RI: Medium: Hierarchical Decision Making for Physical Agents
RI:中:物理代理的分层决策
基本信息
- 批准号:0904672
- 负责人:
- 金额:$ 120万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2009
- 资助国家:美国
- 起止时间:2009-07-01 至 2013-06-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Research under this award addresses a core problem in the development of intelligent systems: the generation of effective, deliberate activity over substantial time scales in complex state spaces. Whereas current methods for plan generation are limited either to very short plans or to very repetitive behavior in highly structured and simplified environments, the investigators are developing a new mathematical framework for hierarchical decision making. The framework, based on so-called "angelic" nondeterministic semantics for high-level actions, underpins new algorithms capable of generating provably optimal high-level plans without expanding those plans into primitive actions. The algorithms therefore satisfy the "downward refinement property," resolving a problem that has been open for over 30 years at the heart of AI planning research. By combining hierarchical deliberation, both offline and online, with hierarchical reinforcement learning and apprenticeship learning for low-level physical skill acquisition, the research seeks to enable dexterous human-scale robots to operate in unstructured environments such as kitchens, offices, and environments of still greater complexity. The research promises to yield a deeper understanding of, and better tools for, large-scale decision making in general, with implications in the social, governmental, corporate, and military spheres. This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).
该奖项下的研究解决了智能系统开发中的一个核心问题:在复杂状态空间中,在相当长的时间尺度上产生有效的、有意识的活动。鉴于目前的计划生成方法局限于非常短的计划或高度结构化和简化的环境中非常重复的行为,研究人员正在开发一个新的数学框架分层决策。该框架,基于所谓的“天使”不确定性语义的高层次的行动,支持新的算法能够生成可证明的最佳高层次的计划,而无需扩展这些计划到原始的行动。因此,这些算法满足了“向下细化属性”,解决了人工智能规划研究核心30多年来一直存在的问题。通过将离线和在线的分层审议与分层强化学习和学徒学习相结合,以获得低水平的身体技能,该研究旨在使灵巧的人类规模机器人能够在非结构化环境中运行,如厨房,办公室和更复杂的环境。这项研究有望产生更深入的理解,更好的工具,大规模的决策一般,在社会,政府,企业和军事领域的影响。该奖项是根据2009年美国复苏和再投资法案(公法111-5)资助的。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Stuart Russell其他文献
When code isn’t law: rethinking regulation for artificial intelligence
当代码不再是法律:重新思考人工智能监管
- DOI:
10.1093/polsoc/puae020 - 发表时间:
2024 - 期刊:
- 影响因子:9.3
- 作者:
Brian Judge;Mark Nitzberg;Stuart Russell - 通讯作者:
Stuart Russell
It is a complicated thing: leaders’ conceptions of students as partners in the neoliberal university
这是一件复杂的事情:领导者将学生视为新自由主义大学合作伙伴的观念
- DOI:
10.1080/03075079.2018.1482268 - 发表时间:
2018 - 期刊:
- 影响因子:4.2
- 作者:
K. Matthews;Alexander Dwyer;Stuart Russell;Eimear Enright - 通讯作者:
Eimear Enright
Efficacy of a Nurse Practitioner Managed Outpatient Intravenous Diuresis Clinic to Relieve Recurrent Congestion in Patients with Cardiac Amyloidosis
- DOI:
10.1016/j.hrtlng.2020.02.017 - 发表时间:
2020-03-01 - 期刊:
- 影响因子:
- 作者:
Julianne Chambers;Abby Cummings;Kimberly Cuomo;Johana Fajardo;Falisha Fitts;Nisha Gilotra;Daniel Judge;Kathryn Menzel;Parker Rhodes;Sarah Riley;Stuart Russell - 通讯作者:
Stuart Russell
AI weapons: Russia’s war in Ukraine shows why the world must enact a ban
人工智能武器:俄罗斯在乌克兰的战争表明为什么世界必须颁布禁令
- DOI:
10.1038/d41586-023-00511-5 - 发表时间:
2023 - 期刊:
- 影响因子:64.8
- 作者:
Stuart Russell - 通讯作者:
Stuart Russell
PROTEINURIA IN PATIENTS RECEIVING LEFT VENTRICULAR ASSIST DEVICES IS HIGHLY ASSOCIATED WITH RENAL FAILURE AND MORTALITY
- DOI:
10.1016/s0735-1097(17)34088-3 - 发表时间:
2017-03-21 - 期刊:
- 影响因子:
- 作者:
Rahat Muslem;Kadir Caliskan;Sakir Akin;Dennis A. Hesselink;Glenn Whitman;Ryan Tedford;Ad J.J.C. Bogers;Olivier Manintveld;Stuart Russell - 通讯作者:
