Make an AI computer
that teaches itself to play a game.
- The article is straight forward. Built a simple game using Pygame & applied NEAT (NeuroEvolution of Augmenting Topologies) algorithm to train AI.
- The files were downloaded and then the program was ready to run.
- We had challenges getting the game running but after changing the following code in “RollingBall.py” it worked.
make the ball jump
self.vel = -9.2
self.tick_count = 0
self.height = self.y
Links to article and files.
- AI Teaches itself to play a game
- Git repo – project files
- If you have issues about “neat”/”neat-python” read this.
- How to fix: AttributeError: module ‘neat’ has no attribute ‘config’
AI can learn to play Snake and Tetris
Neural Network Learns to Play Snake
I Made an A.I. to MASTER TETRIS
- For both videos there are links to the source code.
- To run the program you will need Processing. It is free to download and open source.
- If you have some experience working with coding software, you can make it work in less than an hour. Good luck.
AlphaGo is the first computer program to defeat a professional human Go player, a landmark achievement that experts believe was a decade ahead of its time.
Artificial intelligence research has made rapid progress in a wide variety of domains from speech recognition and image classification to genomics and drug discovery. In many cases, these are specialist systems that leverage enormous amounts of human expertise and data.However, for some problems this human knowledge may be too expensive, too unreliable or simply unavailable.