Search Results for author: James Anderson

Found 18 papers, 4 papers with code

Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments

no code implementations29 May 2024 Han Wang, Sihong He, Zhili Zhang, Fei Miao, James Anderson

In contrast to existing results, we demonstrate that both FedSVRPG-M and FedHAPG-M, both of which leverage momentum mechanisms, can exactly converge to a stationary point of the average performance function, regardless of the magnitude of environment heterogeneity.

Data-Efficient and Robust Task Selection for Meta-Learning

no code implementations11 May 2024 Donglin Zhan, James Anderson

Unlike existing algorithms, DERTS does not require any architecture modification for training and can handle noisy label data in both the support and query sets.

Meta-Learning valid

Market Power and Withholding Behavior of Energy Storage Units

no code implementations2 May 2024 Yiqian Wu, Bolun Xu, James Anderson

We present a framework to differentiate strategic capacity withholding behaviors attributed to market power from inherent competitive bidding in storage unit strategies.

Scheduling

Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning

no code implementations27 Jan 2024 Chenyu Zhang, Han Wang, Aritra Mitra, James Anderson

In response, we introduce FedSARSA, a novel federated on-policy reinforcement learning scheme, equipped with linear function approximation, to address these challenges and provide a comprehensive finite-time error analysis.

reinforcement-learning

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

no code implementations25 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 implementation19 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

Protection Against Graph-Based False Data Injection Attacks on Power Systems

no code implementations21 Apr 2023 Gal Morgenstern, Jip Kim, James Anderson, Gil Zussman, Tirza Routtenberg

We present the GFDI attack as the solution for a non-convex constrained optimization problem.

Learning Personalized Models with Clustered System Identification

1 code implementation3 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.

Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity

no code implementations4 Feb 2023 Han Wang, Aritra Mitra, Hamed Hassani, George J. Pappas, James Anderson

We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem.

FedSysID: A Federated Approach to Sample-Efficient System Identification

1 code implementation25 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

Identification of Intraday False Data Injection Attack on DER Dispatch Signals

no code implementations8 Jul 2022 Jip Kim, Siddharth Bhela, James Anderson, Gil Zussman

The urgent need for the decarbonization of power girds has accelerated the integration of renewable energy.

regression

FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation

no code implementations28 Mar 2022 Han Wang, Siddartha Marella, James Anderson

Federated learning is a framework for distributed optimization that places emphasis on communication efficiency.

Distributed Optimization Federated Learning

Learning Linear Models Using Distributed Iterative Hessian Sketching

no code implementations8 Dec 2021 Han Wang, James Anderson

This work considers the problem of learning the Markov parameters of a linear system from observed data.

Large-Scale System Identification Using a Randomized SVD

no code implementations6 Sep 2021 Han Wang, James Anderson

Learning a dynamical system from input/output data is a fundamental task in the control design pipeline.

Synthesis to Deployment: Cyber-Physical Control Architectures

no code implementations9 Dec 2020 Shih-Hao Tseng, James Anderson

We consider the problem of how to deploy a controller to a (networked) cyber-physical system (CPS).

Optimization and Control Systems and Control Systems and Control

Localized and Distributed H2 State Feedback Control

no code implementations6 Oct 2020 Jing Yu, Yuh-Shyang Wang, James Anderson

Distributed linear control design is crucial for large-scale cyber-physical systems.

SOSTOOLS Version 4.00 Sum of Squares Optimization Toolbox for MATLAB

3 code implementations17 Oct 2013 Antonis Papachristodoulou, James Anderson, Giorgio Valmorbida, Stephen Prajna, Pete Seiler, Pablo Parrilo

Specifically, polynomial and SOS variable declarations made using sossosvar, sospolyvar, sosmatrixvar, etc now return a new polynomial structure, dpvar.

Optimization and Control Mathematical Software Systems and Control

Cannot find the paper you are looking for? You can Submit a new open access paper.