Stuart Russell
Stuart Russell的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Stuart Russell', 18)}}的其他基金
Conference: Inaugural Workshop on Provably Safe and Beneficial AI (PSBAI)
会议:首届可证明安全和有益的人工智能 (PSBAI) 研讨会
- 批准号:
2230996 - 财政年份:2022
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
REU Site: Computer Science in the Interest of Society (CSIS)
REU 网站:造福社会的计算机科学 (CSIS)
- 批准号:
0754843 - 财政年份:2008
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
KDI: Learning Complex Motor Tasks in Natural and Artifical Systems
KDI:学习自然和人工系统中的复杂运动任务
- 批准号:
9873474 - 财政年份:1998
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Learning Complex Probabilistic Models from Data
从数据中学习复杂的概率模型
- 批准号:
9634215 - 财政年份:1997
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
Real-Time Intelligent Control for an Automated Taxi
自动出租车的实时智能控制
- 批准号:
9309729 - 财政年份:1993
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Research on Real-Time Decision Making: The Ralph Project
实时决策研究:拉尔夫项目
- 批准号:
9211512 - 财政年份:1993
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
Japanese Language Award for Gary Ogasawara
加里·小笠原日语奖
- 批准号:
9207213 - 财政年份:1992
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: Solving Chess with Probabilistic Planning and Control
合作研究:用概率规划和控制解决国际象棋问题
- 批准号:
9024557 - 财政年份:1991
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
PYI: Architectures and Algorithms for Autonomous Intelligent Systems
PYI:自主智能系统的架构和算法
- 批准号:
9058427 - 财政年份:1990
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
Research on Real-Time Decision Making: The RALPH Project
实时决策研究:RALPH 项目
- 批准号:
8903146 - 财政年份:1989
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
相似海外基金
Collaborative Research: CyberTraining: Implementation: Medium: Training Users, Developers, and Instructors at the Chemistry/Physics/Materials Science Interface
协作研究:网络培训:实施:媒介:在化学/物理/材料科学界面培训用户、开发人员和讲师
- 批准号:
2321102 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
RII Track-4:@NASA: Bluer and Hotter: From Ultraviolet to X-ray Diagnostics of the Circumgalactic Medium
RII Track-4:@NASA:更蓝更热:从紫外到 X 射线对环绕银河系介质的诊断
- 批准号:
2327438 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: Topological Defects and Dynamic Motion of Symmetry-breaking Tadpole Particles in Liquid Crystal Medium
合作研究:液晶介质中对称破缺蝌蚪粒子的拓扑缺陷与动态运动
- 批准号:
2344489 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: AF: Medium: The Communication Cost of Distributed Computation
合作研究:AF:媒介:分布式计算的通信成本
- 批准号:
2402836 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
Collaborative Research: AF: Medium: Foundations of Oblivious Reconfigurable Networks
合作研究:AF:媒介:遗忘可重构网络的基础
- 批准号:
2402851 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
Collaborative Research: CIF: Medium: Snapshot Computational Imaging with Metaoptics
合作研究:CIF:Medium:Metaoptics 快照计算成像
- 批准号:
2403122 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Differentiable Hardware Synthesis
合作研究:SHF:媒介:可微分硬件合成
- 批准号:
2403134 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Enabling Graphics Processing Unit Performance Simulation for Large-Scale Workloads with Lightweight Simulation Methods
合作研究:SHF:中:通过轻量级仿真方法实现大规模工作负载的图形处理单元性能仿真
- 批准号:
2402804 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: CIF-Medium: Privacy-preserving Machine Learning on Graphs
合作研究:CIF-Medium:图上的隐私保护机器学习
- 批准号:
2402815 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Tiny Chiplets for Big AI: A Reconfigurable-On-Package System
合作研究:SHF:中:用于大人工智能的微型芯片:可重新配置的封装系统
- 批准号:
2403408 - 财政年份:2024
- 资助金额:
$ 120万 - 项目类别:
Standard Grant