A Caltech Library Service

Model Learning Predictive Control in Nonlinear Dynamical Systems

Lale, Sahin and Azizzadenesheli, Kamyar and Hassibi, Babak and Anandkumar, Anima (2021) Model Learning Predictive Control in Nonlinear Dynamical Systems. In: 2021 60th IEEE Conference on Decision and Control (CDC). IEEE , Piscataway, NJ, pp. 757-762. ISBN 978-1-6654-3659-5.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We study the problem of online learning and control in partially observable nonlinear dynamical systems, where the model dynamics are unknown and the controlling agent has only access to the system outputs. We propose Model Learning Predictive Control (MLPC), an efficient online control framework that learns to control the unknown system and minimizes the overall control cost. MLPC employs Random Fourier Features (RFF) to represent the nonlinear system dynamics and learns the underlying system up to a confidence interval. Once a reliable estimate of the dynamics is obtained, MLPC deploys an MPC oracle with the estimated system dynamics for planning. MLPC occasionally updates the underlying model estimates and improves the accuracy and the effectiveness of the MPC policies. We derive a novel finite-time approximation error bound under RFF learning and provide stability guarantees for single trajectory online control. We show that MLPC attains O̅(T^(2/3)) regret after T time steps in online control of stable partially observable nonlinear systems against the controller that uses the same MPC oracle with the true system dynamics. We empirically demonstrate the performance of MLPC on the inverted pendulum task and show the flexibility of the proposed general framework via deploying different planning strategies for the controller design to achieve low-cost control policies.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Lale, Sahin0000-0002-7191-346X
Azizzadenesheli, Kamyar0000-0001-8507-1868
Hassibi, Babak0000-0002-1375-5838
Anandkumar, Anima0000-0002-6974-6797
Additional Information:© 2021 IEEE.
Record Number:CaltechAUTHORS:20220210-721786000
Persistent URL:
Official Citation:S. Lale, K. Azizzadenesheli, B. Hassibi and A. Anandkumar, "Model Learning Predictive Control in Nonlinear Dynamical Systems," 2021 60th IEEE Conference on Decision and Control (CDC), 2021, pp. 757-762, doi: 10.1109/CDC45484.2021.9683670
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:113408
Deposited By: George Porter
Deposited On:11 Feb 2022 18:54
Last Modified:23 Dec 2022 00:54

Repository Staff Only: item control page