Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning
For embodied agents, this work addresses catastrophic forgetting in continual task acquisition by explicitly organizing reusable skills, showing measurable gains over prior methods.
Embodied Continual Learning (ECL) suffers from severe catastrophic forgetting due to feature drift in closed-loop control. The proposed SCE framework uses compositional skill grounding and dual execution-and-transition experts to enable skill reuse, achieving consistent improvements in retention and overall task performance on LIBERO benchmarks and real-world tasks.
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/.