Using Deep Neural Network Based on Reinforcement Learning for Video Game Control Strategy
碩士 === 國立勤益科技大學 === 資訊工程系 === 106 === This paper proposes a game control method that uses game screens as input, improves the architecture of the roll machine neural network, initializes the parameters of the convolution kernel using principal component analysis, and stack these convolution kernels...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/kn92fw |
id |
ndltd-TW-106NCIT5392029 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-106NCIT53920292019-07-04T05:59:50Z http://ndltd.ncl.edu.tw/handle/kn92fw Using Deep Neural Network Based on Reinforcement Learning for Video Game Control Strategy 增強式學習於深度神經網路之仿人類遊戲控制策略應用 Lu-Xun Huang 黃祿勳 碩士 國立勤益科技大學 資訊工程系 106 This paper proposes a game control method that uses game screens as input, improves the architecture of the roll machine neural network, initializes the parameters of the convolution kernel using principal component analysis, and stack these convolution kernels through multiple layers. Learning how to extract feature from input image and base on these feature to make control strategy by reinforcement learning method, effectively realize the game control method that imitates humans using vision as input. This architecture is named Reinforcement Q-Learning on Deep Neural Network (RQDNN). In the experiments of this paper, RQDNN is better than human players and other deep reinforcement learning algorithms. In addition, the RQDNN is much less than the other deep reinforcement learning algorithms using convolutional neural networks for the computational resources required for training. Cheng-Yi Yu Cheng-Jian Lin 游正義 林正堅 2018 學位論文 ; thesis 38 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立勤益科技大學 === 資訊工程系 === 106 === This paper proposes a game control method that uses game screens as input, improves the architecture of the roll machine neural network, initializes the parameters of the convolution kernel using principal component analysis, and stack these convolution kernels through multiple layers. Learning how to extract feature from input image and base on these feature to make control strategy by reinforcement learning method, effectively realize the game control method that imitates humans using vision as input. This architecture is named Reinforcement Q-Learning on Deep Neural Network (RQDNN). In the experiments of this paper, RQDNN is better than human players and other deep reinforcement learning algorithms. In addition, the RQDNN is much less than the other deep reinforcement learning algorithms using convolutional neural networks for the computational resources required for training.
|
author2 |
Cheng-Yi Yu |
author_facet |
Cheng-Yi Yu Lu-Xun Huang 黃祿勳 |
author |
Lu-Xun Huang 黃祿勳 |
spellingShingle |
Lu-Xun Huang 黃祿勳 Using Deep Neural Network Based on Reinforcement Learning for Video Game Control Strategy |
author_sort |
Lu-Xun Huang |
title |
Using Deep Neural Network Based on Reinforcement Learning for Video Game Control Strategy |
title_short |
Using Deep Neural Network Based on Reinforcement Learning for Video Game Control Strategy |
title_full |
Using Deep Neural Network Based on Reinforcement Learning for Video Game Control Strategy |
title_fullStr |
Using Deep Neural Network Based on Reinforcement Learning for Video Game Control Strategy |
title_full_unstemmed |
Using Deep Neural Network Based on Reinforcement Learning for Video Game Control Strategy |
title_sort |
using deep neural network based on reinforcement learning for video game control strategy |
publishDate |
2018 |
url |
http://ndltd.ncl.edu.tw/handle/kn92fw |
work_keys_str_mv |
AT luxunhuang usingdeepneuralnetworkbasedonreinforcementlearningforvideogamecontrolstrategy AT huánglùxūn usingdeepneuralnetworkbasedonreinforcementlearningforvideogamecontrolstrategy AT luxunhuang zēngqiángshìxuéxíyúshēndùshénjīngwǎnglùzhīfǎngrénlèiyóuxìkòngzhìcèlüèyīngyòng AT huánglùxūn zēngqiángshìxuéxíyúshēndùshénjīngwǎnglùzhīfǎngrénlèiyóuxìkòngzhìcèlüèyīngyòng |
_version_ |
1719219978515775488 |