DINAMIK OB’EKTLARNI OPTIMAL BOSHQARISH ALGORITMINI BELLMAN USULI YORDAMIDA TADQIQ ETISH
Kalit so‘zlar:
optimal boshqaruv; Bellman tenglamasi; dinamik tizimlar; Deep Q-learning; stoxastik tizimlarAbstrak
Dinamik tizimlarni optimal boshqarish masalalari zamonaviy boshqaruv nazariyasining muhim yo‘nalishlaridan biridir. Ushbu maqolada Bellman dinamik dasturlash usuli yordamida dinamik ob’ektlarni optimal boshqarish algoritmlari tadqiq etiladi. Yangi algoritmik yondashuvlar, ularning zamonaviy qo‘llanmalardagi ahamiyati va boshqa yondashuvlar bilan taqqoslanishi bayon etiladi.
References
R. Bellman, Dynamic Programming, Princeton University Press, 1957.
R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, MIT Press, 2018.
Q. Ma and J. Stachurski, “Dynamic Programming Deconstructed,” arXiv preprint, 2018.
M. I. Gomoyunov, “Dynamic Programming for Fractional-Order Systems,” arXiv preprint, 2019.
G. Barles, A. Briani, and E. Chasseigne, “A Bellman Approach for Two-Domains Optimal Control Problems,” arXiv preprint, 2011.
O. Zaripov and S. Zaripova, “Dinamik boshqarish obyektlar holatini baholash masalalari,” QMII Journal, 2023.
Downloads
Nashr qilingan
License
Copyright (c) 2025 Akromxo‘jayev Y , Abdusalomov A. J.
This work is licensed under a Creative Commons Attribution 4.0 International License.
(+998)90 142-39-38
Andijon viloyati, Marhamat tumani, Qashqar ko’chasi 189-uy