Policy Compatible Skill Incremental Learning via Lazy Learning Interface

NeurIPSSpotlight2025

Authors
Daehee Lee, Dongsu Lee, TaeYoon Kwack, Wonje Choi, Honguk Woo
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

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 th…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

agent rag

← All NeurIPS 2025 Spotlight papers · Browse the whole archive