2000 character limit reached
Optimality of Linear Policies for Distributionally Robust Linear Quadratic Gaussian Regulator with Stationary Distributions (2410.22826v4)
Published 30 Oct 2024 in math.OC
Abstract: We prove that output-feedback linear policies remain optimal for solving the Linear Quadratic Gaussian regulation problem in the face of worst-case process and measurement noise distributions when these are independent, stationary, and known to be within a radius (in the Wasserstein sense) to some reference zero-mean Gaussian noise distributions. Additionally, we establish the existence of a Nash equilibrium of the zero-sum game between a control engineer, who minimizes control cost, and a fictitious adversary, who chooses the noise distributions that maximize this cost. For general (possibly non-Gaussian) reference noise distributions, we establish a quasi closed-form solution for the worst-case distributions against linear policies. Our work provides a less conservative alternative compared to recent work in distributionally robust control.
- P. Mohajerin Esfahani and D. Kuhn, “Data-driven distributionally robust optimization using the wasserstein metric: Performance guarantees and tractable reformulations,” Mathematical Programming, vol. 171, no. 1, pp. 115–166, 2018.
- J. Blanchet and K. Murthy, “Quantifying distributional model risk via optimal transport,” Mathematics of Operations Research, vol. 44, no. 2, pp. 565–600, 2019.
- J. Blanchet, K. Murthy, and F. Zhang, “Optimal transport-based distributionally robust optimization: Structural properties and iterative schemes,” Mathematics of Operations Research, vol. 47, no. 2, pp. 1500–1529, 2022.
- R. Gao and A. Kleywegt, “Distributionally robust stochastic optimization with wasserstein distance,” Mathematics of Operations Research, vol. 48, no. 2, pp. 603–655, 2023.
- D. Kuhn, P. M. Esfahani, V. A. Nguyen, and S. Shafieezadeh-Abadeh, “Wasserstein distributionally robust optimization: Theory and applications in machine learning,” in Operations research & management science in the age of analytics. Informs, 2019, pp. 130–166.
- B. Han, “Distributionally robust kalman filtering with volatility uncertainty,” arXiv preprint arXiv:2302.05993, 2023.
- K. Kim and I. Yang, “Distributional robustness in minimax linear quadratic control with wasserstein distance,” SIAM Journal on Control and Optimization, vol. 61, no. 2, pp. 458–483, 2023.
- G. Kotsalis, G. Lan, and A. S. Nemirovski, “Convex optimization for finite-horizon robust covariance control of linear stochastic systems,” SIAM Journal on Control and Optimization, vol. 59, no. 1, pp. 296–319, 2021.
- I. R. Petersen, M. R. James, and P. Dupuis, “Minimax optimal control of stochastic uncertain systems with relative entropy constraints,” IEEE Transactions on Automatic Control, vol. 45, no. 3, pp. 398–412, 2000.
- B. P. Van Parys, D. Kuhn, P. J. Goulart, and M. Morari, “Distributionally robust control of constrained stochastic systems,” IEEE Transactions on Automatic Control, vol. 61, no. 2, pp. 430–442, 2015.
- I. Yang, “Wasserstein distributionally robust stochastic control: A data-driven approach,” IEEE Transactions on Automatic Control, vol. 66, no. 8, pp. 3863–3870, 2020.
- B. Taskesen, D. Iancu, Ç. Koçyiğit, and D. Kuhn, “Distributionally robust linear quadratic control,” Advances in Neural Information Processing Systems, vol. 36, 2024.
- A. Terpin, N. Lanzetti, B. Yardim, F. Dorfler, and G. Ramponi, “Trust region policy optimization with optimal transport discrepancies: Duality and algorithm for continuous actions,” Advances in Neural Information Processing Systems, vol. 35, pp. 19 786–19 797, 2022.
- A. Terpin, N. Lanzetti, M. Gadea, and F. Dörfler, “Learning diffusion at lightspeed,” in Advances in Neural Information Processing Systems, 2024, oral Presentation.
- N. Lanzetti, S. Bolognani, and F. Dörfler, “First-order conditions for optimization in the wasserstein space,” arXiv preprint arXiv:2209.12197, 2022.
- N. Lanzetti, A. Terpin, and F. Dörfler, “Variational analysis in the wasserstein space,” arXiv preprint arXiv:2406.10676, 2024.
- V. A. Nguyen, S. Shafiee, D. Filipović, and D. Kuhn, “Mean-covariance robust risk measurement,” arXiv preprint arXiv:2112.09959, 2021.
- M. Benzi, G. H. Golub, and J. Liesen, “Numerical solution of saddle point problems,” Acta numerica, vol. 14, pp. 1–137, 2005.
- M. Razaviyayn, T. Huang, S. Lu, M. Nouiehed, M. Sanjabi, and M. Hong, “Nonconvex min-max optimization: Applications, challenges, and recent theoretical advances,” IEEE Signal Processing Magazine, vol. 37, no. 5, pp. 55–66, 2020.
- J. M. Danskin, “The theory of max-min, with applications,” SIAM Journal on Applied Mathematics, vol. 14, no. 4, pp. 641–664, 1966.
- S. Shafieezadeh Abadeh, V. A. Nguyen, D. Kuhn, and P. M. Mohajerin Esfahani, “Wasserstein distributionally robust kalman filtering,” Advances in Neural Information Processing Systems, vol. 31, 2018.
- A. Ben-Tal, S. Boyd, and A. Nemirovski, “Control of uncertainty-affected discrete time linear systems via convex programming,” Submitted to SIAM Journal on Control and Optimization, 2005.
- J. Skaf and S. P. Boyd, “Design of affine controllers via convex optimization,” IEEE Transactions on Automatic Control, vol. 55, no. 11, pp. 2476–2487, 2010.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.