I made this project as part of WOC organized by SDSLabs.
It is a Python-based simulation where you can tweak the initial conditions and other parameters of an environment and then prey-predator adapt to each other and try to survive for a long time. (You are not playing GOD!)
Evolution-Sim
Algorithm behind
The underling algorithm that trains and which is responsible for the emergence of intelligence (or stupidity in my case) is the NEAT (neural evolution of argumented topology)
Neat tldr
Unlike traditional machine learning approaches that require manually tuning hyperparameters such as learning rate, number of layers, and number of neurons in a neural network with a fixed topology, NEAT (NeuroEvolution of Augmenting Topologies) simultaneously evolves the structure and the parameters of the network. This means NEAT searches for both the optimal topology—adding or removing neurons and connections as needed—and the optimal weights and biases, enabling more flexible solutions that can adapt to the complexity of the problem without prior assumptions about the best architecture.