paper-with-me

Papers

Policy Compatible Skill Incremental Learning via Lazy Learning Interface

2025-09-24 · Daehee Lee, Dongsu Lee, TaeYoon Kwack, Wonje Choi, Honguk Woo arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.20612

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental Learning

Similar Papers 제목 키워드 기반

LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation

2023-02-03 · Rui Xue, Haoyu Han, MohamadAli Torkamani, Jian Pei 외

Recent works have demonstrated the benefits of capturing long-distance dependency in graphs by deeper graph neural networks (GNNs). But deeper GNNs suffer from the long-lasting scalability challenge due to the neighborho…

Graph Representation LearningRepresentation Learning

RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planning

2026-07-18 · Nguyen Viet Tuan Kiet, Bui Dinh Pham, Duong Quoc Chinh, Dao Van Tung 외 arxiv

Multi-agent planning becomes substantially harder when agents must improve specialized decision-making skills while keeping their executable implementations private. This setting arises when independently developed agent…

Sharpened Lazy Incremental Quasi-Newton Method

2023-05-26 · Aakash Lahoti, Spandan Senapati, Ketan Rajawat, Alec Koppel

The problem of minimizing the sum of $n$ functions in $d$ dimensions is ubiquitous in machine learning and statistics. In many applications where the number of observations $n$ is large, it is necessary to use incrementa…

Second-order methods

LazyVLM: Neuro-Symbolic Approach to Video Analytics

2025-05-27 · Xiangru Jian, Wei Pang, Zhengyuan Dong, Chao Zhang 외

Current video analytics approaches face a fundamental trade-off between flexibility and efficiency. End-to-end Vision Language Models (VLMs) often struggle with long-context processing and incur high computational costs,…

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

2024-08-21 · Donghoon Kim, Minjong Yoo, Honguk Woo

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 sett…

parameter-efficient fine-tuning