Research output: Contribution to journal › Article › peer-review
Multistability manipulation by reinforcement learning algorithm inside mode-locked fiber laser. / Kokhanovskiy, Alexey; Kuprikov, Evgeny; Serebrennikov, Kirill et al.
In: Nanophotonics, Vol. 13, No. 16, 01.07.2024, p. 2891-2901.Research output: Contribution to journal › Article › peer-review
}
TY - JOUR
T1 - Multistability manipulation by reinforcement learning algorithm inside mode-locked fiber laser
AU - Kokhanovskiy, Alexey
AU - Kuprikov, Evgeny
AU - Serebrennikov, Kirill
AU - Mkrtchyan, Aram
AU - Davletkhanov, Ayvaz
AU - Bunkov, Alexey
AU - Krasnikov, Dmitry
AU - Shashkov, Mikhail
AU - Nasibulin, Albert
AU - Gladush, Yuriy
N1 - Research funding: The work of A.K. and Y.G. (initiation of the study, conceptualization, development of the algorithms, writing the article) was financially supported by ITMO-MIPT-Skoltech Clover Program. D.K. and A.B. thank RSF grant 20-73-10256 (synthesis of carbon nanotubes with tailored optical spectrum). The work of K.S. (arrangement and automatization of the experimental setup) was supported by the state budget of IAE SB RAS (project No. FWNG-2024-0015).
PY - 2024/7/1
Y1 - 2024/7/1
N2 - Fiber mode-locked lasers are nonlinear optical systems that provide ultrashort pulses at high repetition rates. However, adjusting the cavity parameters is often a challenging task due to the intrinsic multistability of a laser system. Depending on the adjustment of the cavity parameters, the optical output may vary significantly, including Q-switching, single and multipulse, and harmonic mode-locked regimes. In this study, we demonstrate an experimental implementation of the Soft Actor-Critic algorithm for generating a harmonic mode-locked regime inside a state-of-the-art fiber laser with an ion-gated nanotube saturable absorber. The algorithm employs nontrivial strategies to achieve a guaranteed harmonic mode-locked regime with the highest order by effectively managing the pumping power of a laser system and the nonlinear transmission of a nanotube absorber. Our results demonstrate a robust and feasible machine-learning-based approach toward an automatic system for adjusting nonlinear optical systems with the presence of multistability phenomena.
AB - Fiber mode-locked lasers are nonlinear optical systems that provide ultrashort pulses at high repetition rates. However, adjusting the cavity parameters is often a challenging task due to the intrinsic multistability of a laser system. Depending on the adjustment of the cavity parameters, the optical output may vary significantly, including Q-switching, single and multipulse, and harmonic mode-locked regimes. In this study, we demonstrate an experimental implementation of the Soft Actor-Critic algorithm for generating a harmonic mode-locked regime inside a state-of-the-art fiber laser with an ion-gated nanotube saturable absorber. The algorithm employs nontrivial strategies to achieve a guaranteed harmonic mode-locked regime with the highest order by effectively managing the pumping power of a laser system and the nonlinear transmission of a nanotube absorber. Our results demonstrate a robust and feasible machine-learning-based approach toward an automatic system for adjusting nonlinear optical systems with the presence of multistability phenomena.
KW - harmonic mode-locked lasers
KW - multistability
KW - reinforcement learning
KW - saturable absorber
KW - single wall carbon nanotubes
UR - https://www.mendeley.com/catalogue/1c207148-8cb8-3655-8588-56e702479d17/
UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85190723390&origin=inward&txGid=0997058bfa8c61888c07acb9ef3e77c6
U2 - 10.1515/nanoph-2023-0792
DO - 10.1515/nanoph-2023-0792
M3 - Article
VL - 13
SP - 2891
EP - 2901
JO - Nanophotonics
JF - Nanophotonics
SN - 2192-8606
IS - 16
ER -
ID: 60861604