kilroy - Artificial life concepts

Infopost | 2007.10.15

(May need to click to play)

I'm simulating a collective of independent agents. Each is controlled by a set of neural networks that determine the agent's action. The networks train themselves based on positive and negative action outcomes. Currently they eat, swarm, and reproduce. Above you can see them moving as a collective to consume food (green). Their population (plotted below) fluctuates pretty steadily and you can see the group expand and contract based on environmental stimuli. It's pretty processor-intensive, so I've had to set the environment to support only a few hundred organisms.

The algorithms are still pretty basic, development goals include:

More interesting environment features.
Physical traits beyond the decision networks and lifespan.
A genetic algorithm for generating new agents.
Faster pseudo-random and pseud0-gaussian number generators, with minimal flops.
Heritage records to determine which founding organisms were most successful.
Multiple antagonizing colonies.
UI to allow realtime environment manipulation.Leave me your thoughts on algorithms and features.

tags:

Comments

Single finger salute!

This is what you do at work? Now I know who to come to for all the big questions in LIFE. We need to have some sort of mental olympics between a group of us to determine once and for all, the KING and the court jester.

Chris

Au contraire, this is about creating life, work is about destroying it.

Single finger salute!

Are you calling my wife a tramp? She is going to cut you.

◄

2007.10.15

Could you say that into my lapel pin?

2007.10.21

The rise and fall of Sauritch

►

Related / internal

Some posts from this site with similar content.

2008.06.11

Neural networks

I was chatting with Jon about the application of neural networks to stock trading, which is basically a perfect example for explaining the science. It went something like a'this:

2008.06.11

Picking ponies

Naturally I will be indulging my curiosity as to the effectiveness of a good stock market prediction network. It would be a shame not to put money where my mouth is.

2022.08.03

Keras cheat sheet

Examples of keras merging layers, convolutional layers, and activation functions in L, RGB, HSV, and YCbCr.

Related / external

Risky click advisory: these links are produced algorithmically from a crawl of the subsurface web (and some select mainstream web). I haven't personally looked at them or checked them for quality, decency, or sanity. None of these links are promoted, sponsored, or affiliated with this site. For more information, see this post.

sander.ai

Slides for my talk at the Deep Learning London meetup - Sander Dieleman

Slides for my talk at the Deep Learning London meetup

polukhin.tech

Lightweight Neural Network Architectures | Andrii Polukhin

As the field of Deep Learning continues to grow, the demand for efficient and lightweight neural networks becomes increasingly important. In this blog post, we will explore six lightweight neural network architectures.

burakkanber.com

morsecode.me

Perhaps the only of its kind, morsecode.me is a live, online Morse code radio; the most arcane of chat rooms. Users can communicate with one another only by keying Morse. Fortunately the site also comes with a cheat sheet and live translation. I built morsecode.me after I learned

Created 2025.07 from an index of 836,488 pages.

Content

navigation