Re: using game programming to develop animal-equivalent agi

From: Ben Goertzel (
Date: Thu Mar 16 2006 - 06:17:43 MST


> start with an immersive 3D gameworld with a simulation engine running
> newtonian physics and genetic biology. there must be hundreds of
> running codebases today that could be merged to provide this.

If you want to experiment with this in practice, I suggest you may
want to join the AGISim project, a spin-off of the Novamente AGI
project which is involved with creating an open-source 3D environment
specifically for AGI development, based on the open-source
CrystalSpace game engine. The Sourceforge page for AGISim is here:

The one to email if you're interested in becoming involved is Ari
Heljakka, "heljakka at iki dot fi"

For example, one task that has not yet been done is to integrate the
ODE physics engine into AGISim (it already words with CrystalSpace so
this is not a fundamentally hard task, we just haven't gotten around
to it yet).

However, this kind of physics engine is much too simplistic to
support any kind of realistic physics-based genetics. In fact, we
don't yet know how to make a physics engine that supports
physics-based genetics, because no one yet understands the physics
underlying protein-folding very well.

Nevertheless, I think one could probably make an interesting
artificial-genetics-based artificial life framework within AGISim,
which would be nifty because then the adaptive, evolving artificial
organisms could interact with humanoids controlled by Novamente ;-)

Regarding your more general point, I doubt very much that AGI is going
to emerge spontaneously from AI bots inside computer games. This is
for a number of reasons, including

* the first AGI is probably going to push the limits of computing
capability, requiring a network of machines with a lot of RAM, whereas
AI's running in games need to work on the kind of hardware setup a
typical gamer can afford

* a baby AGI is going to be very stupid and boring to play with, which
is not a great gaming experience. Note that Creatures, while cool,
was never a very popular game; and Black and White 2 has much less
focus on teaching the AI's than Black and White 1 did. I see no
evidence that teaching AI babies is actually considered a fun gaming
experience by any substantial portion of the gaming market.

I do think that gaming-style simulation software like CrystalSpace can
be very useful for AGI and Alife research, but it must be used in
somewhat different ways than is appropriate for commercial gaming.

Of course, once you have created a reasonably intelligent AGI, you may
find ways to deploy it within gaming environments for fun and profit.
For instance, an AGI-powered NPC would be really cool in an massive
multiplayer online role-playing game like World of Warcraft or Final
Fantasy 11. But the AGI would have to already be pretty clever to be
marketable in that context. And of course one may find even more
interesting things to do with a clever AGI...

-- Ben

> then, you reverse engineer the properties of an amoeba. you define
> it's sequenced genome in logic, and you assign these properties and
> abilities to in-game programmed objects, and then you let them loose
> in a newtonian phyics based simworld with elements, seasons, sunlight
> and resources. Remember that much of existing science, and physics
> especially, is just reverse engineering; gravity existed long before
> we named it so, as did carbon. We now have a very, very complete
> understanding of the sub-cosmic and super-quantum realms; more than
> enough to replicate organic existence with incredible realism.
> now we know all the answers to how this world should behave, and how
> this ameoba should develop, as it's already happened in our past; we
> have a perfect history of it all preserved for comparison. if the
> world starts to diverge markedly, you can tweak the ratios that
> determine random changes via scarcity of resources, overpopulation,
> climate change etc that drive evolutionary development. you can
> program the basic imperatives of an amoeba; feed, grow, compete,
> survive, divide. yes, the simulation is more complex than my basic
> examples. but I think rigorous apllication of attention to detail
> could overcome any inconsistencies or incompleteness.
> if you build on this, again and again, in painstaking detail, you
> should eventually get to something substantial. how many data points
> are required to map the complete genetic evolutionary development from
> an ameoba to a fieldmouse? alot? sure. an infinite amount? no. we have
> those records, preserved for posterity in thin layers of earth; we can
> trace every step, and then provide a mirror environment to reproduce
> it. and if we can get from ameoba-like to mouse-like satisfactorily,
> can we then progress our bottom-up approach from mouse-like to, well,
> dog-like? monkey-like? man-like? you tell me.
> if this is all sounding too outlandish or complex to simulate at the
> technical level, there's a another 80's tech staple thats coming out
> if it's own winter to help out: Procedural Generation (PG). This is
> how the gameworld terrains of 80's titles generated their in-game
> enivronments when gig's of animations on a dvd weren't an option. This
> procedural approach says you don't have to create a world by hand; you
> just set up the rules, press go, and let the world generate itself.
> This is also the technique used by demoscene developers; check out
> what 64k(!) of procedural generation can do here:
> Wil Wright is the gaming legend is currently championing this, and
> Spore is the game due out this year which is currently knocking my
> socks off.
> the first third of this video is a must-watch:
> and a writeup of the game (and PG) is here:
> Wright isn't just using PG for textures or tiles; he's also using it
> for biomechanics and evolutionary characteristics like swimming,
> walking, hunting, killing, eating and mating. None of the in-game
> creatures in Spore are modelled prior to installing the game. every
> single one evolves using an array of possible physical development
> paths to come to life as completely unique organisms that execute
> motile ability in a completely (un)natural way. If you haven't watch
> the video linked above, I'd recommend doing so now.
> Now the interesting part to all this is that when playing Spore,
> you'll be competing against AI-generated evolving orgranisms; and I
> think if the simulation is realistic enough, and the properties of the
> organisms detailed enough, then we'll be starting to enter the
> god-mode lobby of the SA you lot have been fascinated with lately.
> It seems more and more that if we use sufficently comprehensive narrow
> AI to generate
> simulations of our in-historic-light-cone world that we can create
> glimpes of real intelligence in our simulations.
> There are growing examples of in-game AI generating AGI-like eruptions
> of higher-intelligence-like behaviour. One the recent (elder scrolls
> iv?) mmorpg games had testers walk into a in-game-evolved
> previously-unvisited villiage where none of the townspeople would let
> them in. turns out the villiage guards had gotten drunk and gone
> hunting and gotten lost, and then bandits had raided the villiage.
> each narrow-AI indivdiual guard|bandit|townsperson had combined to
> generate an effect more like that which could be envisioned by a
> higher intellect.
> there's also this older example from 2001:
> "This ability to discriminate has already produced some real surprises
> for testers and creators alike during development. In one situation,
> there was a creature that kept losing a stone-throwing game to another
> creature. To get revenge, the first creature heated a rock, planted it
> in the pile of stones to be thrown and then fell on the floor laughing
> when its rival burned its hands. All this happened without
> intervention from the player."
> -
> The next-gen consoles with their Cell processors are supposedly ideal
> for the 'Procedural Syntheisis' needed to implement Procedural
> Generation - does this mean the next glimmer of basic AGI will come
> from the living room instead of the lab?

This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:56 MDT