【摘 要】
：
The slow convergence rate of reinforcement learning algorithms limits their wider application. In engineering domains, hierarchical reinforcement learning is de
【出 处】
：
Journal of Systems Science and Systems Engineering
论文部分内容阅读
The slow convergence rate of reinforcement learning algorithms limits their wider application. In engineering domains, hierarchical reinforcement learning is developed to perform actions temporally according to prior knowledge. This system can converge fast due to reduced state space. There is a test of elevator group control to show the power of the new system. Two conventional group control algorithms are adopted as prior knowledge. Performance indicates that hierarchical reinforcement learning can reduce the learning time dramatically.
The engineering of the learning process limits their wider application. There is a test of elevator group control to show the power of the new system. Two conventional group control algorithms are adopted as prior knowledge. Performance suggests that hierarchical reinforcement reinforcement learning can reduce the learning time dramatically.
其他文献
梨铁象是我国南方梨树的一种毁灭性害虫。此虫完成一代历时达16—24个月,以成虫在梨树小枝上和以幼虫在梨树干和主枝的韧皮部越冬。成虫寿命长达14个月(446天)。当交配产卵季
水果的现场检疫工作,是检疫把关的重要环节,随着对外开放,贸易往来的日益增多,对进口水果现场检疫快速、准确性的要求越来越高,如何提高水果的现场检疫技术,显然是每个检疫
泡桐是我国著名的速生丰产树种之一,世是河南的优良乡土树种。随着泡桐的大量栽培,害虫也逐渐发展起来,娇驼跷蝽就是其中之一。过去群众对此虫的发生、危害认识不足,以致严
本文介绍了第十一届国际植物保护会议(马尼拉召开)情况,内容涉及会议概况、综合农业系统、日本有害生物综合治理情况、褐飞虱抗性描述方法——蜜露钟、褐飞虱天敌——水黾蝽
请下载后查看，本文暂不支持在线获取查看简介。
Please download to view, this article does not support online access to view profile.
一、澳大利亚的新法律1.1983年9月《检疫公告》第94P 号。除经批准外,禁止蓖麻 Ricinus commun-is(Costor)的种子和植株入境。在澳大利亚有发展蓖麻的潜力,控制其进口是为了
音乐欣赏是音乐教育的重要组成部分,是理解音乐和学好音乐的前提,并且在提高学生审美能力,陶冶学生情操,促进学生综合素质发展等方面发挥着重要的作用。因此,上好音乐欣赏课
经过长期的艰苦训练,即将参加声乐高考的学生大都建立了一定程度的歌唱状态,形成了正确的歌唱姿势、深的呼吸、良好的咽喉状态与共鸣,同时也具备了一定的歌唱表达能力,在歌曲
近几年来,各地发展了不少板栗。但据调查,成活率较低。我县一些山区新栽板栗成活率仅50—60％,最低的只有10％左右。究其原因,除栽培方法不当外,病虫害
In recent years, many
彭阳县属黄土高原丘陵区,地形复杂,气侯变化大,灾害频繁,粮食以冬小麦及杂粮为主,其中莜麦播种面积9万余亩,占粮食播种面积的9.4～11.5%,北部王洼等乡尤为集中,莜麦占粮食作物