processes, bodily form, and sensorimotor capabilities.
Evolutionary simulations automate the process of
finding and optimizing such mind-body parameteri-
zations. Traditionally, evolutionary simulations prop-
agate species that maximize a quantitative “fitness”
function. Natural evolution admits no such fitness
function, and to simulate it requires a slightly dif-
ferent treatment than traditional genetic algorithms.
Instead of optimizing genomes to maximize a pre-
defined fitness function, “naturalistic simulations” re-
quire agents to prove their reproductive fitness in-
dependently, encouraging the evolution of intelligent
autonomy. If the selected AGI framework is flexible
and the simulated environment is sufficiently rich, the
resulting species should exhibit interesting adaptive
behaviors.
2 RELATED WORKS
Evolving autonomous machines is not a novel con-
cept; one of the earliest and most famous attempts at
elaborating this idea is mathematician John von Neu-
mann’s self-reproducing automaton. He hypothesized
a baseline level of complexity that allows the evolu-
tion of increasingly complex systems (von Neumann,
1966, p.78-80), realized by the three sub-processes
of reproduction and evolution: duplication, modifi-
cation, and instantiation of genomes. In his context,
the automaton system itself performs all three sub-
processes, including modifying the genome.
Though “AGI” is often construed as human-level
intelligence, our simulated agents will be more like
primitive animals than humans. They will not be ca-
pable of manually modifying their own genes; the
task of genomic modification belongs to the simula-
tion. As long as the agents handle reproduction au-
tonomously, the simulation design will handle the ac-
tual evolutionary processes behind the scenes. Game
engines such as Unity3D (Juliani et al., 2018) are the
ideal simulator software since they facilitate building
simulated physical worlds and arbitrary scripting.
(Holland, 1992) formalizes a methodology for ap-
proaching so-called “problems of adaptation”. This
work led to the popularization of genetic algorithms,
an evolutionary computing method by which to ex-
plore a space of evolving structures using concep-
tions of fitness, genetics, and reproduction. Genetic
algorithms are arguably the best approach for simu-
lating natural evolution, because they implement the
general principles that make natural genetics adap-
tive. Namely, genetic algorithms use “survival of the
fittest”, recombination, and random mutation to ex-
plore a certain space of evolving structures in search
of more optimal (i.e., “fit”) structures.
(Sims, 1994a; Sims, 1994b) use Holland’s genetic
algorithms to evolve various agent bodies and their
neural networks, including by facing the agents off
in direct physical competition (Sims, 1994a). The
agents are encoded using a highly compact and flexi-
ble genetic language in the form of directed network
graphs. Physical body parts contain sensors (e.g.,
contact sensor, light sensor) or actuators (e.g., rota-
tional force on joints), and each body part has a neural
circuit allowing for some level of distributed control.
(Soros and Stanley, 2014) propose four neces-
sary conditions for open-ended artificial evolution:
1&2.) new and existing individuals must be required
to meet some non-trivial minimum criterion (MC) be-
fore they can reproduce, so species do not degener-
ate into trivial-behavior automatons, 3.) individuals
must autonomously meet that MC, 4.) the complex-
ity of the individual’s genotype can grow unrestricted.
The naturalistic MC is the ability to reproduce, in-
cluding the requisite apparatus and motivation (Soros
and Stanley, 2014, p.2-3).
(Stranneg
˚
ard et al., 2020) establishes a “generic
animats” framework in which simulated organisms
are defined by homeostatic variables, sensors, pat-
terns, motor, actions, and reflexes. (Stranneg
˚
ard et al.,
2021) formalizes ecosystems containing inanimate
objects and organisms that have unique properties
(e.g., digital “animals” have energy levels, environ-
mental objects have certain chemical reactivity) and
common properties (e.g., all objects have mass).
For this discussion we will assume Wang’s work-
ing definition of intelligence: “the capacity of a
system to adapt to its environment with insufficient
knowledge and resources” (Wang, 1995; Wang, 2019,
p.13; p.17-18). According to this definition, the min-
imum requirement for intelligence is to operate un-
der an Assumption of Insufficient Knowledge and Re-
sources (AIKR). A system operating under AIKR: 1.)
uses constant computational resources, 2.) works in
real-time, and 3.) is open to new tasks regardless of
their content. In plainer terms, such a system is like a
living organism: it is a fast, finite agent that operates
effectively even under uncertainty, while constantly
learning from its experience so as to better achieve its
goals. Cognitive frameworks designed with AIKR in
mind may be flexible enough to permit the evolution
of complex adaptive behaviors.
Designing Naturalistic Simulations for Evolving AGI Species
297