Distributional Robustness in Minimax Linear Quadratic Control with Wasserstein Distance

DOI10.1137/22M1494105MaRDI QIDQ5883161FDOQ5883161

Authors: Ki Hyun Kim, Insoon Yang 

Publication date: 29 March 2023

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2102.12715

Recommendations

• Minimax Q-learning control for linear systems using the Wasserstein metric
• Nonparametric Adaptive Robust Control under Model Uncertainty
• Ambiguity tube MPC
• A dynamic game approach to distributionally robust safety specifications for stochastic systems
• Minimax optimal control of stochastic uncertain systems with relative entropy constraints

zbMATH Keywords

discrete-time systemslinear systemsstochastic optimal controldistributional robustness

Mathematics Subject Classification ID

Linear systems in control theory (93C05) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20) Linear optimal control problems (49N05)

Cites Work

• Methods of conjugate gradients for solving linear systems
• Gaussian elimination is not optimal
• Distributionally Robust Control of Constrained Stochastic Systems
• On the rate of convergence in Wasserstein distance of the empirical measure
• Optimal control
• The principle of minimized iterations in the solution of the matrix eigenvalue problem
• Dynamic programming and optimal control. Vol. 2
• An implicit restarted Lanczos method for large symmetric eigenvalue problems
• On the numerical solution of the discrete-time algebraic Riccati equation
• Minimax LQG Control of Stochastic Partially Observed Uncertain Systems
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Minimax optimal control of stochastic uncertain systems with relative entropy constraints
• A dynamic game approach to distributionally robust safety specifications for stochastic systems
• Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach
• Dynamic programming and optimal control. Vol. 1.
• Data-Driven Ambiguity Sets With Probabilistic Guarantees for Dynamic Processes
• Dynamic programming subject to total variation distance ambiguity

Cited In (2)

• Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach
• Minimax Q-learning control for linear systems using the Wasserstein metric

This page was built for publication: Distributional Robustness in Minimax Linear Quadratic Control with Wasserstein Distance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5883161)