Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning

2026-06-14

AI Summary

This work addresses catastrophic forgetting and feature drift in embodied continual learning caused by closed-loop control. To tackle these challenges, the authors propose the Skill-Compositional Experts (SCE) framework, which leverages Compositional Skill Grounding (CSG) to construct a reusable and explicitly structured skill library from task demonstrations. SCE further introduces a dual-mechanism architecture—comprising Execution Experts and Transfer Experts (DETE)—to enable efficient compositional learning of new tasks and smooth transitions between skills. Evaluated on the LIBERO benchmark and real-world robotic platforms, SCE significantly improves task retention and overall performance. Ablation studies and feature drift analyses confirm its effectiveness, marking the first approach to achieve structured, composable embodied continual learning.

Abstract

Embodied Continual Learning (ECL) aims to enable robots to continually acquire new manipulation tasks while retaining previously learned behaviors under closed-loop control. Compared with conventional continual learning, ECL suffers from more severe catastrophic forgetting. Feature drift accumulated under closed-loop control progressively propagates through sequential decision-making, leading to degradation of previously learned behaviors. A key challenge in ECL lies in structured skill reuse across continually evolving tasks, since existing methods primarily focus on skill learning without explicitly organizing them for coherent task execution. To address this issue, we propose SCE, a Skill-Compositional Experts framework for ECL. SCE builds a skill base via Compositional Skill Grounding (CSG), which decomposes task demonstrations into reusable skills. Based on this, Dual Execution-and-Transition Experts (DETE) enable new task learning through skill composition, where one branch ensures skill execution and the other supports transitions between skills for coherent behavior. Experiments on LIBERO benchmarks and real-world manipulation tasks demonstrate that SCE consistently improves retention and overall task performance. Further feature drift analyses and ablation studies verify the effectiveness of our method. Project website: https://eqcy.github.io/sce/.

Problem

• Embodied Continual Learning
• catastrophic forgetting
• skill reuse
• feature drift
• task composition

Innovation

• Skill Composition
• Embodied Continual Learning
• Compositional Skill Grounding
• Dual Experts
• Catastrophic Forgetting