Control of chaotic systems by deep reinforcement learning - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur Accéder directement au contenu
Article Dans Une Revue Proceedings of the Royal Society of London. Series A, Mathematical and physical sciences Année : 2019

Control of chaotic systems by deep reinforcement learning

Résumé

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.
Fichier principal
Vignette du fichier
1906.07672.pdf (5.01 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02406677 , version 1 (26-12-2020)

Identifiants

Citer

Michele Alessandro Bucci, Onofrio Semeraro, Alexandre Allauzen, Guillaume Wisniewski, Laurent Cordier, et al.. Control of chaotic systems by deep reinforcement learning. Proceedings of the Royal Society of London. Series A, Mathematical and physical sciences, In press, 475 (2231), pp.1-20. ⟨10.1098/rspa.2019.0351⟩. ⟨hal-02406677⟩
232 Consultations
112 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More