Corpus ID: 202718992

Efficient Learning of Distributed Linear-Quadratic Controllers

@article{Fattahi2019EfficientLO,
  title={Efficient Learning of Distributed Linear-Quadratic Controllers},
  author={S. Fattahi and N. Matni and S. Sojoudi},
  journal={ArXiv},
  year={2019},
  volume={abs/1909.09895}
}
In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed controllers can be learned with sub-linear sample complexity and computed with near-linear time complexity, both measured with respect to the dimension of the system. In particular… Expand
Distributed Online Linear Quadratic Control for Linear Time-invariant Systems
A Backstepping Approach to System Level Synthesis for Spatially-Invariant Systems
Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of Samples
Graph Neural Networks for Distributed Linear-Quadratic Control
Learning the Globally Optimal Distributed LQ Regulator

References

SHOWING 1-10 OF 75 REFERENCES
On the Sample Complexity of the Linear Quadratic Regulator
Localized LQR optimal control
Transformation of optimal centralized controllers into near-global static distributed controllers
Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
A Characterization of Convex Problems in Decentralized Control$^ast$
A System-Level Approach to Controller Synthesis
Structured optimal and robust control with multiple criteria: a convex solution
Regret Bounds for the Adaptive Control of Linear Quadratic Systems
Distributed control of spatially invariant systems
Structured H∞-optimal control for nested interconnections: A state-space solution
  • C. Scherer
  • Mathematics, Computer Science
  • Syst. Control. Lett.
  • 2013
...
1
2
3
4
5
...