Learning to Play Hard Exploration Games Using Graph-guided Self-navigation
文献类型：会议论文
| 作者 | Zhao EM(赵恩民)1,2 ; Yan RY(闫仁业)1,2; Li K(李凯)1; Li LJ(李丽娟)1; Xing JL(兴军亮)1,2
|
| 出版日期 | 2021-02 |
| 会议日期 | 2021-02 |
| 会议地点 | 线上 |
| DOI | 无 |
| 英文摘要 | Thisworkconsiderstheproblemofdeeprein-
forcementlearning(RL)withlongtimedependenciesands-
parserewards,asarefoundinmanyhardexplorationgames.
Agraph-basedrepresentationisproposedtoallowanagent
toperformself-navigationforenvironmentalexploration.The
graphrepresentationnotonlyeffectivelymodelstheenvironment
structure,butalsoefficientlytracestheagentstatechangesand
thecorrespondingactions.Byencouragingtheagenttoearna
newinfluence-basedcuriosityrewardfornewgameobservations,
thewholeexplorationtaskisdividedintosub-tasks,whichare
effectivelysolvedusingaunifieddeepRLmodel.Experimental
evaluationsonhardexplorationAtariGamesdemonstratethe
effectivenessoftheproposedmethod.Thesourcecodeand
learnedmodelswillbereleasedtofacilitatefurtherstudieson
thisproblem. |
| 学科主题 | 信息科学与系统科学 |
| 语种 | 英语 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/52241]  |
| 专题 | 融合创新中心_决策指挥与体系智能 |
| 通讯作者 | Xing JL(兴军亮) |
| 作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.SchoolofArtificialIntelligence,UniversityofChineseAcademyofSciences |
| 推荐引用方式 GB/T 7714 | Zhao EM,Yan RY,Li K,et al. Learning to Play Hard Exploration Games Using Graph-guided Self-navigation[C]. 见:. 线上. 2021-02. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。