Model+Learning-based Optimal Control: An Inverted Pendulum Study

Simone Baldi, Muhammad Ridho Rosa, Yuzhang Wang

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

16 Downloads (Pure)


This work extends and compares some recent model+learning-based methodologies for optimal control with input saturation. We focus on two methodologies: a model-based actor-critic (MBAC) strategy, and a nonlinear policy iteration strategy. To evaluate the performance of the algorithms, these strategies are applied to the swinging up an inverted pendulum. Numerical simulations show that the neural network approximation in the MBAC strategy can be poor, and the algorithm may converge far from the optimum. In the MBAC approach neither stabilization nor monotonic convergence can be guaranteed, and it is observed that the best value function is not always corresponding to the last one. On the other side the nonlinear policy iteration approach guarantees that every new control policy is stabilizing and generally leads to a monotonically decreasing cost.

Original languageEnglish
Title of host publicationProceedings of the IEEE 16th International Conference on Control and Automation, ICCA 2020
Place of PublicationPiscataway, NJ, USA
ISBN (Electronic)978-1-7281-9093-8
Publication statusPublished - 2020
Event16th IEEE International Conference on Control and Automation, ICCA 2020 - Virtual, Sapporo, Hokkaido, Japan
Duration: 9 Oct 202011 Oct 2020


Conference16th IEEE International Conference on Control and Automation, ICCA 2020
CityVirtual, Sapporo, Hokkaido

Bibliographical note

Accepted Author Manuscript


Dive into the research topics of 'Model+Learning-based Optimal Control: An Inverted Pendulum Study'. Together they form a unique fingerprint.

Cite this