Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for the Model-free LQR

1 code implementation • 25 Jan 2024 • Leonardo F. Toso, Donglin Zhan, James Anderson, Han Wang

We investigate the problem of learning Linear Quadratic Regulators (LQR) in a multi-task, heterogeneous, and model-free setting.

Meta-Learning

Oracle Complexity Reduction for Model-free LQR: A Stochastic Variance-Reduced Policy Gradient Approach

1 code implementation • 19 Sep 2023 • Leonardo F. Toso, Han Wang, James Anderson

We investigate the problem of learning an $\epsilon$-approximate solution for the discrete-time Linear Quadratic Regulator (LQR) problem via a Stochastic Variance-Reduced Policy Gradient (SVRPG) approach.

Policy Gradient Methods

Meta-Learning Operators to Optimality from Multi-Task Non-IID Data

no code implementations • 8 Aug 2023 • Thomas T. C. K. Zhang, Leonardo F. Toso, James Anderson, Nikolai Matni

and non-isotropic.

Generalization Bounds Meta-Learning +1

Learning Personalized Models with Clustered System Identification

1 code implementation • 3 Apr 2023 • Leonardo F. Toso, Han Wang, James Anderson

We address the problem of learning linear system models from observing multiple trajectories from different system dynamics.

FedSysID: A Federated Approach to Sample-Efficient System Identification

1 code implementation • 25 Nov 2022 • Han Wang, Leonardo F. Toso, James Anderson

We study the problem of learning a linear system model from the observations of $M$ clients.

Federated Learning