习方法。特别强调将给予正式的分析,并由此产生的方法将提供一个新的工具箱,为研究人员在经济学,社会科学,进化生物学,以及其他领域的博弈论的方法是常见的。该方案的研究结果将通过国际会议和期刊以及专门汇集不同相关学科研究人员的更专业的讲习班广泛传播。
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
EAGER: Training A Mobile Robot from Human Feedback via Income Learning
-
批准号:1643413
-
项目类别:Standard Grant
-
资助金额:$7.0万
-
财政年份:2016
-
负责人:Michael Littman
-
依托单位:
Collaborative Research: American Innovations in an Age of Discovery: Teaching Science and Engineering through 3D-printed Historical Reconstructions
-
批准号:1508319
-
项目类别:Continuing Grant
-
资助金额:$14.37万
-
财政年份:2015
-
负责人:Michael Littman
-
依托单位:
RI: Medium: Collaborative Research: Teaching Computers to Follow Verbal Instructions
-
批准号:1414931
-
项目类别:Standard Grant
-
资助金额:$51.44万
-
财政年份:2013
-
负责人:Michael Littman
-
依托单位:
RI: Small: Understanding Value-based Multiagent Learning and Its Applications
-
批准号:1414935
-
项目类别:Standard Grant
-
资助金额:$15.7万
-
财政年份:2013
-
负责人:Michael Littman
-
依托单位:
RI: Small: Collaborative Research: Speeding Up Learning through Modeling the Pragmatics of Training
-
批准号:1319618
-
项目类别:Continuing Grant
-
资助金额:$14.8万
-
财政年份:2013
-
负责人:Michael Littman
-
依托单位:
RI: Medium: Collaborative Research: Teaching Computers to Follow Verbal Instructions
-
批准号:1065195
-
项目类别:Standard Grant
-
资助金额:$70.39万
-
财政年份:2011
-
负责人:Michael Littman
-
依托单位:
RI: Small: Understanding Value-based Multiagent Learning and Its Applications
-
批准号:1018152
-
项目类别:Standard Grant
-
资助金额:$45.0万
-
财政年份:2010
-
负责人:Michael Littman
-
依托单位:
Collaborative Research: Pilot Research on Language-Based Strategies for Creative Problem Solving
-
批准号:0757490
-
项目类别:Standard Grant
-
资助金额:$10.0万
-
财政年份:2008
-
负责人:Michael Littman
-
依托单位:
RI: Collaborative Research: Feature Discovery and Benchmarks for Exportable Reinforcement Learning
-
批准号:0713148
-
项目类别:Standard Grant
-
资助金额:$22.5万
-
财政年份:2007
-
负责人:Michael Littman
-
依托单位:
HSD-DRU: The Role of Communication in the Dynamics of Effective Decision Making
-
批准号:0624191
-
项目类别:Standard Grant
-
资助金额:$68.5万
-
财政年份:2007
-
负责人:Michael Littman
-
依托单位:
Evaluating Next Generation Probabilistic Planners
-
批准号:0329153
-
项目类别:Continuing Grant
-
资助金额:$24.39万
-
财政年份:2003
-
负责人:Michael Littman
-
依托单位:
Creating the First International Probabilistic Planning Competition
-
批准号:0315909
-
项目类别:Standard Grant
-
资助金额:$1.02万
-
财政年份:2003
-
负责人:Michael Littman
-
依托单位:
Using System Identification and Learning Control to Manipulate Quantum Processes
-
批准号:9979665
-
项目类别:Standard Grant
-
资助金额:$7.27万
-
财政年份:1999
-
负责人:Michael Littman
-
依托单位:
CAREER: Planning Under Uncertainty in Large Domains
-
批准号:9702576
-
项目类别:Continuing Grant
-
资助金额:$30.0万
-
财政年份:1997
-
负责人:Michael Littman
-
依托单位:
海外基金