NitroGen
NitroGen is a unified vision-to-action foundation model developed by NVIDIA, designed to play video games directly from raw frames. Trained on 40,000 hours of gameplay across over 1,000 games, it maps RGB video footage to gamepad actions, enabling generalist gaming agents to perform tasks in various gaming environments. ([huggingface.co](https://huggingface.co/nvidia/NitroGen?utm_source=openai))
NitroGen is a unified vision-to-action foundation model developed by NVIDIA, designed to play video games directly from raw frames. Trained on 40,000 hours of gameplay across over 1,000 games, it maps RGB video footage to gamepad actions, enabling generalist gaming agents to perform tasks in various gaming environments. ([huggingface.co](https://huggingface.co/nvidia/NitroGen?utm_source=openai))
- 01Trained on 40,000 hours of gameplay across over 1,000 games
- 02Maps RGB video footage to gamepad actions
- 03Supports a wide range of game genres
- 04Utilizes a vision transformer (SigLip2) and a diffusion matching transformer (DiT)
- 05Offers a universal simulator compatible with Gymnasium