Using a Reinforcement Q-Learning-Based Deep Neural Network for Playing Video Games

Using a Reinforcement Q-Learning-Based Deep Neural Network for Playing Video Games

This study proposed a reinforcement Q-learning-based deep neural network (RQDNN) that combined a deep principal component analysis network (DPCANet) and Q-learning to determine a playing strategy for video games. Video game images were used as the inputs. The proposed DPCANet was used to initialize...

Full description

Bibliographic Details
Main Authors: Cheng-Jian Lin, Jyun-Yu Jhang, Hsueh-Yi Lin, Chin-Ling Lee, Kuu-Young Young
Format: Article
Language:English
Published: MDPI AG 2019-10-01
Series:Electronics
Subjects:
convolution neural network
deep principal component analysis network
image sensor
reinforcement learning
q-learning
video game
Online Access:https://www.mdpi.com/2079-9292/8/10/1128

Internet

https://www.mdpi.com/2079-9292/8/10/1128

Similar Items