mlsanityData to 14 Oct 2026

Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum

arXiv 2607.14001 ↗First posted 15 Jul 2026cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

We suggest using the Lyapunov characteristic exponent (LCE) as a dense reward signal for the reinforcement learning problem of stabilizing the inverted pendulum with vertical motion. With LCE, the agent not only successfully found the oscillatory motion known as the Kapitza pendulum but also damped the pendulum's pivoting, leaving it in a strictly upright position.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 2 of its 8 references that are in the map. First posted on arXiv 15 Jul 2026.

Builds on

2 of 8 references.

References · 2

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2015Continuous control with deep reinforcement learningcited by 3,407

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
  2. 2026Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos
  3. 2025Analytical Lyapunov Function Discovery: An RL-based Generative Approach
  4. 2024Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning
  5. 2023Learning to Stabilize High-dimensional Unknown Systems Using Lyapunov-guided Exploration
  6. 2026GIFT: Global stabilisation via Intrinsic Fine Tuning
  7. 2026Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach
  8. 2025A Dynamical Systems Framework for Reinforcement Learning Safety and Robustness Verification