luangrezende/neural-network-circuit-game
Neuroevolution simulation where AI-controlled cars learn to drive a custom circuit using a genetic algorithm (no backpropagation). Built with Python, NumPy and Matplotlib, includes a real-time visualizer and an interactive track editor.
This project helps anyone interested in artificial intelligence and machine learning to understand how AI can learn complex tasks without traditional training methods. You can design custom race tracks, and the AI cars will learn to drive them, showing how simple neural networks can evolve through trial and error. This is for hobbyists, educators, or students exploring neuroevolution and genetic algorithms.
Use this if you want to visually experiment with AI learning to drive a car through a custom circuit using genetic algorithms instead of traditional backpropagation.
Not ideal if you need to build or train production-grade AI models, as this is primarily a conceptual demonstration.
Stars
16
Forks
4
Language
Python
License
—
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/luangrezende/neural-network-circuit-game"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ArztSamuel/Applying_EANNs
A 2D Unity simulation in which cars learn to navigate themselves through different courses. The...
idreesshaikh/Autonomous-Driving-in-Carla-using-Deep-Reinforcement-Learning
Deep Reinforcement Learning (PPO) in Autonomous Driving (Carla) [from scratch]
kevinhughes27/TensorKart
self-driving MarioKart with TensorFlow
lexfridman/deeptraffic
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
KimangKhenng/Traffic-SImulation-and-Visualization
Traffic Intersection Simulation Using C++ and Qt