Supplementary material from "Control of chaotic systems by deep reinforcement learning"
Version 2 2019-11-05, 13:12Version 2 2019-11-05, 13:12
Version 1 2019-10-24, 14:40Version 1 2019-10-24, 14:40
Posted on 2019-11-05 - 13:12
Deep reinforcement learning (DRL) is applied to control a nonlinear, chaotic system governed by the one-dimensional Kuramoto–Sivashinsky (KS) equation. DRL uses reinforcement learning principles for the determination of optimal control solutions and deep neural networks for approximating the value function and the control policy. Recent applications have shown that DRL may achieve superhuman performance in complex cognitive tasks. In this work, we show that using restricted localized actuation, partial knowledge of the state based on limited sensor measurements and model-free DRL controllers, it is possible to stabilize the dynamics of the KS system around its unstable fixed solutions, here considered as target states. The robustness of the controllers is tested by considering several trajectories in the phase space emanating from different initial conditions; we show that DRL is always capable of driving and stabilizing the dynamics around target states. The possibility of controlling the KS system in the chaotic regime by using a DRL strategy solely relying on local measurements suggests the extension of the application of RL methods to the control of more complex systems such as drag reduction in bluff-body wakes or the enhancement/diminution of turbulent mixing.
CITE THIS COLLECTION
DataCite
DataCiteDataCite
3 Biotech3 Biotech
3D Printing in Medicine3D Printing in Medicine
3D Research3D Research
3D-Printed Materials and Systems3D-Printed Materials and Systems
4OR4OR
AAPG BulletinAAPG Bulletin
AAPS OpenAAPS Open
AAPS PharmSciTechAAPS PharmSciTech
Abhandlungen aus dem Mathematischen Seminar der Universität HamburgAbhandlungen aus dem Mathematischen Seminar der Universität Hamburg
ABI Technik (German)ABI Technik (German)
Academic MedicineAcademic Medicine
Academic PediatricsAcademic Pediatrics
Academic PsychiatryAcademic Psychiatry
Academic QuestionsAcademic Questions
Academy of Management DiscoveriesAcademy of Management Discoveries
Academy of Management JournalAcademy of Management Journal
Academy of Management Learning and EducationAcademy of Management Learning and Education
Academy of Management PerspectivesAcademy of Management Perspectives
Academy of Management ProceedingsAcademy of Management Proceedings
Academy of Management ReviewAcademy of Management Review
Bucci, M. A.; Semeraro, O.; Allauzen, A.; Wisniewski, G.; Cordier, L.; Mathelin, L. (2019). Supplementary material from "Control of chaotic systems by deep reinforcement learning". The Royal Society. Collection. https://doi.org/10.6084/m9.figshare.c.4711487.v2