Python A.I. Tutorial (with NEAT) - Part 3 - Adding the A.I.

preview_player
Показать описание
Learn to create your own 2D-Video Games using the module Pygame with Python. In this video I'll be showing you how to add the A.I. to the finished game.





◾◾◾◾◾🎬 Overview 🎬◾◾◾◾◾
Previous Episode:
Part 2 - Setup & Display Dinosaur

Next Episode:
Part 4 - Adding the A.I.

◾◾◾◾◾⌚ Timestamps ⌚◾◾◾◾◾
00:00 | NEAT Algorithm Explained
01:03 | NEAT Configuration File
03:07 | Setup NEAT Algorithm
04:04 | Fitness Function
07:24 | Results

◾◾◾◾◾ 🌎 Let's Connect! ◾◾◾◾◾

◾◾◾◾◾
🌟 Please leave a LIKE and SUBSCRIBE for more! 🌟
Рекомендации по теме
Комментарии
Автор

Hi, what w great tutorial! One think I am not sure about. I have checked your code and I was unable to find a line that would assign score value to the genomes.

Is it a mistake, or maybe you don't need to do it - apart lowering fitness score for dinosaurs that hit the obstacles - because you are ending generation with a single dinosaur and neural net?

radosawbysewski
Автор

What about okay external games like web games by scanning with opencv

gankhiang
Автор

Hi, I loved your tutorial series, you're almost the only one to offer NEAT tutorials. However, after exploring your config file I find it strange to use tanh as the activation function if the condition for jumping is your eval_genomes is that the output returns a number greater than 0.5. If you use tanh you get values between -1 and 1, whereas sigmoid returns values between 0 and 1.

simonnaulet
Автор

Great video! When did we set up the inputs?

matousjarolim
Автор

I did everything but my genomes are not evolving they are doing the exact same thing for 100s of gens 😢 its the exact fitness logic as yours

cubingforever
Автор

The dinosaurs never seem to learn for me and will always act randomly

ragingenby