权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

RI: Small: High Confidence, Efficient Learning Under Rich Task Specifications

RI：小：丰富任务规格下的高置信度、高效学习

基本信息

批准号：
1617639
负责人：
Scott Niekum
金额：
$ 47万
依托单位：
University of Texas at Austin
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2016
资助国家：
美国
起止时间：
2016-08-01 至 2020-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1617639&HistoricalAwards=false
关键词：
RI Small Confidence Efficient Learning

项目摘要

Artificially intelligent machines such as autonomous vehicles and personal robots are poised to contribute in many economic sectors, but cannot be deployed on a large scale without measurable confidence that they will operate correctly. This is especially true for safety-critical systems in which humans could be injured or infrastructure could be damaged by incorrect behavior. The proposed research will address this key issue by developing methods that allow intelligent agents to learn to perform challenging tasks and adapt to new situations, while simultaneously providing strong guarantees of correctness and safety. Once deployed, these future robotic systems will have broad impacts on society ranging from automating small manufacturing to giving new freedom to disabled and elderly populations through safe and personalized in-home care. The proposed robotics applications will additionally create opportunities for interactive educational K-12 programs to encourage interest in STEM areas, as well as undergraduate and graduate education.Towards these goals, the proposed work focuses on three primary research thrusts: 1) We will design safe learning algorithms that provide theoretical probabilistic satisfaction and data efficiency guarantees over both the expected reward of a policy and its correctness with respect to a high-level specification. 2) In order to account for the gap between theoretical and practical efficiency in learning, we will develop model-based and model-free off-policy evaluation methods that leverage active sampling strategies and bootstrapping to achieve practical efficiency. 3) We will develop hybrid techniques that combine and amplify the advantages of both strong theoretical and efficient practical guarantees. The merit of the proposed algorithms will be systematically evaluated on complex, real-world problems in robotic reconfigurable manufacturing that require learning optimized, yet safe policies with a high degree of confidence in settings with low-to-medium quantities of available data.

自动驾驶汽车和个人机器人等智能机器有望在许多经济领域做出贡献，但如果没有对它们正确运行的可衡量信心，就无法大规模部署。对于安全关键系统尤其如此，在这些系统中，人员可能会受伤，或者基础设施可能会因不正确的行为而损坏。拟议的研究将通过开发方法来解决这一关键问题，这些方法允许智能代理学习执行具有挑战性的任务并适应新的情况，同时提供正确性和安全性的强有力保证。一旦部署，这些未来的机器人系统将对社会产生广泛的影响，从小型制造自动化到通过安全和个性化的家庭护理为残疾人和老年人提供新的自由。拟议的机器人应用将为互动教育K-12计划创造机会，以鼓励对STEM领域的兴趣，以及本科和研究生教育。为了实现这些目标，拟议的工作侧重于三个主要研究方向：第一章我们将设计安全的学习算法，提供理论上的概率满意度和数据效率保证，超过预期的回报的政策和它的对于高级规范的正确性。2)为了解释学习中理论和实践效率之间的差距，我们将开发基于模型和无模型的政策外评估方法，利用主动采样策略和自举来实现实际效率。3)我们将开发联合收割机的混合技术，并放大强大的理论和有效的实践保证的优势。所提出的算法的优点将在机器人可重构制造中的复杂的现实问题上进行系统评估，这些问题需要学习优化，但在具有低到中等数量可用数据的设置中具有高度置信度的安全策略。

项目成果

期刊论文数量（17）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Bayesian Robust Optimization for Imitation Learning

DOI：
发表时间：
2020-07
期刊：
ArXiv
影响因子：
0
作者：
Daniel S. Brown;S. Niekum;Marek Petrik
通讯作者：
Daniel S. Brown;S. Niekum;Marek Petrik

Human Gaze Assisted Artificial Intelligence: A Review

DOI：
10.24963/ijcai.2020/689
发表时间：
2020-07
期刊：
IJCAI : proceedings of the conference
影响因子：
0
作者：
Ruohan Zhang;Akanksha Saran;Bo Liu-;Yifeng Zhu;Sihang Guo;S. Niekum;D. Ballard;M. Hayhoe
通讯作者：
Ruohan Zhang;Akanksha Saran;Bo Liu-;Yifeng Zhu;Sihang Guo;S. Niekum;D. Ballard;M. Hayhoe

Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications