GameNGen (WIP)

Open-source implementation of GameNGen: Diffusion Models Are Real-Time Game Engines¹

1. Train Agent Play
2. Collect data at scale
3. Train the diffusion model

Planning to use the VIZDoomBot library to train the agent to play the game. See specific README for more details.

Tutorial on getting started with Doom RL using Stable Baselines 3 and VizDoom.

• See Tutorial on folder train_agent_play/tutorial_get_started_doom_rl.

Resources:

• VizdoomBot - GitHub / Website
• Doom RL Tutorial Medium Article by Leandro Kieliger
• Doom RL Tutorial Notebook
• Stable Baselines 3
• VizDoom

@misc{valevski2024diffusionmodelsrealtimegame,
        title={Diffusion Models Are Real-Time Game Engines}, 
        author={Dani Valevski and Yaniv Leviathan and Moab Arar and Shlomi Fruchter},
        year={2024},
        eprint={2408.14837},
        archivePrefix={arXiv},
        primaryClass={cs.LG},
        url={https://arxiv.org/abs/2408.14837}, 
  }