CogitoNTNU/NEATactics
NEAT is neat! An implementation of neuroevolution of augmenting topologies playing Super Mario Bros.
This project helps researchers and enthusiasts in artificial intelligence and game development understand and experiment with neuroevolution. It takes a simulated game environment, specifically a Super Mario-inspired platformer, and evolves a neural network to learn how to play the game effectively. The output is an AI agent that can navigate and play the game, demonstrating learned strategies. This tool is for AI researchers, students, and game developers interested in evolutionary algorithms and agent-based learning.
Use this if you want to explore how AI can learn to play games from scratch through an evolutionary process, without explicit programming for each move.
Not ideal if you need a plug-and-play solution for building game-playing AI without understanding the underlying neuroevolutionary principles.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Oct 16, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CogitoNTNU/NEATactics"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
wagenaartje/neataptic
:rocket: Blazing fast neuro-evolution & backpropagation for the browser and Node.js
uber-research/deep-neuroevolution
Deep Neuroevolution
alenaksu/neatjs
NEAT (Neuro Evolution of Augmenting Topologies) implementation in JavaScript
liquidcarrot/carrot
🥕 Evolutionary Neural Networks in JavaScript
flxsosa/DeepHyperNEAT
A public python implementation of the DeepHyperNEAT system for evolving neural networks....