A multiagent reinforcement learning approach based on different states

来源 :Journal of Harbin Institute of Technology | 被引量 : 0次 | 上传用户:JasonCrazy
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
In this paper we describe a new reinforcement learning approach based on different states. When the multiagent is in coordination state,we take all coordinative agents as players and choose the learning approach based on game theory. When the multiagent i
其他文献
In this paper the alkali-activated slag cementitious materials(AASCM)which strength at 600 ℃ is larger than that of AASCM at room temperature,were prepared to
期刊
This paper presents an algorithm that combines the chaos optimization algorithm with the maximum entropy ( COA-ME) by using entropy model based on chaos algorit
The numerical simulation on drawing process of automotive B-pillar was carried out on AutoForm software,and dangerous forming areas were discovered.The processi
文章根据2001~2005年呼和浩特市环境监测资料,运用主要污染物监测统计结果、不同污染物的污染分担率比较、综合污染指数、地表水质变化趋势等方式分析了呼和浩特市地表水的污染现状、变化趋势、地表水质污染特征和地表水质污染的原因。
Resin adsorption technique with XAD-8 and XAD-4 was used to characterize the raw water from Erlong reservoir in Jilin province of China. The NOM chemical compos
In the paper the three-dimensional flow fields are numerically simulated in the vertical-shaft mechanical mix tank of a water treatment plant by means of FLUENT
期刊
<正> 自1991年6月开始通过国际协力事业团的&#39;印度二化性养蚕技术开发计划&#39;的五年计划,带着困难的问题迎来了第三个年头。执行本计划的是卡纳塔克邦的迈索尔和班加罗
Three-dimensional ( 3-D) directional wave focusing is one of the mechanisms that contribute to the generation of freak waves. To simulate and analyze this pheno
期刊