TY - CHAP

T1 - Implementation of reinforcement learning algorithms for fiber mode-locked lasers

AU - Kokhanovskiy, A.

AU - Serebrennikov, K.

AU - Kuprikov, E.

N1 - This work was supported by the state budget of IAE SB RAS (project No FWNG-2024-0015).

PY - 2024

Y1 - 2024

N2 - We demonstrate the use of various types of reinforcement learning algorithms for the following tasks: self-starting, stability under temperature fluctuations, and optimization of the pulsed regimes of fiber mode-locked lasers. The feasibility of implementing reinforcement algorithms in a multi-stable system such as fiber-locked lasers is demonstrated. The main problems with reinforcement learning algorithms are discussed.

AB - We demonstrate the use of various types of reinforcement learning algorithms for the following tasks: self-starting, stability under temperature fluctuations, and optimization of the pulsed regimes of fiber mode-locked lasers. The feasibility of implementing reinforcement algorithms in a multi-stable system such as fiber-locked lasers is demonstrated. The main problems with reinforcement learning algorithms are discussed.

KW - fiber mode-locked lasers

KW - machine learning algorithms

KW - ultrafast phenomena

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85203123672&origin=inward&txGid=39c5bd1a8847411e6bf35393395c52c1

UR - https://www.mendeley.com/catalogue/62826d59-a3b0-395a-bdff-5a89c92bcbd6/

U2 - 10.1109/ICLO59702.2024.10624542

DO - 10.1109/ICLO59702.2024.10624542

M3 - Chapter

SN - 9798350390674

T3 - 2024 International Conference Laser Optics, ICLO 2024 - Proceedings

SP - 442

BT - 2024 International Conference Laser Optics, ICLO 2024 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2024 International Conference Laser Optics

Y2 - 1 July 2024 through 5 July 2024

ER -