Upload folder using huggingface_hub

README.md

@@ -0,0 +1,56 @@
+---
+library_name: pytorch
+license: apache-2.0
+model_name: space-invaders-world-model
+tags:
+- world-model
+- diffusion
+- atari
+- space-invaders
+- video-generation
+---
+
+# space-invaders-world-model
+
+A diffusion world model of Atari Space Invaders, trained from scratch. Given the last 4 frames and actions, a small U-Net denoises the next 64×64 frame; fed its own frames, it generates a video that your actions steer. After [DIAMOND](https://arxiv.org/abs/2405.12399). `atari.py` in this repo collects the data, trains, plays and doubles as the loader.
+
+
+
+## 🚀 Usage
+
+Play it in the browser. Each button press generates one frame:
+
+```
+uv run "$(hf download jgalego/space-invaders-world-model atari.py --quiet)" play --game SpaceInvaders
+```
+
+From Python, with `atari.py` on the path:
+
+```python
+import torch
+from atari import DEVICE, collect, load, rollout, to_float
+
+model = load("jgalego/space-invaders-world-model")
+frames, _, _ = collect(4, seed=0, game="SpaceInvaders")  # four real frames to start from
+context = to_float(frames[:4])[None].to(DEVICE)
+moves = torch.tensor([[0, 0, 0] + [1] * 16], device=DEVICE)  # FIRE for 16 frames
+video = rollout(model, context, moves)  # (1, 16, 3, 64, 64) in [-1, 1]
+```
+
+Actions: 0 NOOP, 1 FIRE, 2 RIGHT, 3 LEFT, 4 RIGHTFIRE, 5 LEFTFIRE.
+
+## 🏋️ Training
+
+Not trained yet.
+
+## 📊 Results
+
+Rollouts on held-out windows from episodes whose seeds never appear in training. The model gets four real frames and the real actions, then only its own frames. **Repeat** keeps showing the last real frame. Much of an Atari frame never changes, so **changed pixels** scores only the pixels where the real or the predicted frame differs from the last real frame.
+
+Not evaluated yet.
+
+## ⚠️ Limitations
+
+- A random policy does not get far, so the model knows the early game best.
+- 64×64 frames: small sprites are a pixel or two and can blur or vanish over long rollouts.
+- Errors compound: every generated frame becomes input for the next.