Escaping High-order Saddles in Policy Optimization for Linear Quadratic Gaussian (LQG) Control

R. E. Kalman, “Contributions to the theory of optimal control,” Bol. soc. mat. mexicana , vol. 5, no. 2, pp. 102–119, 1960

1960

Earlier work this paper cites.

G. Hewer, “An iterative technique for the computation of the steady state gains for the discrete optimal regulator,” IEEE Trans. Automat. Contr. , vol. 16, no. 4, pp. 382–384, 1971

1971

Earlier work this paper cites.

J. C. Doyle, “Guaranteed margins for LQG regulators,” IEEE Trans. Automat. Contr. , vol. 23, no. 4, pp. 756–757, 1978

Original

1978

Earlier work this paper cites.

P. Lancaster and L. Rodman, Algebraic riccati equations . Clarendon press, 1995

1995

Earlier work this paper cites.

K. Zhou, J. C. Doyle, K. Glover, et al. , Robust and optimal control . Prentice hall New Jersey, 1996, vol. 40

1996

Earlier work this paper cites.

V. Balakrishnan and L. Vandenberghe, “Semidefinite programming duality and linear time-invariant systems,” IEEE Trans. Automat. Contr. , vol. 48, no. 1, pp. 30–41, 2003

2003

Earlier work this paper cites.

D. Bertsekas, Dynamic programming and optimal control: Volume I . Athena scientific, 2012, vol. 1

2012

Earlier work this paper cites.

G. E. Dullerud and F. Paganini, A course in robust control theory: a convex approach . Springer Science & Business Media, 2013, vol. 36

2013

Earlier work this paper cites.

R. Ge, F. Huang, C. Jin, and Y. Yuan, “Escaping from saddle points—online stochastic gradient for tensor decomposition,” in Conference on learning theory . PMLR, 2015, pp. 797–842

2015

Cited alongside, same era.

Y. Carmon and J. C. Duchi, “Gradient descent efficiently finds the cubic-regularized non-convex newton step,” arXiv preprint arXiv:1612.00547 , 2016

Original

2016

Cited alongside, same era.

C. Jin, R. Ge, P. Netrapalli, S. M. Kakade, and M. I. Jordan, “How to escape saddle points efficiently,” in International Conference on Machine Learning . PMLR, 2017, pp. 1724–1732

2017

Cited alongside, same era.

M. Fazel, R. Ge, S. M. Kakade, and M. Mesbahi, “Global convergence of policy gradient methods for linearized control problems,” arXiv preprint arXiv:1801.05039 , 2018

Original

2018

Cited alongside, same era.

K. Zhang, Z. Yang, and T. Basar, “Policy optimization provably converges to nash equilibria in zero-sum linear quadratic games,” Advances in Neural Information Processing Systems , vol. 32, pp. 11 602–11 614, 2019

2019

Later among the works it cites.

J. Bu, A. Mesbahi, M. Fazel, and M. Mesbahi, “LQR through the lens of first order methods: Discrete-time case,” arXiv preprint arXiv:1907.08921 , 2019

Original

2019

Later among the works it cites.

L. Furieri, Y. Zheng, and M. Kamgarpour, “Learning the globally optimal distributed LQ regulator,” in Learning for Dynamics and Control . PMLR, 2020, pp. 287–297

2020

Later among the works it cites.

Y. Sun and M. Fazel, “Learning optimal controllers by policy gradient: Global optimality via convex parameterization,” in 2021 60th IEEE Conference on Decision and Control (CDC) . IEEE, 2021, pp. 4576–4581

2021

Later among the works it cites.