MatPoliquin/stable-retro-scripts

Train models on retro games. AI vs AI contest. Pytorch C++ plugin for RetroArch that let you override player input with models

50
/ 100
Established

This project helps AI researchers and hobbyists train machine learning models to play classic retro video games. You provide game ROMs and the system outputs trained AI models capable of playing the game, which can then be used to create improved AI opponents or even pit two AI models against each other in player-versus-player games. The end-user is an AI developer or enthusiast interested in reinforcement learning for game AI.

Use this if you want to develop, train, and test AI models to play retro video games and integrate them with emulators like RetroArch for a more challenging AI opponent.

Not ideal if you're looking for an out-of-the-box retro gaming experience without diving into AI model training and development.

AI-research reinforcement-learning game-AI retro-gaming emulator-development
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

39

Forks

11

Language

C++

License

MIT

Last pushed

Feb 22, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MatPoliquin/stable-retro-scripts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.