Developing Generative Adversarial Nets to Extend Training Sets and Optimize Discrete Actions

This study proposes the use of generative adversarial networks (GANs) to solve two crucial problems in the unmanned ship navigation: insufficient training data for neural networks and convergence of optimal actions under discrete conditions. To achieve smart collision avoidance of unmanned ships in...

Ful tanımlama

Kaydedildi:

Detaylı Bibliyografya
Asıl Yazarlar:	Ruolan Zhang, Masao Furusho
Materyal Türü:	Artigo
Dil:	Inglês
Baskı/Yayın Bilgisi:	Gdynia Maritime University 2019-12-01
Seri Bilgileri:	TransNav
Konular:	maritime education and training (met) met system in japan unmanned ship navigation generative adversarial network (gan) discrete actions lifeboat monte carlo tree search (mcts) learning methods
Online Erişim:	https://www.transnav.eu/files/Developing_Generative_Adversarial_Nets_to_Extend_Training_Sets_and_Optimize_Discrete_Actions,967.pdf
Etiketler:	Etiketle Etiket eklenmemiş, İlk siz ekleyin!

Developing Generative Adversarial Nets to Extend Training Sets and Optimize Discrete Actions

Benzer Materyaller