An official website of the United States government
Many optimal and robust control problems are nonconvex and potentially nonsmooth in their policy optimization forms. In Part II of this paper, we introduce a new and unified Extended Convex Lifting (ECL) framework to reveal hidden convexity in classical optimal and robust control problems from a modern optimization perspective. Our optimization perspective offers a bridge between nonconvex policy optimization and convex reformulations, enabling convex analysis for nonconvex problems. Despite non-convexity and non-smoothness, the existence of an ECL not only reveals that minimizing the original function is equivalent to a convex problem but also certifies a class of first-order non-degenerate stationary points to be globally optimal. This ECL framework can cover many benchmark control problems, including LQR, LQG, and H∞ robust control. We also believe that the new ECL framework will be of independent interest for analyzing nonconvex problems beyond control.
more »
« less
This content will become publicly available on March 18, 2027
Benign Nonconvex Landscapes in Optimal and Robust Control, Part I: Global Optimality
Direct policy search has achieved great empirical success in reinforcement learning. Many recent studies have revisited its theoretical foundation for continuous control, which reveals elegant nonconvex geometry in various benchmark problems. This paper considers two fundamental optimal and robust control problems with partial observability: Linear Quadratic Gaussian (LQG) control and H∞ robust control. In the policy space, the former problem is smooth but nonconvex, while the latter one is nonsmooth and nonconvex. We highlight some interesting and surprising “discontinuity” of LQG and H∞ cost functions around the boundary of their domains. Despite the lack of convexity (and possibly smoothness), we show that for a class of non-degenerate policies, all Clarke stationary points are globally optimal and there is no spurious local minimum for both LQG and H∞ control. The main results are established by a new and unified framework of Extended Convex Lifting (ECL), which reconciles the gap between nonconvex policy optimization and convex reformulations. This ECL framework is of independent interest, and we discuss its details in Part II of this paper.
more »
« less
- PAR ID:
- 10677009
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Transactions on Automatic Control
- ISSN:
- 0018-9286
- Page Range / eLocation ID:
- 1 to 16
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Ozay, Necmiye; Balzano, Laura; Panagou, Dimitra; Abate, Alessandro (Ed.)Many optimal and robust control problems are nonconvex and potentially nonsmooth in their policy optimization forms. In this paper, we introduce the Extended Convex Lifting (ECL) framework, which reveals hidden convexity in classical optimal and robust control problems from a modern optimization perspective. Our ECL framework offers a bridge between nonconvex policy optimization and convex reformulations. Despite non-convexity and non-smoothness, the existence of an ECL for policy optimization not only reveals that the policy optimization problem is equivalent to a convex problem, but also certifies a class of first-order non-degenerate stationary points to be globally optimal. We further show that this ECL framework encompasses many benchmark control problems, including LQR, state-feedback and output-feedback H-infinity robust control. We believe that ECL will also be of independent interest for analyzing nonconvex problems beyond control.more » « less
-
Common reinforcement learning methods seek optimal controllers for unknown dynamical systems by searching in the "policy" space directly. A recent line of research, starting with [1], aims to provide theoretical guarantees for such direct policy-update methods by exploring their performance in classical control settings, such as the infinite horizon linear quadratic regulator (LQR) problem. A key property these analyses rely on is that the LQR cost function satisfies the "gradient dominance" property with respect to the policy parameters. Gradient dominance helps guarantee that the optimal controller can be found by running gradient-based algorithms on the LQR cost. The gradient dominance property has so far been verified on a case-by-case basis for several control problems including continuous/discrete time LQR, LQR with decentralized controller, H2/H∞ robust control.In this paper, we make a connection between this line of work and classical convex parameterizations based on linear matrix inequalities (LMIs). Using this, we propose a unified framework for showing that gradient dominance indeed holds for a broad class of control problems, such as continuous- and discrete-time LQR, minimizing the L2 gain, and problems using system-level parameterization. Our unified framework provides insights into the landscape of the cost function as a function of the policy, and enables extending convergence results for policy gradient descent to a much larger class of problems.more » « less
-
This paper addresses the end-to-end sample complexity bound for learning the H2 optimal controller (the Linear Quadratic Gaussian (LQG) problem) with unknown dynamics, for potentially unstable Linear Time Invariant (LTI) systems. The robust LQG synthesis procedure is performed by considering bounded additive model uncertainty on the coprime factors of the plant. The closed-loopi dentification of the nominal model of the true plant is performed by constructing a Hankel-like matrix from a single time-series of noisy finite length input-output data, using the ordinary least squares algorithm from Sarkar and Rakhlin (2019). Next, an H∞ bound on the estimated model error is provided and the robust controller is designed via convex optimization, much in the spirit of Mania et al. (2019) and Zheng et al. (2020b), while allowing for bounded additive uncertainty on the coprime factors of the model. Our conclusions are consistent with previous results on learning the LQG and LQR controllers.more » « less
-
— In large-scale and model-free settings, first-order algorithms are often used in an attempt to find the optimal control action without identifying the underlying dynamics. The convergence properties of these algorithms remain poorly understood because of nonconvexity. In this paper, we revisit the continuous-time linear quadratic regulator problem and take a step towards demystifying the efficiency of gradient-based strategies. Despite the lack of convexity, we establish a linear rate of convergence to the globally optimal solution for the gradient descent algorithm. The key component of our analysis is that we relate the gradient-flow dynamics associated with the nonconvex formulation to that of a convex reparameterization. This allows us to provide convergence guarantees for the nonconvex approach from its convex counterpart.more » « less
