RI: Small: Concept Formation in Partially Observable Domains

RI：小：部分可观察领域中的概念形成

• 批准号: 1813223
• 负责人: Cynthia Matuszek
• 金额: $ 40万
• 依托单位: University of Maryland Baltimore County
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-01 至 2022-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1813223&HistoricalAwards=false
• 关键词: RI; Small; Concept; Formation; Partially

This research focuses on providing artificial intelligence (AI) systems with ways to represent knowledge about a problem domain, by creating descriptions of its observations over time. This work is important because the AI systems can transfer their knowledge from one problem domain to another, enabling them to learn complex behaviors in different environments over time. In addition, the learned representation provides a basis for creating explanations of the agent's behavior, a capability that is becoming increasingly important as AI agents are being applied to more aspects of our daily lives. The resulting learning transfer methods we will create are applicable to a wide variety of problems of interest to the broader AI community, including explainable systems, intelligent wearable computing, and robotic assistants in real world environments.The agents enabled by this work will automatically extract concepts (high-level descriptors) from perceptions, construct a hierarchy of experiences, and record learned behaviors over this structure, by extending existing reinforcement learning methods with these novel representations. Concepts serve as simple, portable, efficient packets of hierarchical knowledge that can be learned in parallel. Our novel contribution, concept-based memory, extends previous work on concept formation to identify useful properties of the domain that are not directly observable in all contexts, expanding the agent's world model and improving performance in partially observable domains. Concept-based memory provides a process for creating multi-layered abstract representations of a domain and the tasks in the domain, enabling learning transfer across multiple tasks, and providing a basis for creating explanations of learned behaviors. Our method for concept formation in reinforcement learning domains, called concept-aware feature extraction (CAFE), produces concept-lattice representations that permit knowledge learned from one task to be applied to a new problem by identifying the appropriate level of generalization for common knowledge between the tasks. We will enable scalability by integrating CAFE with abstract Markov decision processes (AMDPs) and by developing heuristic pruning methods that reduce the branching factor of the concept latticesThis award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

本研究的重点是为人工智能（AI）系统提供表示问题领域知识的方法，通过创建其随时间的观察描述。这项工作很重要，因为人工智能系统可以将他们的知识从一个问题领域转移到另一个问题领域，使他们能够在不同的环境中学习复杂的行为。此外，学习表征为创建代理行为的解释提供了基础，随着AI代理被应用于我们日常生活的更多方面，这种能力变得越来越重要。我们将创建的学习迁移方法适用于广泛的人工智能社区感兴趣的各种问题，包括可解释系统、智能可穿戴计算和现实世界环境中的机器人助手。这项工作支持的智能体将自动从感知中提取概念（高级描述符），构建经验层次，并通过使用这些新表征扩展现有的强化学习方法，在此结构上记录学习行为。概念是简单、便携、高效的分层知识包，可以并行学习。我们的新贡献，基于概念的记忆，扩展了之前关于概念形成的工作，以识别在所有上下文中不能直接观察到的领域的有用属性，扩展了智能体的世界模型并提高了部分可观察领域的性能。基于概念的记忆提供了一个创建领域和领域内任务的多层抽象表示的过程，实现了跨多个任务的学习迁移，并为创建学习行为的解释提供了基础。我们在强化学习领域的概念形成方法，称为概念感知特征提取（CAFE），产生概念格表示，通过识别任务之间公共知识的适当泛化水平，允许从一个任务中学习的知识应用于新问题。我们将通过将CAFE与抽象马尔可夫决策过程（AMDPs）集成，并通过开发减少概念格分支因子的启发式修剪方法来实现可扩展性。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Neural Variational Learning for Grounded Language Acquisition

• DOI: 10.1109/ro-man50785.2021.9515374
• 发表时间: 2021-07
• 期刊: 2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)
• 作者: Nisha Pillai;Cynthia Matuszek;Francis Ferraro

Sampling Approach Matters: Active Learning for Robotic Language Acquisition

• DOI: 10.1109/bigdata50022.2020.9378415
• 发表时间: 2020-11
• 期刊: 2020 IEEE International Conference on Big Data (Big Data)
• 作者: Nisha Pillai;Edward Raff;Francis Ferraro;Cynthia Matuszek

Planning with Abstract Learned Models While Learning Transferable Subtasks

在学习可转移子任务的同时使用抽象学习模型进行规划

• DOI: 10.1609/aaai.v34i06.6555
• 发表时间: 2020
• 期刊: Proceedings of the AAAI Conference on Artificial Intelligence
• 作者: Winder, John;Milani, Stephanie;Landen, Matthew;Oh, Erebus;Parr, Shane;Squire, Shawn;desJardins, Marie;Matuszek, Cynthia
• 通讯作者: Matuszek, Cynthia

Practical Cross-modal Manifold Alignment for Robotic Grounded Language Learning

• DOI: 10.1109/cvprw53098.2021.00177
• 发表时间: 2021-06
• 期刊: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
• 作者: A. Nguyen;Frank Ferraro;Cynthia Matuszek

A Spoken Language Dataset of Descriptions for Speech-Based Grounded Language Learning

• DOI: 10.13016/m2bmhe-tmzc
• 发表时间: 2021-06
• 作者: Gaoussou Youssouf Kebe;Padraig Higgins;Patrick Jenkins;Kasra Darvish;Rishabh Sachdeva;Ryan Barron