1. NCCU Academic Hub
  2. Publications
  3. Item

Publications-Proceedings

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 The Matter of Deep Reinforcement Learning Towards Practical AI Applications
作者 陳聖智
Chen, Sheng-Chih
Thaipisutikul, Tipajin
Chen, Yi-Cheng
Hui, Lin
Mongkolwat, Pattanasak
Shih, Timothy K.
貢獻者 傳播學院
關鍵詞 learning (artificial intelligence) ; multi-agent systems ; neural nets; complex problem ; temporal-difference learning ; Deep Q-Learning agent ; self-driving car application ; RNN A3C agents ; Breakout AI game application ; deep reinforcement learning ; eligibility trace ; experience replay; Deep Reinforcement Learning; A3C; Q-Learning; Deep Q-Learning
日期 2019-08
上傳時間 11-Feb-2022 15:22:33 (UTC+8)
摘要 Reinforcement Learning (RL) is an extraordinarily paradigm that aims to solve a complex problem. This technique leverages the traditional feedforward networks with temporal-difference learning to overcome supervised and unsupervised real-world problems. However, RL is one of state-of-the-art topic due to the opaque aspects in design and implementation. Also, in which situation we will get performance gain from RL is still unclear. Therefore, This study firstly examines the impact of Experience Replay in Deep Q-Learning agent with Self-Driving Car application. Secondly, The impact of Eligibility Trace in RNN A3C agents with Breakout AI game application is studied. Our results indicated that these two techniques enhance RL performance by more than 20 percent as compared with traditional RL methods.
關聯 The 12th International Conference on Ubi-Media Computing.(Ubi-Media 2019), University of Indonesia, Indonesia
資料類型 conference
DOI https://doi.org/10.1109/Ubi-Media.2019.00014
dc.contributor 傳播學院
dc.creator (作者) 陳聖智
dc.creator (作者) Chen, Sheng-Chih
dc.creator (作者) Thaipisutikul, Tipajin
dc.creator (作者) Chen, Yi-Cheng
dc.creator (作者) Hui, Lin
dc.creator (作者) Mongkolwat, Pattanasak
dc.creator (作者) Shih, Timothy K.
dc.date (日期) 2019-08
dc.date.accessioned 11-Feb-2022 15:22:33 (UTC+8)-
dc.date.available 11-Feb-2022 15:22:33 (UTC+8)-
dc.date.issued (上傳時間) 11-Feb-2022 15:22:33 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/139080-
dc.description.abstract (摘要) Reinforcement Learning (RL) is an extraordinarily paradigm that aims to solve a complex problem. This technique leverages the traditional feedforward networks with temporal-difference learning to overcome supervised and unsupervised real-world problems. However, RL is one of state-of-the-art topic due to the opaque aspects in design and implementation. Also, in which situation we will get performance gain from RL is still unclear. Therefore, This study firstly examines the impact of Experience Replay in Deep Q-Learning agent with Self-Driving Car application. Secondly, The impact of Eligibility Trace in RNN A3C agents with Breakout AI game application is studied. Our results indicated that these two techniques enhance RL performance by more than 20 percent as compared with traditional RL methods.
dc.format.extent 587711 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) The 12th International Conference on Ubi-Media Computing.(Ubi-Media 2019), University of Indonesia, Indonesia
dc.subject (關鍵詞) learning (artificial intelligence) ; multi-agent systems ; neural nets; complex problem ; temporal-difference learning ; Deep Q-Learning agent ; self-driving car application ; RNN A3C agents ; Breakout AI game application ; deep reinforcement learning ; eligibility trace ; experience replay; Deep Reinforcement Learning; A3C; Q-Learning; Deep Q-Learning
dc.title (題名) The Matter of Deep Reinforcement Learning Towards Practical AI Applications
dc.type (資料類型) conference
dc.identifier.doi (DOI) 10.1109/Ubi-Media.2019.00014
dc.doi.uri (DOI) https://doi.org/10.1109/Ubi-Media.2019.00014