RI: Medium: Collaborative Research: Optimizing Policies for Service Organizations in Complex Structured Domains
RI: Medium: Collaborative Research: Optimizing Policies for Service Organizations in Complex Structured Domains
批准号:
0964705
负责人:
Prasad Tadepalli
金额:
$58.17万
依托单位:
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
2010
资助国家:
美国
项目状态:
已结题
起止时间:
2010-07-01 至 2015-06-30
中文摘要
该项目使用模拟器和概率行动模型研究了一类重要的复杂结构化规划域,称为“服务域”。服务领域的例子包括优化典型城市的应急响应,安排医院的医生和护士,管理典型办公室的任务,以最佳方式将产品从配送中心送到商店。这些领域具有关系结构、并行行为、多时间尺度决策、外生事件以及对人类可解释的解决方案的需求等特点,这使得它们具有很高的挑战性。该项目通过多种技术为服务领域开发可扩展和原则性的规划算法,包括新的多时间尺度优化的分层框架、基于新的无模型的基于模拟的规划算法和基于一阶决策图的基于模型的规划。这些技术通过与俄勒冈州科瓦利斯消防部门的合作,被应用到优化城市火灾和应急反应的现实世界问题上。该项目的成果包括解决服务领域的新算法和框架,紧急响应领域算法的原型实现,以及用于研究的服务领域的新试验台。这项工作的更广泛影响包括更具成本效益的应急系统,以及开发新的面向研究的课程、教程和关于服务领域下一代决策支持系统的特别讲习班。
英文摘要
This project studies an important class of complex structured planning domains called ``service domains'' using simulators and probabilisticaction models. Examples of service domains include optimizing emergency response in a typical city, scheduling doctors and nurses in a hospital, administering tasks in a typical office, optimally delivering products to shops from distribution centers. These domains share many characteristics such as relational structure, parallel actions, multi-time-scale decision making, exogenous events, and the need for human interpretable solutions that make them highly challenging.The project develops scalable and principled planning algorithms for service domains through a variety of techniques including a novelhierarchical framework of multi-time-scale optimization, newmodel-free simulation-based planning algorithms, and model-based planning via composition of first-order decision diagrams. These techniques are applied to the real-world problem of optimizing the fire and emergency response in cities through a collaborationwith the fire department of Corvallis, Oregon. The results of the project include new algorithms and frameworks to solve service domains, prototype implementations of the algorithmsin the emeregency response domain, and new testbeds of service domains for research. The broader impact of the work includes more cost-effective emergency response systems, and development of new research-oriented courses, tutorials and special workshops on the next generation decision support systems for service domains.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
RI: Small: Integrating Learning and Search for Structured Prediction
-
批准号:1219258
-
项目类别:Standard Grant
-
资助金额:$45.0万
-
财政年份:2012
-
负责人:Prasad Tadepalli
-
依托单位:
Relational Reinforcement Learning
-
批准号:0329278
-
项目类别:Continuing Grant
-
资助金额:$41.16万
-
财政年份:2003
-
负责人:Prasad Tadepalli
-
依托单位:
Average Reward Reinforcement Learning: Scaling up
-
批准号:0098050
-
项目类别:Continuing Grant
-
资助金额:$36.87万
-
财政年份:2001
-
负责人:Prasad Tadepalli
-
依托单位:
Average Reward Reinforcement Learning
-
批准号:9520243
-
项目类别:Continuing Grant
-
资助金额:$22.49万
-
财政年份:1995
-
负责人:Prasad Tadepalli
-
依托单位:
Tradeoffs in Learning and Planning
-
批准号:9111231
-
项目类别:Standard Grant
-
资助金额:$7.0万
-
财政年份:1991
-
负责人:Prasad Tadepalli
-
依托单位:
海外基金