QQ客服 官方微博 反馈留言

	Autonomous discovery and creation of options in hierarchical reinforcement learning
	Meng Jiang-hua ; Zhu Ji-hong ; Sun Zeng-qi
	2010-05-06 ; 2010-05-06
关键词	Theoretical or Mathematical/ learning (artificial intelligence)/ autonomous option discovery option creation hierarchical reinforcement learning exploration density inspection/ C1230L Learning in AI
中文摘要	Autonomous discovery and creation of options is one of the open and difficult problems in research of hierachical reinforcement learning (RL).The new method presented in this article is named "exploration density (ED) inspection", which discovers and creates useful options through inspecting ED in state space. The method has many advantages such as task-independence, no need of prior knowledge. ED method works well in unknown surroundings and the options it created can transfer among tasks directly.
语种	中文 ; 中文
出版者	Publishing House of the Journal of Computer Engineering and Applications ; China
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/9819]
专题	清华大学
推荐引用方式 GB/T 7714	Meng Jiang-hua,Zhu Ji-hong,Sun Zeng-qi. Autonomous discovery and creation of options in hierarchical reinforcement learning[J],2010, 2010.
APA	Meng Jiang-hua,Zhu Ji-hong,&Sun Zeng-qi.(2010).Autonomous discovery and creation of options in hierarchical reinforcement learning..
MLA	Meng Jiang-hua,et al."Autonomous discovery and creation of options in hierarchical reinforcement learning".(2010).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

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。