AST-guard
A gradient-immune structural guard designed to prevent reward hacking in reinforcement learning.
Why it made the shelf
It is an open source tool for securing and guiding reinforcement learning models against reward hacking.
Seen on
- First seen
- 3 months ago
- Best score
- 3 points
Behind the tool
Who built it. How it grew.
People, backing, growth, and ownership. Every claim links to its source.
Official sitegithub.com
Source review queued
Public trail
Where it showed up
1 reference from 1 publisher.
- First trace
- Hacker News3 months ago
- 01Hacker NewsFirst trace
A gradient-immune structural guard against RL reward hacking
