Tillett/Game-Playing-with-Machine-Learning
Game Playing with various AI and Machine Learning techniques
This project helps you explore how AI can learn to play classic video games like Super Mario Bros. and Super Mario World. You provide a game ROM and an emulator, and the system uses machine learning algorithms to generate a 'player' that learns to complete levels. This is for anyone interested in observing artificial intelligence in action, especially those curious about genetic algorithms and how they can be applied to game environments.
No commits in the last 6 months.
Use this if you want to experiment with genetic algorithms or the NEAT algorithm to see how AI can independently learn to navigate and solve challenges within video games.
Not ideal if you're looking for a ready-to-use game-playing bot that doesn't require setup with emulators and ROMs, or if you need to integrate AI into commercial game development.
Stars
19
Forks
5
Language
Lua
License
—
Category
Last pushed
May 01, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tillett/Game-Playing-with-Machine-Learning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yenchenlin/DeepLearningFlappyBird
Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
ChenglongChen/pytorch-DRL
PyTorch implementations of various Deep Reinforcement Learning (DRL) algorithms for both single...
nikp06/subwAI
Scripts for training an AI to play the endless runner Subway Surfers using a supervised machine...
vladfi1/phillip
The SSBM "Phillip" AI.
kingyuluk/RL-FlappyBird
Using reinforcement learning to train FlappyBird.