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

Slava Andrejev

7/15/2026

cs.LG

No confident code implementation found for this paper.

Abstract

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.

View on arXiv View PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

SuPLE: Robot Learning with Lyapunov Rewards

84% match1 repo2024

Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games

81% match2023

Subequivariant Reinforcement Learning Framework for Coordinated Motion Control

80% match2024

Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience

79% match1 repo192022

Auxiliary Reward Generation with Transition Distance Representation Learning

79% match2024

CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations

79% match2023

Cite this paper

@article{andrejev2026lyapunov,
  title  = {Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum},
  author = {Slava Andrejev},
  year   = {2026},
  eprint = {2607.14001},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2607.14001v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

[![Code of Paper](https://codeofpaper.com/badge/2607.14001.svg)](https://codeofpaper.com/paper/2607.14001)