Zobrazeno 1 - 10
of 32
pro vyhledávání: '"穆朝絮"'
Publikováno v:
智能科学与技术学报, Vol 2, Iss 4, Pp 314-326 (2020)
深度强化学习主要被用来处理感知-决策问题，已经成为人工智能领域重要的研究分支。概述了基于值函数和策略梯度的两类深度强化学习算法，详细阐述了深度Q网络、深度策略梯度及相关
Externí odkaz:
https://doaj.org/article/b1e27ad3ac674c4fb3fa276c913ba61b
Publikováno v:
Infrared and Laser Engineering. 51:20220194
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f73e3a3fa60304ecf7f8dba31cf7bffb
https://doi.org/10.3788/irla20220194
https://doi.org/10.3788/irla20220194
Publikováno v:
Acta Automatica Sinica; Mar2017, Vol. 43 Issue 3, p366-375, 10p
Publikováno v:
Integrated Intelligent Energy; Sep2024, Vol. 46 Issue 9, p28-36, 9p
Publikováno v:
China Sciencepaper; Jul2024, Vol. 19 Issue 7, p821-830, 11p
Publikováno v:
Application Research of Computers / Jisuanji Yingyong Yanjiu. Nov2022, Vol. 39 Issue 11, p3358-3364. 7p.
Publikováno v:
Application Research of Computers / Jisuanji Yingyong Yanjiu. Nov2022, Vol. 39 Issue 11, p3327-3364. 7p.
Publikováno v:
Systems Engineering & Electronics; May2024, Vol. 46 Issue 5, p1628-1655, 28p
Publikováno v:
Journal of Nanjing University of Aeronautics & Astronautics / Nanjing Hangkong Hangtian Daxue Xuebao; Apr2024, Vol. 56 Issue 2, p364-374, 11p
Publikováno v:
Control Theory & Applications / Kongzhi Lilun Yu Yinyong; Nov2023, Vol. 40 Issue 11, p2049-2058, 10p