Learning Parameterized Skills from Demonstrations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gupta, Vedant, Fu, Haotian, Luo, Calvin, Jiang, Yiding, Konidaris, George
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915582357536768
author Gupta, Vedant
Fu, Haotian
Luo, Calvin
Jiang, Yiding
Konidaris, George
author_facet Gupta, Vedant
Fu, Haotian
Luo, Calvin
Jiang, Yiding
Konidaris, George
contents We present DEPS, an end-to-end algorithm for discovering parameterized skills from expert demonstrations. Our method learns parameterized skill policies jointly with a meta-policy that selects the appropriate discrete skill and continuous parameters at each timestep. Using a combination of temporal variational inference and information-theoretic regularization methods, we address the challenge of degeneracy common in latent variable models, ensuring that the learned skills are temporally extended, semantically meaningful, and adaptable. We empirically show that learning parameterized skills from multitask expert demonstrations significantly improves generalization to unseen tasks. Our method outperforms multitask as well as skill learning baselines on both LIBERO and MetaWorld benchmarks. We also demonstrate that DEPS discovers interpretable parameterized skills, such as an object grasping skill whose continuous arguments define the grasp location.
format Preprint
id arxiv_https___arxiv_org_abs_2510_24095
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Parameterized Skills from Demonstrations
Gupta, Vedant
Fu, Haotian
Luo, Calvin
Jiang, Yiding
Konidaris, George
Machine Learning
Artificial Intelligence
Robotics
We present DEPS, an end-to-end algorithm for discovering parameterized skills from expert demonstrations. Our method learns parameterized skill policies jointly with a meta-policy that selects the appropriate discrete skill and continuous parameters at each timestep. Using a combination of temporal variational inference and information-theoretic regularization methods, we address the challenge of degeneracy common in latent variable models, ensuring that the learned skills are temporally extended, semantically meaningful, and adaptable. We empirically show that learning parameterized skills from multitask expert demonstrations significantly improves generalization to unseen tasks. Our method outperforms multitask as well as skill learning baselines on both LIBERO and MetaWorld benchmarks. We also demonstrate that DEPS discovers interpretable parameterized skills, such as an object grasping skill whose continuous arguments define the grasp location.
title Learning Parameterized Skills from Demonstrations
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2510.24095