https://github.com/saineshnakra/fai-evolving-world

A comparative study of genetic algorithms through parallel evolution simulation. Two distinct populations of agents evolve simultaneously using different GA implementations while competing for survival in a shared 2D environment.
https://github.com/saineshnakra/fai-evolving-world

ai genetic-algorithm pygame pygame-simulation python

Last synced: 9 months ago
JSON representation

A comparative study of genetic algorithms through parallel evolution simulation. Two distinct populations of agents evolve simultaneously using different GA implementations while competing for survival in a shared 2D environment.

• Host: GitHub
• URL: https://github.com/saineshnakra/fai-evolving-world
• Owner: saineshnakra
• License: mit
• Created: 2025-06-01T18:30:25.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-07-07T15:16:39.000Z (about 1 year ago)
• Last Synced: 2025-07-07T16:29:21.388Z (about 1 year ago)
• Topics: ai, genetic-algorithm, pygame, pygame-simulation, python
• Language: Python
• Homepage:
• Size: 63.5 MB
• Stars: 0
• Watchers: 0
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Evolving World: Comparative Genetic Algorithm Simulation

To see the Demo : https://www.youtube.com/watch?v=9_YamV3CggA

A 2D artificial life simulation comparing two distinct genetic algorithms through parallel evolution of competing agent populations. This project explores how different evolutionary strategies perform under identical environmental pressures in a shared survival-oriented world.

## Project Overview

Two populations of agents evolve simultaneously using different genetic algorithm implementations:

- **GA 1 (Foragers)**: Traditional survival-focused agents that search for food sources

- **GA 2 (Predators)**: Aggressive agents that can steal food from others or act as predators

Both populations compete in the same 2D environment, allowing direct comparison of algorithmic performance, adaptation rates, and emergent behaviors.

## Key Features

- **Dual Evolution System**: Parallel genetic algorithms with different survival strategies

- **Shared Environment**: Common world with food sources, hazards, and resource competition

- **Real-time Visualization**: 2D rendering of both populations and their evolutionary dynamics

- **Comprehensive Metrics**: Fitness tracking, survival rates, and behavioral analysis

- **Configurable Parameters**: Adjustable mutation rates, selection methods, and environmental conditions

## Implementation

Built with modular, reusable code architecture following academic project standards. The system implements proper genetic algorithm fundamentals while exploring the less-studied question of comparative GA performance in shared environments.

## Research Applications

This simulation framework enables study of evolutionary computation, algorithm comparison, predator-prey dynamics, and emergent artificial life behaviors. Ideal for exploring how different genetic operators and selection pressures influence population evolution in competitive settings.

## Academic Context

Developed as part of an AI course project exploring genetic algorithms, artificial life, and evolutionary computation. Incorporates insights from NEAT, novelty search, and established ALIFE research methodologies.

## Pre-requisites:

`python = 3.11.5`

## To install and run code:

`make start`