Farama-Foundation/ViZDoom
Reinforcement Learning environments based on the 1993 game Doom :godmode:
Provides Python and C++ APIs compatible with Gymnasium/Gym frameworks, built on the ZDoom engine for authentic game mechanics. Features direct access to visual buffers, depth maps, audio streams, and semantic object labeling, enabling multi-modal learning approaches. Achieves 7000+ frames/second in sync mode while supporting async/multiplayer scenarios and custom WAD-based environments via ACS scripting.
1,990 stars.
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
aleju/mario-ai
Playing Mario with Deep Reinforcement Learning
chris-chris/pysc2-examples
StarCraft II - pysc2 Deep Reinforcement Learning Examples
gavento/gamegym
A game theory framework with examples and algorithms
Kaixhin/Atari
Persistent advantage learning dueling double DQN for the Arcade Learning Environment