Learning by Abstraction and Analogy: Acquiring Planning Expertise in Complex Domains

通过抽象和类比学习：获得复杂领域的规划专业知识

• 批准号: 9022499
• 负责人: Jaime Carbonell
• 金额: $ 18.43万
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1991
• 资助国家: 美国
• 起止时间: 1991-09-15 至 1995-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9022499&HistoricalAwards=false
• 关键词: Learning; Abstraction; Analogy; Acquiring; Planning

This is the first year of a three year continuing award. To plan in complex, large-scale tasks requires elaborate and costly knowledge engineering and programming to design and implement task-specific planners. General planning methods, on the other hand, apply only to small constrained tasks because of the inherent combinatiorial search. Although some worthy inroads have been made by modern planners, such as SIPE, to combine general planning methods with hand-crafted domain heuristic, This research considers a different alternative: focused machine learning of control knowledge to guide search. In particular, the fully-implemented PRODIGY planner presents the ideal substrate on which to investigate multiple learning methods. Previously explanation-based learning was successfully integrated in PRODIGY. This research addresses automated acquisition of abstraction spaces for hierarchical planning, case-based learning with derivational analogy, and their synergistic integration. Proper abstractions in partially-decomposable domains provide major performance improvements, and automated abstraction eliminates the bottleneck of laborious hand-coded abstraction. Derivational analogy provides and extremely flexible case-based replay mechanism, falling back to general planning when solution to subgoals do not transfer. Together, both methods should prove even more effective, with abstraction providing the key indices for case-based memory search (those features that cannot abstracted away, such as bottleneck points or roots of dependency networks), and derivational analogy speeding up search within abstraction spaces. Through this automated acquisition of control knowledge, planners will be able to solve increasingly complex planning domains.

这是连续三年获奖的第一年。 规划 在复杂的、大规模的任务中， 知识工程和编程来设计和实施 特定任务的规划者。 另一方面，一般规划方法 一方面，只适用于小的限制任务，因为 固有组合搜索 虽然一些有价值的进展 现代规划者，如SIPE，已经将联合收割机 一般规划方法与手工制作的领域启发式，这 研究人员考虑了另一种选择：专注的机器 学习控制知识指导搜索。 特别是， 全面实施的PRODIGY计划提供了理想的 研究多种学习方法的基础。 以前以学习为基础的学习成功地融入了 在Prodigy。 这项研究解决了自动采集 分层规划的抽象空间，基于案例的学习 与衍生类比，以及它们的协同整合。 部分可分解域中的适当抽象提供了 主要的性能改进和自动化抽象 消除了费力的手工编码抽象的瓶颈。 派生类比法提供了极其灵活的基于案例的 重放机制，解决方案时退回到总体规划 子目标之间的关系不会转移。 两种方法加在一起， 甚至更有效，抽象提供关键索引 对于基于案例的记忆搜索（那些不能 抽象掉，如瓶颈点或依赖根 网络），和衍生类比加速搜索内 抽象空间 通过这种自动化的收购， 控制知识，规划者将能够解决越来越多的问题， 复杂的规划领域。