LQGNET: Hybrid Model-Based and Data-Driven Linear Quadratic Stochastic Control
Authors:
- 4 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Stochastic control deals with finding an optimal control signal for a dynamical system in a setting with uncertainty, playing a key role in numerous applications. The linear quadratic Gaussian (LQG) is a widely-used setting, where the system dynamics is represented as a linear Gaussian state-space (SS) model, and the objective function is quadratic. For this setting, the optimal controller is obtained in closed form by the separation principle. However, in practice, the underlying system dynamics often cannot be faithfully captured by a fully known linear Gaussian SS model, limiting its performance. Here, we present LQGNet, a stochastic controller that leverages data to operate under partially known dynamics. LQGNet augments the state tracking module of separation-based control with a dedicated trainable algorithm. The resulting system preserves the operation of classic LQG control while learning to cope with partially known SS models without having to fully identify the dynamics. We empirically show that LQGNet outperforms classic stochastic control by overcoming mismatched SS models.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Reward is enoughArtificial Intelligence, 2021
- A Survey of Deep Learning Applications to Autonomous Vehicle ControlIEEE Transactions on Intelligent Transportation Systems, 2020
- Deep Reinforcement Learning: A Brief SurveyIEEE Signal Processing Magazine, 2017
- Optimal Control2012
- A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems2005
- Optimal control-1950 to 1985IEEE Control Systems, 1996
- Duality between the discrete-time Kalman filter and LQ control lawIEEE Transactions on Automatic Control, 1995
- Separation of Estimation and Control for Decentralized Stochastic Control SystemsIFAC Proceedings Volumes, 1978
- The role and use of the stochastic linear-quadratic-Gaussian problem in control system designIEEE Transactions on Automatic Control, 1971
- A General Solution for Linear, Sampled-Data ControlJournal of Basic Engineering, 1963