Periodic Skill Discovery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Jonghae, Cho, Daesol, Lee, Jusuk, Shim, Dongseok, Jang, Inkyu, Kim, H. Jin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908677419565056
author Park, Jonghae
Cho, Daesol
Lee, Jusuk
Shim, Dongseok
Jang, Inkyu
Kim, H. Jin
author_facet Park, Jonghae
Cho, Daesol
Lee, Jusuk
Shim, Dongseok
Jang, Inkyu
Kim, H. Jin
contents Unsupervised skill discovery in reinforcement learning (RL) aims to learn diverse behaviors without relying on external rewards. However, current methods often overlook the periodic nature of learned skills, focusing instead on increasing the mutual dependence between states and skills or maximizing the distance traveled in latent space. Considering that many robotic tasks - particularly those involving locomotion - require periodic behaviors across varying timescales, the ability to discover diverse periodic skills is essential. Motivated by this, we propose Periodic Skill Discovery (PSD), a framework that discovers periodic behaviors in an unsupervised manner. The key idea of PSD is to train an encoder that maps states to a circular latent space, thereby naturally encoding periodicity in the latent representation. By capturing temporal distance, PSD can effectively learn skills with diverse periods in complex robotic tasks, even with pixel-based observations. We further show that these learned skills achieve high performance on downstream tasks such as hurdling. Moreover, integrating PSD with an existing skill discovery method offers more diverse behaviors, thus broadening the agent's repertoire. Our code and demos are available at https://jonghaepark.github.io/psd/
format Preprint
id arxiv_https___arxiv_org_abs_2511_03187
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Periodic Skill Discovery
Park, Jonghae
Cho, Daesol
Lee, Jusuk
Shim, Dongseok
Jang, Inkyu
Kim, H. Jin
Machine Learning
Robotics
Unsupervised skill discovery in reinforcement learning (RL) aims to learn diverse behaviors without relying on external rewards. However, current methods often overlook the periodic nature of learned skills, focusing instead on increasing the mutual dependence between states and skills or maximizing the distance traveled in latent space. Considering that many robotic tasks - particularly those involving locomotion - require periodic behaviors across varying timescales, the ability to discover diverse periodic skills is essential. Motivated by this, we propose Periodic Skill Discovery (PSD), a framework that discovers periodic behaviors in an unsupervised manner. The key idea of PSD is to train an encoder that maps states to a circular latent space, thereby naturally encoding periodicity in the latent representation. By capturing temporal distance, PSD can effectively learn skills with diverse periods in complex robotic tasks, even with pixel-based observations. We further show that these learned skills achieve high performance on downstream tasks such as hurdling. Moreover, integrating PSD with an existing skill discovery method offers more diverse behaviors, thus broadening the agent's repertoire. Our code and demos are available at https://jonghaepark.github.io/psd/
title Periodic Skill Discovery
topic Machine Learning
Robotics
url https://arxiv.org/abs/2511.03187