Farama-Foundation/ViZDoom
Reinforcement Learning environments based on the 1993 game Doom :godmode:
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.
Stars
1,990
Forks
432
Language
C++
License
—
Category
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.
Related frameworks
Talendar/flappy-bird-gym
An OpenAI Gym environment for the Flappy Bird game
chris-chris/pysc2-examples
StarCraft II - pysc2 Deep Reinforcement Learning Examples
aleju/mario-ai
Playing Mario with Deep Reinforcement Learning
gsurma/atari
AI research environment for the Atari 2600 games 🤖.
Kaixhin/Atari
Persistent advantage learning dueling double DQN for the Arcade Learning Environment