Diagnosing Faults in Reinforcement Learning Simulators and World Models with Canonical Polynomial Invariants
This story is from 2026-09-15. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.13194v1 Announce Type: new Abstract: A large literature builds physical structure into learned dynamics on the premise that models respecting the underlying physics predict better. We test that premise using exact polynomial invariants recovered from trajectories and canonicalised as red…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-15 04:00 · arXiv cs.LG
Diagnosing Faults in Reinforcement Learning Simulators and World Models with Canonical Polynomial Invariants