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

这是为期三年的连续奖项的第一年。要在复杂、大规模的任务中进行计划，需要复杂而昂贵的知识工程和编程来设计和实施特定于任务的计划器。另一方面，由于固有的组合搜索，一般的规划方法只适用于受约束的小任务。尽管现代规划者，如SIPE，已经取得了一些有价值的进展，将一般的规划方法与手工制作的领域启发式相结合，但这项研究考虑了另一种选择：专注于控制知识的机器学习来指导搜索。特别是，全面实施的神童计划器提供了理想的基础，在其上研究多种学习方法。此前，基于解释的学习被成功地整合到了Prodigy中。这项研究致力于分层规划抽象空间的自动获取、基于案例的派生类比学习以及它们的协同整合。部分可分解领域中的适当抽象提供了重大的性能改进，而自动化抽象消除了费力的手工编码抽象的瓶颈。派生类比提供了极其灵活的基于案例的回放机制，当子目标的解决方案没有转移时，可以退回到一般计划。总而言之，这两种方法应该被证明更有效，抽象为基于案例的内存搜索(那些无法抽象的特征，如瓶颈点或依赖网络的根)提供了关键索引，派生类比加快了抽象空间内的搜索。通过这种控制知识的自动获取，规划者将能够解决日益复杂的计划领域。

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.