Concept detail
reward hacking and metric gaming in agent training/evaluation
0 tagged videos · 1 connection videos · degree 0
Publication timeline
- 2026-081 video
Source videos
Observed neighbors
Goodhart's Law
Proxy-target divergence is the same phenomenon expressed in mathematics-community terms.
1 source videos
ICM 2026 Public Lectures - Terence TaoRelated tagged insights
No core insights are tagged with this concept.