用元学习提升控制模型对参数变化的适应能力。
Learning to Adapt: Reptile-D-Learning for Robust and Efficient Control Under Parametric Uncertainty
- 用元学习捕捉不同参数系统的共性动态结构
- 在未见参数配置下仍保持稳定控制性能
- 适合需要快速适应新环境的机器人控制场景
基于学习的李雅普诺夫控制（LLC）为非线性系统提供形式化稳定性保障，但其有效性依赖于精确的系统模型。参数变化和不确定性可能导致稳定性约束失效，引发高昂的重新训练成本。尽管D-learning无需显式动力学模型即可估计李雅普诺夫导数，但仍受限于单任务动态，且在大参数偏移下性能下降。我们提出Reptile-D-learning框架，利用Reptile元学习算法捕捉不同参数系统间的共享动态结构，从而学习可泛化的李雅普诺夫网络初始化与高性能控制器。在多个非线性控制系统上的实验表明，Reptile-D-learning显著提升了对未见参数配置的泛化能力与快速适应性能。
原文摘要 · Abstract (English)
Learning-based Lyapunov Control (LLC) provides formal stability guarantees for nonlinear systems, but its validity relies heavily on accurate system models. Parameter variations and uncertainties may invalidate stability constraints, leading to costly retraining. Although D-learning can estimate Lyapunov derivatives without relying on explicit dynamics models, it remains limited by single-task dynamics and degrades under large parameter shifts. We propose Reptile-D-learning, a framework that leverages the Reptile meta-learning algorithm to capture shared dynamical structures across systems with different parameters, thereby learning a generalizable Lyapunov network initialization and a high-performance controller. Experiments on multiple nonlinear control systems demonstrate that Reptile-D-learning significantly improves both generalization and rapid adaptation to unseen parameter configurations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。