A reinforcement-learning-driven symbolic transformer generates and verifies analytical local Lyapunov functions for nonlinear systems up to ten dimensions, including a claimed new certificate for a lossy power system.
This implies that if ˜Vϕ is invalid, the neighborhoods of x∗ 1 and x∗ 2 are highly likely to capture significant violations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Analytical Lyapunov Function Discovery: An RL-based Generative Approach
A reinforcement-learning-driven symbolic transformer generates and verifies analytical local Lyapunov functions for nonlinear systems up to ten dimensions, including a claimed new certificate for a lossy power system.