Home▸AI & Machine Learning▸Reward Hacking in 3D: A Robot Climbs the Proxy, Not the Goal

🤖 Reward Hacking in 3D: A Robot Climbs the Proxy, Not the Goal

3D reward hacking demonstration built with Blender and Three.js: a robot and 139 other agents climb a proxy reward surface with a decoy peak above the true reward terrain, with presets, adjustable decoy strength, learning rate and noise, and four numerical checks.

AI & Machine Learning3DModerate60 FPS📱 Mobile-adapted🟠 Blender⇄ 2D version
Reward Hacking in 3D: A Robot Climbs the Proxy, Not the Goal ↗ Open standalone
⚙ Under the hood

3D reward hacking demonstration built with Blender and Three.js: a robot and 139 other agents climb a proxy reward surface with a decoy peak above the true reward terrain, with presets, adjustable decoy strength, learning rate and noise, and four numerical checks.

Reward hackingAI safetyGoodhart's lawReinforcement learningGradient ascent

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)