Imagen de Portada

Convergence Guarantees of Model-free Policy Gradient Methods for LQR with Stochastic Data

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Song, Bowen, Iannelli, Andrea
Formato:	Preprint
Publicado:	2025
Materias:	Systems and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Stochastic Gradient Descent Approach to Design Policy Gradient Methods for LQR
por: Song, Bowen, et al.
Publicado: (2026)

Sample-Efficient Model-Free Policy Gradient Methods for Stochastic LQR via Robust Linear Regression
por: Song, Bowen, et al.
Publicado: (2025)

Robustness of Online Identification-based Policy Iteration to Noisy Data
por: Song, Bowen, et al.
Publicado: (2025)

The Role of Identification in Data-driven Policy Iteration: A System Theoretic Study
por: Song, Bowen, et al.
Publicado: (2024)

Convergence and Robustness of Value and Policy Iteration for the Linear Quadratic Regulator
por: Song, Bowen, et al.
Publicado: (2024)

Policy Gradient Methods for the Cost-Constrained LQR: Strong Duality and Global Convergence
por: Zhao, Feiran, et al.
Publicado: (2024)

On Globally Optimal Stochastic Policy Gradient Methods for Domain Randomized LQR Synthesis
por: Nguyen-Le, Alex, et al.
Publicado: (2026)

Policy Gradient Bounds in Multitask LQR
por: Stamouli, Charis, et al.
Publicado: (2025)

Convergence Analysis of Gradient Flow for Overparameterized LQR Formulations
por: de Oliveira, Arthur Castello B., et al.
Publicado: (2024)

Convergence and stability of Q-learning in Hierarchical Reinforcement Learning
por: Manenti, Massimiliano, et al.
Publicado: (2025)

Stability-Certified On-Policy Data-Driven LQR via Recursive Learning and Policy Gradient
por: Sforni, Lorenzo, et al.
Publicado: (2024)

Hidden Convexity in Active Learning: A Convexified Online Input Design for ARX Systems
por: Chatzikiriakos, Nicolas, et al.
Publicado: (2025)

Policy Gradient for LQR with Domain Randomization
por: Fujinami, Tesshu, et al.
Publicado: (2025)

Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches
por: Zhao, Feiran, et al.
Publicado: (2025)

On the (almost) Global Exponential Convergence of the Overparameterized Policy Optimization for the LQR Problem
por: Wafi, Moh Kamalul, et al.
Publicado: (2025)

Adaptive control mechanisms in gradient descent algorithms
por: Iannelli, Andrea
Publicado: (2025)

Data-Driven Stabilization of Continuous-Time LTI Systems from Noisy Input-Output Data
por: Bosso, Alessandro, et al.
Publicado: (2025)

LQR for Systems with Probabilistic Parametric Uncertainties: A Gradient Method
por: Cui, Leilei, et al.
Publicado: (2026)

Stochastic LQR Design With Disturbance Preview
por: Liu, Jietian, et al.
Publicado: (2024)

Data-Enabled Policy Optimization for Direct Adaptive Learning of the LQR
por: Zhao, Feiran, et al.
Publicado: (2024)

Accelerated ADMM: Automated Parameter Tuning and Improved Linear Convergence
por: Tavakoli, Meisam, et al.
Publicado: (2025)

Beyond Bounded Noise: Stochastic Set-Membership Estimation for Nonlinear Systems
por: Brändle, Felix, et al.
Publicado: (2026)

Learning Soft Constrained MPC Value Functions: Efficient MPC Design and Implementation providing Stability and Safety Guarantees
por: Chatzikiriakos, Nicolas, et al.
Publicado: (2024)

Revisiting LQR Control from the Perspective of Receding-Horizon Policy Gradient
por: Zhang, Xiangyuan, et al.
Publicado: (2023)

A Policy Gradient Framework for Stochastic Optimal Control Problems with Global Convergence Guarantee
por: Zhou, Mo, et al.
Publicado: (2023)

A hybrid systems framework for data-based adaptive control of linear time-varying systems
por: Iannelli, Andrea, et al.
Publicado: (2024)

Online Convex Optimization and Integral Quadratic Constraints: An automated approach to regret analysis
por: Jakob, Fabian, et al.
Publicado: (2025)

Data-Driven LQR with Finite-Time Experiments via Extremum-Seeking Policy Iteration
por: Carnevale, Guido, et al.
Publicado: (2024)

A Globally Convergent Policy Gradient Method for Linear Quadratic Gaussian (LQG) Control
por: Sadamoto, Tomonori, et al.
Publicado: (2023)

Global Convergence of Policy Gradient Methods for ReLU Controllers in Linear Quadratic Regulation
por: Rodriguez-Gil, Jhojan A., et al.
Publicado: (2026)

Stochastic MPC with Online-optimized Policies and Closed-loop Guarantees
por: Bartos, Marcell, et al.
Publicado: (2025)

MR-ARL: Model Reference Adaptive Reinforcement Learning for Robustly Stable On-Policy Data-Driven LQR
por: Borghesi, Marco, et al.
Publicado: (2024)

Density-Driven Optimal Control: Convergence Guarantees for Stochastic LTI Multi-Agent Systems
por: Lee, Kooktae
Publicado: (2026)

Analyzing the Impact of Computation in Adaptive Dynamic Programming for Stochastic LQR Problem
por: Cao, Wenhan, et al.
Publicado: (2024)

Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimization
por: Kanakeri, Vinay, et al.
Publicado: (2025)

A Bayesian Perspective on the Data-Driven LQR
por: Schwaller, Thierry, et al.
Publicado: (2026)

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
por: Ding, Dongsheng, et al.
Publicado: (2023)

Sample Complexity Bounds for Linear System Identification from a Finite Set
por: Chatzikiriakos, Nicolas, et al.
Publicado: (2024)

On the Effect of Quadratic Regularization in Direct Data-Driven LQR
por: Klädtke, Manuel, et al.
Publicado: (2026)

Power-Constrained Policy Gradient Methods for LQR
por: Verma, Ashwin, et al.
Publicado: (2025)