Commit ·
10464d0
0
Parent(s):
docs: organization card with inline links and canonical role names
Browse files- .gitattributes +35 -0
- README.md +22 -0
- index.html +26 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: SPADE
|
| 3 |
+
emoji: ♠️
|
| 4 |
+
colorFrom: indigo
|
| 5 |
+
colorTo: purple
|
| 6 |
+
sdk: static
|
| 7 |
+
pinned: false
|
| 8 |
+
license: mit
|
| 9 |
+
short_description: A model that writes and solves its own environments.
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<div align="center">
|
| 13 |
+
|
| 14 |
+
# SPADE ♠
|
| 15 |
+
|
| 16 |
+
**Self-Play in Adaptive Synthetic Executable Environments**
|
| 17 |
+
|
| 18 |
+
[Paper](https://arxiv.org/abs/2608.19197) · [Code](https://github.com/spade-rl/spade) · [Models & Data](https://huggingface.co/spade-rl) · [Project](https://spade-rl.github.io)
|
| 19 |
+
|
| 20 |
+
</div>
|
| 21 |
+
|
| 22 |
+
A single model plays two roles: an **Environment Designer** that writes executable environments, and a **Reasoning Agent** that solves them. The Environment Designer is rewarded for producing environments at the frontier of what the Reasoning Agent can currently solve, so the curriculum keeps pace with the policy instead of being fixed in advance.
|
index.html
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<!doctype html>
|
| 2 |
+
<html lang="en">
|
| 3 |
+
<head>
|
| 4 |
+
<meta charset="utf-8" />
|
| 5 |
+
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
| 6 |
+
<title>SPADE</title>
|
| 7 |
+
<style>
|
| 8 |
+
body { max-width: 720px; margin: 0 auto; padding: 36px 18px; font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Arial, sans-serif; font-size: 15px; line-height: 1.6; color: #1b1f24; }
|
| 9 |
+
@media (prefers-color-scheme: dark) { body { color: #e6e6e6; background: #0d1117; } }
|
| 10 |
+
h1 { font-size: 30px; margin: 0 0 4px; }
|
| 11 |
+
.sub { font-size: 15px; opacity: .75; margin: 0 0 14px; }
|
| 12 |
+
.badges img { height: 22px; margin: 3px; }
|
| 13 |
+
p.lede { margin: 18px 0 0; overflow-wrap: anywhere; }
|
| 14 |
+
p.lede b { font-weight: 650; }
|
| 15 |
+
</style>
|
| 16 |
+
</head>
|
| 17 |
+
<body>
|
| 18 |
+
<div align="center">
|
| 19 |
+
<h1>SPADE ♠</h1>
|
| 20 |
+
<p class="sub"><b>Self-Play in Adaptive Synthetic Executable Environments</b></p>
|
| 21 |
+
<p class="links"><a href="https://arxiv.org/abs/2608.19197" target="_blank" rel="noopener">Paper</a> · <a href="https://github.com/spade-rl/spade" target="_blank" rel="noopener">Code</a> · <a href="https://huggingface.co/spade-rl" target="_blank" rel="noopener">Models & Data</a> · <a href="https://spade-rl.github.io" target="_blank" rel="noopener">Project</a></p>
|
| 22 |
+
</div>
|
| 23 |
+
|
| 24 |
+
<p class="lede">A single model plays two roles: an <b>Environment Designer</b> that writes executable environments, and a <b>Reasoning Agent</b> that solves them. The Environment Designer is rewarded for producing environments at the frontier of what the Reasoning Agent can currently solve, so the curriculum keeps pace with the policy instead of being fixed in advance.</p>
|
| 25 |
+
</body>
|
| 26 |
+
</html>
|