Policy Compatible Skill Incremental Learning via Lazy Learning Interface

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Daehee, Lee, Dongsu, Kwack, TaeYoon, Choi, Wonje, Woo, Honguk
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914255291285504
author Lee, Daehee
Lee, Dongsu
Kwack, TaeYoon
Choi, Wonje
Woo, Honguk
author_facet Lee, Daehee
Lee, Dongsu
Kwack, TaeYoon
Choi, Wonje
Woo, Honguk
contents Skill Incremental Learning (SIL) is the process by which an embodied agent expands and refines its skill set over time by leveraging experience gained through interaction with its environment or by the integration of additional data. SIL facilitates efficient acquisition of hierarchical policies grounded in reusable skills for downstream tasks. However, as the skill repertoire evolves, it can disrupt compatibility with existing skill-based policies, limiting their reusability and generalization. In this work, we propose SIL-C, a novel framework that ensures skill-policy compatibility, allowing improvements in incrementally learned skills to enhance the performance of downstream policies without requiring policy re-training or structural adaptation. SIL-C employs a bilateral lazy learning-based mapping technique to dynamically align the subtask space referenced by policies with the skill space decoded into agent behaviors. This enables each subtask, derived from the policy's decomposition of a complex task, to be executed by selecting an appropriate skill based on trajectory distribution similarity. We evaluate SIL-C across diverse SIL scenarios and demonstrate that it maintains compatibility between evolving skills and downstream policies while ensuring efficiency throughout the learning process.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20612
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Policy Compatible Skill Incremental Learning via Lazy Learning Interface
Lee, Daehee
Lee, Dongsu
Kwack, TaeYoon
Choi, Wonje
Woo, Honguk
Machine Learning
Skill Incremental Learning (SIL) is the process by which an embodied agent expands and refines its skill set over time by leveraging experience gained through interaction with its environment or by the integration of additional data. SIL facilitates efficient acquisition of hierarchical policies grounded in reusable skills for downstream tasks. However, as the skill repertoire evolves, it can disrupt compatibility with existing skill-based policies, limiting their reusability and generalization. In this work, we propose SIL-C, a novel framework that ensures skill-policy compatibility, allowing improvements in incrementally learned skills to enhance the performance of downstream policies without requiring policy re-training or structural adaptation. SIL-C employs a bilateral lazy learning-based mapping technique to dynamically align the subtask space referenced by policies with the skill space decoded into agent behaviors. This enables each subtask, derived from the policy's decomposition of a complex task, to be executed by selecting an appropriate skill based on trajectory distribution similarity. We evaluate SIL-C across diverse SIL scenarios and demonstrate that it maintains compatibility between evolving skills and downstream policies while ensuring efficiency throughout the learning process.
title Policy Compatible Skill Incremental Learning via Lazy Learning Interface
topic Machine Learning
url https://arxiv.org/abs/2509.20612