Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jordana, Armand, Zhang, Jianghan, Amigo, Joseph, Righetti, Ludovic
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.22087
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908585420652544
author Jordana, Armand
Zhang, Jianghan
Amigo, Joseph
Righetti, Ludovic
author_facet Jordana, Armand
Zhang, Jianghan
Amigo, Joseph
Righetti, Ludovic
contents Zero-order optimization techniques are becoming increasingly popular in robotics due to their ability to handle non-differentiable functions and escape local minima. These advantages make them particularly useful for trajectory optimization and policy optimization. In this work, we propose a mathematical tutorial on random search. It offers a simple and unifying perspective for understanding a wide range of algorithms commonly used in robotics. Leveraging this viewpoint, we classify many trajectory optimization methods under a common framework and derive novel competitive RL algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2506_22087
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Introduction to Zero-Order Optimization Techniques for Robotics
Jordana, Armand
Zhang, Jianghan
Amigo, Joseph
Righetti, Ludovic
Robotics
Zero-order optimization techniques are becoming increasingly popular in robotics due to their ability to handle non-differentiable functions and escape local minima. These advantages make them particularly useful for trajectory optimization and policy optimization. In this work, we propose a mathematical tutorial on random search. It offers a simple and unifying perspective for understanding a wide range of algorithms commonly used in robotics. Leveraging this viewpoint, we classify many trajectory optimization methods under a common framework and derive novel competitive RL algorithms.
title An Introduction to Zero-Order Optimization Techniques for Robotics
topic Robotics
url https://arxiv.org/abs/2506.22087