Skip to content

This is my submission to Debuggit 2k23. This is an AI model to train cars for use in car racing games as opponent AI. The difficulty of the AI can be adjusted by training the model to a specific level of proficiency. The cars use ANN for movement and are trained by genetic algorithms

Notifications You must be signed in to change notification settings

StoneCoder123/AI-RaceCars

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI-RaceCars

This is my submission to Debuggit 2k23. This is an AI model to train cars. As an applications, it can be used in car racing games as opponent AI. The difficulty of the AI can be adjusted by training the model to a specific level of proficiency. The cars use ANN for movement and are trained by genetic algorithms

The engine used is the Unity Game Engine. The purpose of the engine is only for 3D rendering. All the code for the neural networks and implementation of genetic algorithms is done in C#.

I might later extend this to make a fully fledged racing game where the AI is trained by this method.

To run the game, click on the Self Driving Car.exe file. Make sure there are to .dll errors.

Important Controls And Instructions: 1) 'P' is to progress a generation ( Each car's NN is updated) 2) 'Space' resets the cars to start

When satisfied with the current generation, Press 'P' and then quickly later press 'Space' to reset the cars and let them traverse the track again

About

This is my submission to Debuggit 2k23. This is an AI model to train cars for use in car racing games as opponent AI. The difficulty of the AI can be adjusted by training the model to a specific level of proficiency. The cars use ANN for movement and are trained by genetic algorithms

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published