Category: Computer
Hits: 3799

This project which I call it life experiment is a very simple simulation of the world. This world consists of food which is distributed randomly and some creatures. Every creature has its own mind which is a simple neural network and has a random number of neurons.


These creatures are placed randomly on this world without any knowledge about it and they eventually learn to find food and eat it. Also, they learn to attack, kill and eat each other. Creatures have a satisfaction method which calculates the satisfaction of the creature based on its distance from food, other creatures, and its energy. The only thing that the creatures know is that they want to increase their satisfaction. This project had a lot of interesting results for example it showed that the environment is more important than IQ (at least in this model) because also high IQ creatures usually last longer than others but the ones that were in a good environment with high amount of food or a lot of contentions tend to last the longest.

some screenshots of the first version :

 a random created world for life experiment

figure 1- A randomly created world. the red squares are food and the blue ones are our creatures and the number beside creatures is the number of neurons on their mind

life experiment after the food ran out

figure 2- after a while, the food runs out and the creatures are forced to eat each other after that. The size of squares show the creatures energy level

life experiment after 10000 iterations

figure 3- after 10000 iterations the world looks like this

This project is still developing and I'm adding new actions like communication or mating to creatures.

If you have any suggestions or questions please email me at This email address is being protected from spambots. You need JavaScript enabled to view it..

You can access the source code from Github from the following link: