---
license: mit
tags:
- world-model
- diffusion
- doom
- game-engine
- diamond
---

# Diamond Doom Health Gathering v5.3

A diffusion-based world model trained on Doom Health Gathering maps with **zero entity persistence regression** through 490 effective epochs.

## Key Features

- **69.8M parameter** EDM (Elucidated Diffusion Model) with AR4 autoregressive conditioning
- **6-channel minimap conditioning**: disparity, walls, items top-down, items FOV, enemies top-down, enemies FOV
- **Zero disappearances** across all persistence tests (items AND enemies)
- **5-action space**: NOOP, FORWARD, TURN_LEFT, TURN_RIGHT, ATTACK
- GameNGen noise augmentation (10 buckets, alpha_max=0.7)

## Training Data

- 1400 episodes on 100 procedurally generated Health Gathering WADs
- Unkillable DoomPlayers as enemies (100% visibility in non-combat episodes)
- 42.5% combat, 42.5% normal (SF agent), 15% edge-case episodes
- 723,800 total training steps

## Persistence Results

| Epoch | Items Disappearances | Enemies Disappearances | Denoiser Loss |
|-------|---------------------|----------------------|---------------|
| 50 | 0 | 0 | 0.01123 |
| 100 | 0 | 0 | 0.01069 |
| 200 | 0 | 0 | 0.01011 |
| 300 (this ckpt) | 0 | 0 | 0.00973 |

## Usage



Controls: Z/UP=Forward, A/LEFT=Turn Left, R/RIGHT=Turn Right, SPACE=Attack

## Architecture

Based on [DIAMOND](https://github.com/eloialonso/diamond) with minimap conditioning extensions.
Architecturally equivalent to the Memory/Observation/Dynamics decomposition in
[MultiGen](https://arxiv.org/abs/2603.06679) (Stanford/Google, 2026).

## Files

- `agent_epoch_00300.pt` — Model checkpoint (267MB, effective epoch 490)
- `config/` — Hydra configs for agent, env, and trainer
- `data/v5_3_init/` — 3 initialization episodes with weapon + enemies