{{Short description|AI life simulation using evolutionary algorithms}} {{Multiple issues| {{No footnotes|date=June 2022}} {{More citations needed|date=September 2024}} }} {{Infobox software | name = | logo = <!-- Image name is enough. --> | logo alt = | logo caption = | screenshot = Polyworld.gif | screenshot size = 300px | screenshot alt = | caption = Polyworld Screenshot, 1994 | collapsible = <!-- Any text here will collapse the screenshot. --> | author = | developer = | released = <!-- {{Start date and age|YYYY|MM|DD|df=yes/no}} --> | discontinued = <!-- Set to yes if software is discontinued, otherwise omit. --> | ver layout = <!-- simple (default) or stacked --> | latest release version = 2.6 | latest release date = Feb 2015 <!-- {{Start date and age|YYYY|MM|DD|df=yes/no}} --> | latest preview version = | latest preview date = <!-- {{Start date and age|YYYY|MM|DD|df=yes/no}} --> | repo = <!-- {{URL|example.org}} --> | programming language = C++, Python | engine = <!-- or engines --> | operating system = | platform = | included with = | size = | language = | language count = <!-- Number only --> | language footnote = | genre = | license = Apple Public Source License | alexa = | website = <!-- {{URL|example.org}} --> | standard = | AsOf = }} '''Polyworld''' is a cross-platform (Linux, Mac OS X) program written by Larry Yaeger to evolve Artificial Intelligence through natural selection and evolutionary algorithms.
It uses the Qt graphics toolkit and OpenGL to display a graphical environment in which a population of trapezoid agents search for food, mate, have offspring, and prey on each other. The population is typically only in the hundreds, as each individual is rather complex and the environment consumes considerable computer resources. The graphical environment is necessary since the individuals actually move around the 2-D plane and must be able to "see." Since some basic abilities, like eating carcasses or randomly generated food, seeing other individuals, mating or fighting with them, etc., are possible, a number of interesting behaviours have been observed to spontaneously arise after prolonged evolution, such as cannibalism, predators and prey, and mimicry.
Each individual makes decisions based on a neural net using Hebbian learning; the neural net is derived from each individual's genome. The genome does not merely specify the wiring of the neural nets, but also determines their size, speed, color, mutation rate and a number of other factors. The genome is randomly mutated at a set probability, which are also changed in descendant organisms.<ref>{{Cite web |last=Yaeger |first=Larry |title=Yeager: Computational Genetics, Physiology, Metabolism, Neural Systems, Learning, Vision, and Behavior |url=https://shinyverse.org/larryy/Yaeger.ALife3.pdf |access-date=July 26, 2024 |website=}}</ref>
==References== {{reflist}}
==External links== *[https://github.com/polyworld/polyworld Github entry] *[https://shinyverse.org/larryy/Polyworld.html Yaeger's page on Polyworld] *[https://www.youtube.com/watch?v=_m97_kL4ox0 Google TechTalk about Polyworld]
Category:Applications of artificial intelligence Category:Artificial life Category:Digital organisms
{{science-software-stub}}