id: 05996203
dt: a
an: 05996203
au: Lehman, Joel; Stanley, Kenneth O.
ti: Novelty search and the problem with objectives.
so: Riolo, Rick (ed.) et al., Genetic programming theory and practice IX.
    Selected papers based on the presentations at the 9th workshop, Ann
    Arbor, MI, USA, May 12‒14, 2011. Foreword by Una-Maay O’Reilly. New
    York, NY: Springer (ISBN 978-1-4614-1769-9/hbk;
    978-1-4614-1770-5/ebook). Genetic and Evolutionary Computation, 37-56
    (2011).
py: 2011
pu: New York, NY: Springer
la: EN
cc: 
ut: novelty search; objective-based search; non-objective search; deception;
    evolutionary computation
ci: 
li: doi:10.1007/978-1-4614-1770-5_3
ab: Summary: By synthesizing a growing body ofwork in search processes that are
    not driven by explicit objectives, this paper advances the hypothesis
    that there is a fundamental problem with the dominant paradigm of
    objective-based search in evolutionary computation and genetic
    programming: Most ambitious objectives do not illuminate a path to
    themselves. That is, the gradient of improvement induced by ambitious
    objectives tends to lead not to the objective itself but instead to
    deadend local optima. Indirectly supporting this hypothesis, great
    discoveries often are not the result of objective-driven search. For
    example, the major inspiration for both evolutionary computation and
    genetic programming, natural evolution, innovates through an open-ended
    process that lacks a final objective. Similarly, large-scale cultural
    evolutionary processes, such as the evolution of technology,
    mathematics, and art, lack a unified fixed goal. In addition, direct
    evidence for this hypothesis is presented from a recently-introduced
    search algorithm called novelty search. Though ignorant of the ultimate
    objective of search, in many instances novelty search has
    counter-intuitively outperformed searching directly for the objective,
    including a wide variety of randomly-generated problems introduced in
    an experiment in this chapter. Thus a new understanding is beginning to
    emerge that suggests that searching for a fixed objective, which is the
    reigning paradigm in evolutionary computation and even machine learning
    as a whole, may ultimately limit what can be achieved. Yet the
    liberating implication of this hypothesis argued in this paper is that
    by embracing search processes that are not driven by explicit
    objectives, the breadth and depth of what is reachable through
    evolutionary methods such as genetic programming may be greatly
    expanded.
rv: