Výsledky vyhledávání

Reinforcement Learning Guided by Double Replay Memory

Autor: Yong-Hak Lee, JiSeong Han, Kichun Jo, JunSang Cho, Eunseon Sim, Wontaek Lim, Kyoungmin Ko, SungHwan Kim

Publikováno v: Journal of Sensors, Vol 2021 (2021)

Experience replay memory in reinforcement learning enables agents to remember and reuse past experiences. Most of the reinforcement models are subject to single experience replay memory to operate agents. In this article, we propose a framework that

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c666b0c82e5a824dc805a2160c096642
https://doaj.org/article/0fb34c9469624956bbdc9d7e800b976e

Zobrazit plný text záznamu

Predictive Models of Fire via Deep learning Exploiting Colorific Variation

Autor: JiSeong Han, Ung Hwang, ChanSeo Lee, Gwangsu Kim, SungHwan Kim, YeongKwang Han

Publikováno v: ICAIIC

Predictive models on fire have been increasingly popular in computer image analysis. Due to late strides of deep learning techniques, we are now unprecedently benefited from its flexible applicability. In most cases, however, the conventional algorit

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fd6224e03d1ebebda7aa05029ef906ac
https://doi.org/10.1109/icaiic.2019.8669042

Zobrazit plný text záznamu

Vision-Based Deep Q-Learning Network Models to Predict Particulate Matter Concentration Levels Using Temporal Digital Image Data

Autor: ByungYong Lee, SeongMin Yang, SeHee Jung, Sung Won Han, SungHwan Kim, Jaehwa Lee, JiSeong Han

Publikováno v: Journal of Sensors, Vol 2019 (2019)

Particulate matter (PM) has been revealed to have detrimental effects on public health, social economy, agriculture, and so forth. Thus, it became one of the major concerns in terms of a factor that can reduce “quality of life” over East Asia, wh

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9b1048fc556752df3d3951634d0ef2e3
https://doaj.org/article/4f20258ee8a9401eb704ba38c1684b0d

Zobrazit plný text záznamu