An Improved DQN Algorithm for Identifying Complex Reward Functions Using Multi-stage Neural Network

碩士 === 國立成功大學 === 工程科學系 === 106

Bibliographic Details
Main Authors: YUN-KAIWANG, 王雲楷
Other Authors: Ting-Wei Hou
Format: Others
Language:en_US
Published: 2018
Online Access:http://ndltd.ncl.edu.tw/handle/t993k4
id ndltd-TW-106NCKU5028042
record_format oai_dc
spelling ndltd-TW-106NCKU50280422019-10-31T05:22:18Z http://ndltd.ncl.edu.tw/handle/t993k4 An Improved DQN Algorithm for Identifying Complex Reward Functions Using Multi-stage Neural Network 適用於辨識複雜獎勵函數之改良DQN演算法-使用多階層類神經網絡 YUN-KAIWANG 王雲楷 碩士 國立成功大學 工程科學系 106 Ting-Wei Hou 侯廷偉 2018 學位論文 ; thesis 64 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立成功大學 === 工程科學系 === 106
author2 Ting-Wei Hou
author_facet Ting-Wei Hou
YUN-KAIWANG
王雲楷
author YUN-KAIWANG
王雲楷
spellingShingle YUN-KAIWANG
王雲楷
An Improved DQN Algorithm for Identifying Complex Reward Functions Using Multi-stage Neural Network
author_sort YUN-KAIWANG
title An Improved DQN Algorithm for Identifying Complex Reward Functions Using Multi-stage Neural Network
title_short An Improved DQN Algorithm for Identifying Complex Reward Functions Using Multi-stage Neural Network
title_full An Improved DQN Algorithm for Identifying Complex Reward Functions Using Multi-stage Neural Network
title_fullStr An Improved DQN Algorithm for Identifying Complex Reward Functions Using Multi-stage Neural Network
title_full_unstemmed An Improved DQN Algorithm for Identifying Complex Reward Functions Using Multi-stage Neural Network
title_sort improved dqn algorithm for identifying complex reward functions using multi-stage neural network
publishDate 2018
url http://ndltd.ncl.edu.tw/handle/t993k4
work_keys_str_mv AT yunkaiwang animproveddqnalgorithmforidentifyingcomplexrewardfunctionsusingmultistageneuralnetwork
AT wángyúnkǎi animproveddqnalgorithmforidentifyingcomplexrewardfunctionsusingmultistageneuralnetwork
AT yunkaiwang shìyòngyúbiànshífùzájiǎnglìhánshùzhīgǎiliángdqnyǎnsuànfǎshǐyòngduōjiēcénglèishénjīngwǎngluò
AT wángyúnkǎi shìyòngyúbiànshífùzájiǎnglìhánshùzhīgǎiliángdqnyǎnsuànfǎshǐyòngduōjiēcénglèishénjīngwǎngluò
AT yunkaiwang improveddqnalgorithmforidentifyingcomplexrewardfunctionsusingmultistageneuralnetwork
AT wángyúnkǎi improveddqnalgorithmforidentifyingcomplexrewardfunctionsusingmultistageneuralnetwork
_version_ 1719284060828729344