Farama-Foundation/ViZDoom

Reinforcement Learning environments based on the 1993 game Doom :godmode:

53
/ 100
Established

This project helps AI researchers develop and test bots that learn to play the classic game Doom using only the visual information on the screen. It takes raw visual input (like what a human player sees) and provides an environment for training AI agents, ultimately producing agents capable of playing the game effectively. It is designed for researchers and practitioners in machine visual learning and deep reinforcement learning.

1,990 stars.

Use this if you are an AI researcher focused on visual reinforcement learning and want a fast, customizable, and robust environment for training agents in a complex 3D world.

Not ideal if you are looking for a pre-built Doom AI to just play the game, or if your research doesn't involve visual or reinforcement learning.

artificial-intelligence-research reinforcement-learning computer-vision game-AI machine-learning-environments
No License No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 25 / 25

How are scores calculated?

Stars

1,990

Forks

432

Language

C++

License

Last pushed

Mar 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Farama-Foundation/ViZDoom"

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