Steven Minton

Goal-Driven Learning

Using Multi-Strategy Learning to Improve Planning E ciency and Quality

viii Chapter

Constraint-Based Generalization: Learning Game-Playing Plans From Single Examples

Constraint-based Generalization is a technique for deducing generalizations from a single example. We show how this technique can be used for learning tactical combinations in games and discuss an implementation which learns forced wins in tic-tat-toe, go-moku, and chess.’

Selective Sampling with Co-Testing: Preliminary Results

We present a novel approach to selective sampling, cotesting, which can be applied to problems with redundant views (i.e., problems with multiple disjoint sets of attributes that can be used for learning). The main idea behind co-testing consists of selecting the queries among the unlabeled examples on which the existing

Derivational analogy : a theory of reconstructive problem solving and expertise acquisition

Derivational analogy, a method of solving problems based on the transfer of past experience to new probiem situations, is d iscussed in the context of other general approaches to problem solving. T h e exper ience transfer process consists of recreating lines of reasoning, including decision sequences and accompanying justifications, that proved effective in solving particular problems requirin...