Evolution of sustained foraging in three-dimensional environments with physics

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@Article{Chaumont:2016:GPEM,
  author =       "Nicolas Chaumont and Christoph Adami",
  title =        "Evolution of sustained foraging in three-dimensional
                 environments with physics",
  journal =      "Genetic Programming and Evolvable Machines",
  year =         "2016",
  volume =       "17",
  number =       "4",
  pages =        "359--390",
  month =        dec,
  keywords =     "genetic algorithms, genetic programming, alife,
                 Sustainable foraging, 3D environment, Physics
                 simulator, Body-brain co-evolution, Foraging map EVO",
  ISSN =         "1389-2576",
  DOI =          "doi:10.1007/s10710-016-9270-z",
  size =         "32 pages",
  abstract =     "Artificially evolving foraging behavior in simulated
                 articulated animals has proved to be a notoriously
                 difficult task. Here, we co-evolve the morphology and
                 controller for virtual organisms in a three-dimensional
                 physical environment to produce goal-directed
                 locomotion in articulated agents. We show that
                 following and reaching multiple food sources can evolve
                 de novo, by evaluating each organism on multiple food
                 sources placed on a basic pattern that is gradually
                 randomized across generations. We devised a strategy of
                 evolutionary ``staging'', where the best organism from
                 a set of evolutionary experiments using a particular
                 fitness function is used to seed a new set, with a
                 fitness function that is progressively altered to
                 better challenge organisms as evolution improves them.
                 We find that an organism's efficiency at reaching the
                 first food source does not predict its ability at
                 finding subsequent ones because foraging efficiency
                 crucially depends on the position of the last food
                 source reached, an effect illustrated by ``foraging
                 maps'' that capture the organism's controller state,
                 body position, and orientation. Our best evolved
                 foragers are able to reach multiple food sources over
                 90percent of the time on average, a behavior that is
                 key to any biologically realistic simulation where a
                 self-sustaining population has to survive by collecting
                 food sources in three-dimensional, physical
                 environments.",
  notes =        "Founder organisms

                 'The genome description is specified in a script-like
                 fashion'

                 'The types are defined by the manner in which they
                 process inputs: Sum, Product, Divide, SumThreshold,
                 GreaterThan, SignOf, Min, Max, Abs, If, Interpolate,
                 Sin, Cos, Atan, Log, Exp, Sigmoid, Integrate,
                 Differentiate, Smooth, Memory, Wave, Saw, and
                 constant.'",
}

Genetic Programming entries for Nicolas Chaumont Christoph Adami

Citations