Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Donghoon, Yoo, Minjong, Woo, Honguk
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913475420225536
author Kim, Donghoon
Yoo, Minjong
Woo, Honguk
author_facet Kim, Donghoon
Yoo, Minjong
Woo, Honguk
contents Goal-conditioned (GC) policy learning often faces a challenge arising from the sparsity of rewards, when confronting long-horizon goals. To address the challenge, we explore skill-based GC policy learning in offline settings, where skills are acquired from existing data and long-horizon goals are decomposed into sequences of near-term goals that align with these skills. Specifically, we present an `offline GC policy learning via skill-step abstraction' framework (GLvSA) tailored for tackling long-horizon GC tasks affected by goal distribution shifts. In the framework, a GC policy is progressively learned offline in conjunction with the incremental modeling of skill-step abstractions on the data. We also devise a GC policy hierarchy that not only accelerates GC policy learning within the framework but also allows for parameter-efficient fine-tuning of the policy. Through experiments with the maze and Franka kitchen environments, we demonstrate the superiority and efficiency of our GLvSA framework in adapting GC policies to a wide range of long-horizon goals. The framework achieves competitive zero-shot and few-shot adaptation performance, outperforming existing GC policy learning and skill-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11300
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks
Kim, Donghoon
Yoo, Minjong
Woo, Honguk
Machine Learning
Artificial Intelligence
Goal-conditioned (GC) policy learning often faces a challenge arising from the sparsity of rewards, when confronting long-horizon goals. To address the challenge, we explore skill-based GC policy learning in offline settings, where skills are acquired from existing data and long-horizon goals are decomposed into sequences of near-term goals that align with these skills. Specifically, we present an `offline GC policy learning via skill-step abstraction' framework (GLvSA) tailored for tackling long-horizon GC tasks affected by goal distribution shifts. In the framework, a GC policy is progressively learned offline in conjunction with the incremental modeling of skill-step abstractions on the data. We also devise a GC policy hierarchy that not only accelerates GC policy learning within the framework but also allows for parameter-efficient fine-tuning of the policy. Through experiments with the maze and Franka kitchen environments, we demonstrate the superiority and efficiency of our GLvSA framework in adapting GC policies to a wide range of long-horizon goals. The framework achieves competitive zero-shot and few-shot adaptation performance, outperforming existing GC policy learning and skill-based methods.
title Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.11300