Game overview
The purpose of this app is to simulate natural selection with evolving creatures.
There are two types of creatures: carnivores and herbivores. Every creature has to bring its prey inside the home circle. If they are successful, they reproduce by mitosis. Creatures will die if they run out of health or if their age is equal to the lifespan value. Creature can take damage by another creature or by starvation.
Every creature has a brain (neural network), which decides among three options: move forward, turn right, turn left. This network is evolved using a genetic algorithm.
About neural network:
Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. In this app creatures will learn to recognize patterns between their position and distance from the environmental objects.
About genetic algorithm:
The genetic algorithm repeatedly modifies a population of creatures. At each step, the genetic algorithm selects best performing creatures from the current population to be parents and uses them to produce the children for the next generation.
Every creature has a brain (neural network), which decides among three options: move forward, turn right, turn left. This network is evolved using a genetic algorithm.
About neural network:
Neural networks are a set of algorithms, modeled loosely after the human brain, that are designed to recognize patterns. In this app creatures will learn to recognize patterns between their position and distance from the environmental objects.
About genetic algorithm:
The genetic algorithm repeatedly modifies a population of creatures. At each step, the genetic algorithm selects best performing creatures from the current population to be parents and uses them to produce the children for the next generation.
Developer
More games by Kent Pirma