Multi-Agent Control: Mechanism Design and Adaptive Learning

多智能体控制：机制设计和自适应学习

• 批准号: 0424445
• 负责人: Pravin Varaiya
• 金额: $ 15.59万
• 依托单位: University of California-Berkeley
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2004
• 资助国家: 美国
• 起止时间: 2004-09-01 至 2005-10-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0424445&HistoricalAwards=false
• 关键词: Multi; Agent; Control; Mechanism; Design

ECS-0424445Multi-agent control: mechanism design and adaptive learningPI Pravin Varaiya, University of California, Berkeley, [e-mail] Abstract We seek to study control strategies for multi-agent systems in which agents have differentinformation and possibly different objectives. We organize these decision-making settings as cooperative or non-cooperative games. The objective is to design the 'rules of the game'in such a way that agents acting selfishly on their own behalf arrive at promoting sociallydesirable strategies. We will focus on 'combinatorial auctions' as the paradigmatic game. Second, we want to study control strategies with low computational complexity, which rules out dynamic programming or global optimization. The approach is to reduce complexity by resoring to 'learning', based on simulation or experiments, in order to estimate the valueof a particular strategy. Examples to test our approach will be drawn from bandwidth trading in communication networks.

多智能体控制：机制设计和自适应学习pi Pravin Varaiya，加州大学伯克利分校，[e-mail]摘要我们寻求研究多智能体系统的控制策略，其中智能体具有不同的信息和可能不同的目标。我们将这些决策设置组织为合作或非合作游戏。我们的目标是设计“游戏规则”，使自私地代表自己行事的代理人达到促进社会理想策略的目的。我们将把“组合拍卖”作为典型的游戏。其次，我们希望研究计算复杂度较低的控制策略，从而排除动态规划或全局优化。这种方法是通过基于模拟或实验的“学习”来降低复杂性，以便估计特定策略的价值。我们将从通信网络的带宽交易中抽取一些例子来测试我们的方法。