mlsanityData to 14 Oct 2026

Convergence of Gradient-based MAML in LQR

arXiv 2309.06588 ↗First posted 12 Sep 2023eess.SY cs.LG cs.SYcited by 5

Not on the map. Why?

Abstract (arXiv)

The main objective of this research paper is to investigate the local convergence characteristics of Model-agnostic Meta-learning (MAML) when applied to linear system quadratic optimal control (LQR). MAML and its variations have become popular techniques for quickly adapting to new tasks by leveraging previous learning knowledge in areas like regression, classification, and reinforcement learning. However, its theoretical guarantees remain unknown due to non-convexity and its structure, making it even more challenging to ensure stability in the dynamic system setting. This study focuses on exploring MAML in the LQR setting, providing its local convergence guarantees while maintaining the stability of the dynamical system. The paper also presents simple numerical results to demonstrate the convergence properties of MAML in LQR tasks.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 13 of its 30 references that are in the map. First posted on arXiv 12 Sep 2023.

Builds on

13 of 30 references.

References · 13

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  3. 2018Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulatorcited by 250
  4. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  5. 2019On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithmscited by 132
  6. 2017Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environmentscited by 108
  7. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 58
  8. 2019LQR through the Lens of First Order Methods: Discrete-time Casecited by 40
  9. 2022MAML and ANIL Provably Learn Representationscited by 30
  10. 2019Alpha MAML: Adaptive Model-Agnostic Meta-Learningcited by 25
  11. 2022Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learningcited by 22
  12. 2020On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learningcited by 19
1 more
  1. 2020Policy Optimization for Markovian Jump Linear Quadratic Control: Gradient-Based Methods and Global Convergencecited by 4

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQRcited by 17
  2. 2025Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learningcited by 6
  3. 2024Decision Transformer as a Foundation Model for Partially Observable Continuous Controlcited by 5
  4. 2024A Moreau Envelope Approach for LQR Meta-Policy Estimationcited by 2
  5. 2025MAKO: Meta-Adaptive Koopman Operators for Learning-based Model Predictive Control of Parametrically Uncertain Nonlinear Systemscited by 1