An overview on algorithms and applications of deep reinforcement learning

Deep reinforcement learning (DRL) is mainly applied to solve the perception-decision problem, and has become an important research branch in the field of artificial intelligence.Two kinds of DRL algorithms based on value function and policy gradient were summarized, including deep Q network, policy...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaoyang LIU, Chaoxu MU, Changyin SUN
Format: Article
Language:zho
Published: POSTS&TELECOM PRESS Co., LTD 2020-12-01
Series:智能科学与技术学报
Subjects:
Online Access:http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202034
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846171127031791616
author Zhaoyang LIU
Chaoxu MU
Changyin SUN
author_facet Zhaoyang LIU
Chaoxu MU
Changyin SUN
author_sort Zhaoyang LIU
collection DOAJ
description Deep reinforcement learning (DRL) is mainly applied to solve the perception-decision problem, and has become an important research branch in the field of artificial intelligence.Two kinds of DRL algorithms based on value function and policy gradient were summarized, including deep Q network, policy gradient as well as related developed algorithms.In addition, the applications of DRL in video games, navigation, multi-agent cooperation and recommendation field were intensively reviewed.Finally, a prospect for the future research of DRL was made, and some research suggestions were given.
format Article
id doaj-art-86d54b026a904c00b82eb57191c12874
institution Kabale University
issn 2096-6652
language zho
publishDate 2020-12-01
publisher POSTS&TELECOM PRESS Co., LTD
record_format Article
series 智能科学与技术学报
spelling doaj-art-86d54b026a904c00b82eb57191c128742024-11-11T06:52:10ZzhoPOSTS&TELECOM PRESS Co., LTD智能科学与技术学报2096-66522020-12-01231432659638255An overview on algorithms and applications of deep reinforcement learningZhaoyang LIUChaoxu MUChangyin SUNDeep reinforcement learning (DRL) is mainly applied to solve the perception-decision problem, and has become an important research branch in the field of artificial intelligence.Two kinds of DRL algorithms based on value function and policy gradient were summarized, including deep Q network, policy gradient as well as related developed algorithms.In addition, the applications of DRL in video games, navigation, multi-agent cooperation and recommendation field were intensively reviewed.Finally, a prospect for the future research of DRL was made, and some research suggestions were given.http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202034artificial intelligence;deep reinforcement learning;value function;policy gradient;navigation;cooperation;complex environment;generalization;robustness
spellingShingle Zhaoyang LIU
Chaoxu MU
Changyin SUN
An overview on algorithms and applications of deep reinforcement learning
智能科学与技术学报
artificial intelligence;deep reinforcement learning;value function;policy gradient;navigation;cooperation;complex environment;generalization;robustness
title An overview on algorithms and applications of deep reinforcement learning
title_full An overview on algorithms and applications of deep reinforcement learning
title_fullStr An overview on algorithms and applications of deep reinforcement learning
title_full_unstemmed An overview on algorithms and applications of deep reinforcement learning
title_short An overview on algorithms and applications of deep reinforcement learning
title_sort overview on algorithms and applications of deep reinforcement learning
topic artificial intelligence;deep reinforcement learning;value function;policy gradient;navigation;cooperation;complex environment;generalization;robustness
url http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202034
work_keys_str_mv AT zhaoyangliu anoverviewonalgorithmsandapplicationsofdeepreinforcementlearning
AT chaoxumu anoverviewonalgorithmsandapplicationsofdeepreinforcementlearning
AT changyinsun anoverviewonalgorithmsandapplicationsofdeepreinforcementlearning
AT zhaoyangliu overviewonalgorithmsandapplicationsofdeepreinforcementlearning
AT chaoxumu overviewonalgorithmsandapplicationsofdeepreinforcementlearning
AT changyinsun overviewonalgorithmsandapplicationsofdeepreinforcementlearning