Datasets › VizDoom
VizDoom
ViZDoom is an AI research platform based on the classical First Person Shooter game Doom. The most popular game mode is probably the so-called Death Match, where several players join in a maze and fight against each other. After a fixed time, the match ends and all the players are ranked by the FRAG scores defined as kills minus suicides. During the game, each player can access various observations, including the first-person view screen pixels, the corresponding depth-map and segmentation-map (pixel-wise object labels), the bird-view maze map, etc. The valid actions include almost all the keyboard-stroke and mouse-control a human player can take, accounting for moving, turning, jumping, shooting, changing weapon, etc. ViZDoom can run a game either synchronously or asynchronously, indicating whether the game core waits until all players’ actions are collected or runs in a constant frame rate without waiting.
Source: Arena: a toolkit for Multi-Agent Reinforcement Learning Image Source: https://github.com/mwydmuch/ViZDoom
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Image Generation | VizDoom | GAUDI FID 33.7 | GAUDI: A Neural Architect for Immersive 3D Scene Generation | apple/ml-gaudi | 4 | Compare |
| Scene Generation | VizDoom | GSN FID 37.21 | Unconstrained Scene Generation with Locally Conditioned... | apple/ml-gsn | 3 | Compare |
| Game of Doom | ViZDoom Basic Scenario | DQN Average Score 82.2 | ViZDoom: A Doom-based AI Research Platform for Visual... | NervanaSystems/coach +9 | 1 | Compare |
Papers archive 2025-07-28
5 shown of 5 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 156. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| GAUDI: A Neural Architect for Immersive 3D Scene Generation | 1 | 4 | 27 Jul 2022 | not harvested |
| Unconstrained Scene Generation with Locally Conditioned Radiance Fields | 1 | 1 | 1 Apr 2021 | not harvested |
| pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis | 3 | 1 | 2 Dec 2020 | ran 3 of 4 samples (1 unverified; 2 pointer-only for licence) |
| GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis | 1 | 1 | 5 Jul 2020 | ran 3 of 12 samples (9 unverified) |
| ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning | 10 | 1 | 6 May 2016 | ran 2 of 5 samples (3 unverified; 5 pointer-only for licence) |
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- ViZDoom Basic Scenario
- VizDoom
2 variant names, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections