ru
ru
Source
Chaos, Solitons & Fractals
DATE OF PUBLICATION
07/02/2024
Authors
Dmitry Dylov Oleg Rogov Rishat Zagidullin Sergey Rykovanov Nikolay Kalmykov
Share

Suppressing modulation instability with reinforcement learning

Modulation instability, Reinforcement learning, q-learning, Complex Ginzburg–Landau equation

Abstract

Modulation instability is a phenomenon of spontaneous pattern formation in nonlinear media, oftentimes leading to an unpredictable behavior and a degradation of a signal of interest. We propose an approach based on reinforcement learning to suppress the unstable modes in the system by optimizing the parameters for the time modulation of the potential in the nonlinear system. We test our approach in 1D and 2D cases and propose a new class of physically-meaningful reward functions to guarantee tamed instability.

Full text DOWNLOAD pdf

Similar publications

IJCAI
Probabilistically Robust Watermarking of Neural Networks
Mikhail Pautov, Nikita Bogdanov, Stanislav Pyatkin, Oleg Rogov, Ivan Oseledets
SOURCE
Aging Cell
Epistemic uncertainty challenges aging clock reliability in predicting rejuvenation effects
Dmitrii Kriukov, Ekaterina Kuzmina, Evgeniy Efimov, Dmitry Dylov, Ekaterina Khrameeva
SOURCE
Nature
Medical image captioning via generative pretrained transformers
Alexander Selivanov, Oleg Rogov, Daniil Chesakov, Artem Shelmanov, Irina Fedulova, Dmitry Dylov
SOURCE
EMNLP
ALToolbox: A Set of Tools for Active Learning Annotation of Natural Language Texts
Akim Tsvigun, Leonid Sanochkin, Daniil Larionov, Gleb Kuzmin, Artem Vazhentsev, Ivan Lazichny, Nikita Khromov, Danil Kireev, Aleksandr Rubashevskii, Dmitry Dylov, Igor Galitskiy, Artem Shelmanov
SOURCE
IEEE Access
LAMBO: Landmarks Augmentation With Manifold-Barycentric Oversampling
Iaroslav Bespalov, Nazar Buzun, Oleg Kachan, Dmitry Dylov
SOURCE
COLT
Strong Gaussian Approximation for the Sum of Random Vectors
Nazar Buzun, Nikolay Shvetsov, Dmitry Dylov
SOURCE
Contact us
Join AIRI
You can ask us a question or suggest a joint project in the field of AI

Message sent.

Thank you!

Something went wrong. Try again