Standard

A Deep Reinforcement Learning Algorithm for Smart Control of Hysteresis Phenomena in a Mode-Locked Fiber Laser. / Kokhanovskiy, Alexey; Shevelev, Alexey; Serebrennikov, Kirill et al.

In: Photonics, Vol. 9, No. 12, 921, 01.12.2022.

Research output: Contribution to journal › Article › peer-review

Harvard

Kokhanovskiy, A, Shevelev, A, Serebrennikov, K, Kuprikov, E & Turitsyn, S 2022, 'A Deep Reinforcement Learning Algorithm for Smart Control of Hysteresis Phenomena in a Mode-Locked Fiber Laser', Photonics, vol. 9, no. 12, 921. https://doi.org/10.3390/photonics9120921

APA

Kokhanovskiy, A., Shevelev, A., Serebrennikov, K., Kuprikov, E., & Turitsyn, S. (2022). A Deep Reinforcement Learning Algorithm for Smart Control of Hysteresis Phenomena in a Mode-Locked Fiber Laser. Photonics, 9(12), [921]. https://doi.org/10.3390/photonics9120921

Vancouver

Kokhanovskiy A, Shevelev A, Serebrennikov K, Kuprikov E, Turitsyn S. A Deep Reinforcement Learning Algorithm for Smart Control of Hysteresis Phenomena in a Mode-Locked Fiber Laser. Photonics. 2022 Dec 1;9(12):921. doi: 10.3390/photonics9120921

Author

Kokhanovskiy, Alexey ; Shevelev, Alexey ; Serebrennikov, Kirill et al. / A Deep Reinforcement Learning Algorithm for Smart Control of Hysteresis Phenomena in a Mode-Locked Fiber Laser. In: Photonics. 2022 ; Vol. 9, No. 12.

BibTeX

@article{957b23d28d4b4dbab51e9fbc1d13ed1c,
title = "A Deep Reinforcement Learning Algorithm for Smart Control of Hysteresis Phenomena in a Mode-Locked Fiber Laser",
abstract = "We experimentally demonstrate the application of a double deep Q-learning network algorithm (DDQN) for design of a self-starting fiber mode-locked laser. In contrast to the static optimization of a system design, the DDQN reinforcement algorithm is capable of learning the strategy of dynamic adjustment of the cavity parameters. Here, we apply the DDQN algorithm for stable soliton generation in a fiber laser cavity exploiting a nonlinear polarization evolution mechanism. The algorithm learns the hysteresis phenomena that manifest themselves as different pumping-power thresholds for mode-locked regimes for diverse trajectories of adjusting optical pumping.",
keywords = "fiber mode-locked lasers, hysteresis phenomena, reinforcement learning",
author = "Alexey Kokhanovskiy and Alexey Shevelev and Kirill Serebrennikov and Evgeny Kuprikov and Sergey Turitsyn",
note = "Funding: This work was supported by the Russian Science Foundation (Grant No. 17-72-30006-P).",
year = "2022",
month = dec,
day = "1",
doi = "10.3390/photonics9120921",
language = "English",
volume = "9",
journal = "Photonics",
issn = "2304-6732",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "12",

}

RIS

TY - JOUR

T1 - A Deep Reinforcement Learning Algorithm for Smart Control of Hysteresis Phenomena in a Mode-Locked Fiber Laser

AU - Kokhanovskiy, Alexey

AU - Shevelev, Alexey

AU - Serebrennikov, Kirill

AU - Kuprikov, Evgeny

AU - Turitsyn, Sergey

N1 - Funding: This work was supported by the Russian Science Foundation (Grant No. 17-72-30006-P).

PY - 2022/12/1

Y1 - 2022/12/1

N2 - We experimentally demonstrate the application of a double deep Q-learning network algorithm (DDQN) for design of a self-starting fiber mode-locked laser. In contrast to the static optimization of a system design, the DDQN reinforcement algorithm is capable of learning the strategy of dynamic adjustment of the cavity parameters. Here, we apply the DDQN algorithm for stable soliton generation in a fiber laser cavity exploiting a nonlinear polarization evolution mechanism. The algorithm learns the hysteresis phenomena that manifest themselves as different pumping-power thresholds for mode-locked regimes for diverse trajectories of adjusting optical pumping.

AB - We experimentally demonstrate the application of a double deep Q-learning network algorithm (DDQN) for design of a self-starting fiber mode-locked laser. In contrast to the static optimization of a system design, the DDQN reinforcement algorithm is capable of learning the strategy of dynamic adjustment of the cavity parameters. Here, we apply the DDQN algorithm for stable soliton generation in a fiber laser cavity exploiting a nonlinear polarization evolution mechanism. The algorithm learns the hysteresis phenomena that manifest themselves as different pumping-power thresholds for mode-locked regimes for diverse trajectories of adjusting optical pumping.

KW - fiber mode-locked lasers

KW - hysteresis phenomena

KW - reinforcement learning

UR - https://www.scopus.com/inward/record.url?eid=2-s2.0-85144675885&partnerID=40&md5=6c1645228290de7a7368a37e6ccc55af

UR - https://www.mendeley.com/catalogue/34dc78fb-7254-3560-a419-e88a3fb583dc/

U2 - 10.3390/photonics9120921

DO - 10.3390/photonics9120921

M3 - Article

VL - 9

JO - Photonics

JF - Photonics

SN - 2304-6732

IS - 12

M1 - 921

ER -

ID: 44675204