Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Layered Learning

Peter Stone and Manuela Veloso. Layered Learning. In Ramon López de Mántaras and Enric Plaza, editors, Machine Learning: ECML 2000 (Proceedings of the Eleventh European Conference on Machine Learning), pp. 369–381, Springer Verlag, Barcelona,Catalonia,Spain, May/June 2000.

Download

[PDF]152.3kB  [postscript]362.7kB  

Abstract

This paper presents layered learning, a hierarchical machine learning paradigm. Layered learning applies to tasks for which learning a direct mapping from inputs to outputs is intractable with existing learning algorithms. Given a hierarchical task decomposition into subtasks, layered learning seamlessly integrates separate learning at each subtask layer. The learning of each subtask directly facilitates the learning of the next higher subtask layer by determining at least one of three of its components: (i) the set of training examples; (ii) the input representation; and/or (iii) the output representation. We introduce layered learning in its domain-independent general form. We then present a full implementation in a complex domain, namely simulated robotic soccer.

BibTeX Entry

@InCollection(ECML2000,
        Author="Peter Stone and Manuela Veloso",
        Title="Layered Learning",
        booktitle="Machine Learning: ECML 2000 (Proceedings of the Eleventh European Conference on Machine Learning)",
        editor="Ramon L\'{o}pez de M\'{a}ntaras and Enric Plaza",
        month="May/June",
        Year="2000",
        address="Barcelona,Catalonia,Spain",
        publisher="Springer Verlag",
        pages="369--381",
        abstract={
                 This paper presents layered learning, a hierarchical
                 machine learning paradigm.  Layered learning applies
                 to tasks for which learning a direct mapping from
                 inputs to outputs is intractable with existing
                 learning algorithms. Given a hierarchical task
                 decomposition into subtasks, layered learning
                 seamlessly integrates separate learning at each
                 subtask layer. The learning of each subtask directly
                 facilitates the learning of the next higher subtask
                 layer by determining at least one of three of its
                 components: (i) the set of training examples; (ii)
                 the input representation; and/or (iii) the output
                 representation. We introduce layered learning in its
                 domain-independent general form. We then present a
                 full implementation in a complex domain, namely
                 simulated robotic soccer.
        },
)

Generated by bib2html.pl (written by Patrick Riley ) on Wed Sep 24, 2014 22:15:10