Please use this identifier to cite or link to this item: https://ah.nccu.edu.tw/handle/140.119/139080


Title: The Matter of Deep Reinforcement Learning Towards Practical AI Applications
Authors: 陳聖智
Chen, Sheng-Chih
Thaipisutikul, Tipajin
Chen, Yi-Cheng
Hui, Lin
Mongkolwat, Pattanasak
Shih, Timothy K.
Contributors: 傳播學院
Keywords: 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
Date: 2019-08
Issue Date: 2022-02-11 15:22:33 (UTC+8)
Abstract: 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.
Relation: The 12th International Conference on Ubi-Media Computing.(Ubi-Media 2019), University of Indonesia, Indonesia
Data Type: conference
DOI 連結: https://doi.org/10.1109/Ubi-Media.2019.00014
Appears in Collections:[傳播學院] 會議論文

Files in This Item:

File Description SizeFormat
339.pdf573KbAdobe PDF39View/Open


All items in 學術集成 are protected by copyright, with all rights reserved.


社群 sharing