Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Jinmin, Li, Kai, Zang, Yifan, Fu, Haobo, Fu, Qiang, Xing, Junliang, Cheng, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916834321629184
author He, Jinmin
Li, Kai
Zang, Yifan
Fu, Haobo
Fu, Qiang
Xing, Junliang
Cheng, Jian
author_facet He, Jinmin
Li, Kai
Zang, Yifan
Fu, Haobo
Fu, Qiang
Xing, Junliang
Cheng, Jian
contents Offline multi-task reinforcement learning aims to learn a unified policy capable of solving multiple tasks using only pre-collected task-mixed datasets, without requiring any online interaction with the environment. However, it faces significant challenges in effectively sharing knowledge across tasks. Inspired by the efficient knowledge abstraction observed in human learning, we propose Goal-Oriented Skill Abstraction (GO-Skill), a novel approach designed to extract and utilize reusable skills to enhance knowledge transfer and task performance. Our approach uncovers reusable skills through a goal-oriented skill extraction process and leverages vector quantization to construct a discrete skill library. To mitigate class imbalances between broadly applicable and task-specific skills, we introduce a skill enhancement phase to refine the extracted skills. Furthermore, we integrate these skills using hierarchical policy learning, enabling the construction of a high-level policy that dynamically orchestrates discrete skills to accomplish specific tasks. Extensive experiments on diverse robotic manipulation tasks within the MetaWorld benchmark demonstrate the effectiveness and versatility of GO-Skill.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06628
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
He, Jinmin
Li, Kai
Zang, Yifan
Fu, Haobo
Fu, Qiang
Xing, Junliang
Cheng, Jian
Machine Learning
Artificial Intelligence
Offline multi-task reinforcement learning aims to learn a unified policy capable of solving multiple tasks using only pre-collected task-mixed datasets, without requiring any online interaction with the environment. However, it faces significant challenges in effectively sharing knowledge across tasks. Inspired by the efficient knowledge abstraction observed in human learning, we propose Goal-Oriented Skill Abstraction (GO-Skill), a novel approach designed to extract and utilize reusable skills to enhance knowledge transfer and task performance. Our approach uncovers reusable skills through a goal-oriented skill extraction process and leverages vector quantization to construct a discrete skill library. To mitigate class imbalances between broadly applicable and task-specific skills, we introduce a skill enhancement phase to refine the extracted skills. Furthermore, we integrate these skills using hierarchical policy learning, enabling the construction of a high-level policy that dynamically orchestrates discrete skills to accomplish specific tasks. Extensive experiments on diverse robotic manipulation tasks within the MetaWorld benchmark demonstrate the effectiveness and versatility of GO-Skill.
title Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.06628