This article presents a completely automated approach to generating abstractions for planning. The abstractions are generated using a tractable, domain-independent algorithm whose only input is the definition of a problem to be solved and whose output is an abstraction hierarchy that is tailored to the particular problem. The algorithm generates abstraction hierarchies by dropping literals from the original problem definition. It forms abstractions that satisfy the ordered monotonicity property, which guarantees that the structure of an abstract solution is not changed in the process of refining it. The algorithm for generating abstractions is implemented in a system called alpine, which generates abstractions for a hierarchical version of the prodigy problem solver. The abstractions generated by alpine are tested in multiple domains on large problem sets and are shown to produce shorter solutions with significantly less search than planning without using abstraction. 1 1 ...

The use of abstraction in problem solving is an effective approach to reducing search, but finding good abstractions is a difficult problem, even for people. This paper identifies a criterion for selecting useful abstractions, describes a tractable algorithm for generating them, and empirically demonstrates that the abstractions reduce search. The abstraction learner, called alpine,isinte- grated with the prodigy problem solver [Minton et al., 1989b, Carbonell et al.,1991] and has been tested on large problem sets in multiple domains.

It has long been recognized that hierarchical problem solving can be used to reduce search. Yet, there has been little analysis of the problemsolving method and few experimental results. This paper provides the first comprehensive analytical and empirical demonstrations of the effectiveness of hierarchical problem solving. First, the paper shows analytically that hierarchical problem solving can reduce the size of the searchspace from exponential to linear in the solution length and identifies a sufficient set of assumptions for such reductions in search. Second, it presents empirical results both in a domain that meets all of these assumptions as well as in domains in which these assumptions do not strictly hold. Third, the paper explores the conditions under which hierarchical problem solving will be effective in practice.

Semantic query optimization can dramatically speed up database query answering by knowledge intensive reformulation. But the problem of how to learn required semantic rules has not previously been solved. This paper describes an approach using an inductive learning algorithm to solve the problem. In our approach, learning is triggered by user queries and then the system induces semantic rules from the information in databases. The inductive learning algorithm used in this approach can select an appropriate set of relevant attributes from a potentially huge number of attributes in real-world databases. Experimental results demonstrate that this approach can learn sufficient background knowledge to reformulate queries and provide a 57 percent average performance improvement. 1 INTRODUCTION Speeding up a system's performance is one of the major goals of machine learning. Explanation-based learning is typically used for speedup learning, while applications of inductive learning are usual...

Existing plan synthesis approaches in artificial intelligence fall into two categories -- domain independent and domain dependent. The domain independent approaches are applicable across a variety of domains, but may not be very efficient in any one given domain. The domain dependent approaches need to be (re)designed for each domain separately, but can be very efficient in the domain for which they are designed. One enticing alternative to these approaches is to automatically synthesize domain independent planners given the knowledge about the domain and the theory of planning. In this paper, we investigate the feasibility of using existing automated software synthesis tools to support such synthesis. Specifically, we describe an architecture called CLAY in which the Kestrel Interactive Development System (KIDS) is used to derive a domain-customized planner through a semi-automatic combination of a declarative theory of planning, and the declarative control knowledge specific to a giv...

The query reformulation approach (also called semantic query optimization) takes advantage of the semantic knowledge about the contents of databases for optimization. The basic idea is to use the knowledge to reformulate a query into a less expensive yet equivalent query. Previous work on semantic query optimization has shown the cost reduction that can be achieved by reformulation, we further point out that when applied to distributed multidatabase queries, the reformulation approach can reduce the cost of moving intermediate data from one site to another. However, a robust and efficient method to discover the required knowledge has not yet been developed. This paper presents an example-guided, data-driven learning approach to acquire the knowledge needed in reformulation. We use example queries to guide the learning to capture the database usage pattern. In contrast to the heuristic-driven approach proposed by Siegel, the data-driven approach is more likely to learn the re...

Many applications of knowledge discovery and data mining such as rule discovery for semantic query optimization, database integration and decision support, require the knowledge to be consistent with data. However, databases usually change over time and makemachine-discovered knowledge inconsistent. Useful knowledge should be robust against database changessothatitisunlikely to become inconsistentafter database changes. This paper defines this notion of robustness in the context of relational databases that contain multiple relations and describes how robustness of first-order Horn-clause rules can be estimated and applied in knowledge discovery.Our experiments show that the estimation approach can accurately predict the robustness of a rule.

Adding knowledge to a knowledge-based system is not monotonically beneficial. We discuss and experimentally validate this observation in the context of CABINS, a system that learns control knowledge for iterative repair in ill-structured optimization problems. In CABINS, situation-dependent user's decisions that guide the repair process are captured in cases together with contextual problem information. During iterative revision in CABINS, cases are exploited for both selection of repair actions and evaluation of repair results. In this paper, we experimentally demonstrated that unfiltered learned knowledge can degrade problem solving performance. We developed and experimentally evaluated the effectiveness of a set of knowledge filtering strategies that are designed to increase problem solving efficiency of the intractable iterative optimization process without sacrificing solution quality. These knowledge filtering strategies utilize progressive case base retrievals and failure inform...

CABINS is a framework of modeling an optimization task in illstructured domains. In such domains, neither systems nor human experts possess the exact model for guiding optimization. And the user's model of optimality is subjective and situation-dependent. CABINS optimizes a solution through iterative revision using case-based reasoning. In CABINS, task structure analysis was adopted for creating an initial model of the optimization task. Generic vocabularies found in the analysis were specialized into case feature descriptions for application problems. Extensive experimentation on job shop scheduling problems has shown that CABINS can operationalize and improve the model through the accumulation of cases. A knowledge-based system (or an expert system) has explicit representation of knowledge in addition to the inference mechanism that operates on the