CAREER: Value Function Approximation for Control of Complex Systems
CAREER: Value Function Approximation for Control of Complex Systems
批准号:
9985229
负责人:
Benjamin Van Roy
金额:
$20.0万
依托单位:
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2000
资助国家:
美国
项目状态:
已结题
起止时间:
2000-04-01 至 2005-09-30
中文摘要
9985229VanRoyThis建议的研究致力于发展精简和可靠的计算方法的价值函数近似。 一个成功的结果将是近似算法,这是广泛访问和有效的控制复杂systems.Proposal方法建立在工作领域的神经动态规划,有时被称为“近似动态规划”或“强化学习”。“将要开发的算法基于近似值迭代、时间差、学习和线性规划。 还将探讨一种“特征选择”的方法,其中涉及与简化问题有关的价值函数的使用。为了促进对正在开发的方法的务实看法,并为评估想法提供一个试验平台,选择了两个应用程序在项目中发挥不可或缺的作用:动态风险管理和多类排队网络的控制。这个项目的教育部分包括一个新的研究生水平的神经动力学课程编程与当前课程的重新调整一起,以更加强调计算,促进对系统变得更加复杂时使用近似值的欣赏,并促进对许多学科中随机控制问题的统一看法。
英文摘要
9985229Van RoyThis proposed research is devoted to the development of streamlined and reliable computational methods for value function approximation. A successful outcome would be approximation algorithms that are widely-accessible and effective in the control of complex systems.Proposed approximation methods build on work in the area of neuro-dynamic programming which is sometimes called "Approximate Dynamic Programming" or "Reinforcement Learning." Algorithms that will be developed are based on approximate value iteration, temporal-difference, learning, and linear programming. A method for "feature selection" involving the use of value functions associated with simplified problems will also be explored.To promote a pragmatic view of methods under development, and to provide a testbed for evaluation of ideas, two applications have been chosen to play integral roles in the project: dynamic risk management and the control of multiclass queuing networks.The educational component of this project includes a new graduate level course on neurodynamic programming together with a realignment of current courses to incorporate a greater emphasis on computation, to foster an appreciation for the use of approximations when system become more complex, and to promote a unified view of stochastic control problems across many disciplines.***
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Directed Regression
-
批准号:0968707
-
项目类别:Standard Grant
-
资助金额:$33.0万
-
财政年份:2010
-
负责人:Benjamin Van Roy
-
依托单位:
ITR: Axioms and Algorithms for Reputation
-
批准号:0428868
-
项目类别:Continuing Grant
-
资助金额:$120.0万
-
财政年份:2004
-
负责人:Benjamin Van Roy
-
依托单位:
国内基金
海外基金
基于时间序列间分位相依性(quantile dependence)的风险值(Value-at-Risk)预测模型研究
-
批准号:71903144
-
项目类别:青年科学基金项目
-
资助金额:17.0万元
-
批准年份:2019
-
负责人:张申
-
依托单位: