SIA OpenIR  > 机器人学研究室
Autonomic Learning Framework Based on Behavior Policy
Li DC(李德才); He YQ(何玉庆)
作者部门机器人学研究室
会议名称5th International Conference on Cognitive Neurodynamics (ICCN)
会议日期June 3-7, 2015
会议地点Sanya, China
会议录名称Advances in Cognitive Neurodynamics (V) : Proceedings of the Fifth International Conference on Cognitive Neurodynamics
出版者Springer Verlag
出版地Berlin
2016
页码501-509
收录类别CPCI(ISTP)
WOS记录号WOS:000387956200068
产权排序1
ISSN号2213-3569
ISBN号978-981-10-0205-2
关键词Complex Natural Environment Autonomous Learning Framework Behavior Policy Inverse Reinforcement Learning
摘要In this paper, a novel autonomous learning framework is proposed. Different form the traditional learning framework, which maps environment to the action space directly, the new method abstracts behavior policies from the demonstrations and expresses it with a parameterized model. Based on the parameterized policies, cost function and environment constraints are generated, which together with the dynamic constraints of the robot are used to optimize the decision actions. A simulation on the grid world proved the effectiveness of the proposed method.
语种英语
引用统计
文献类型会议论文
条目标识符http://ir.sia.cn/handle/173321/19243
专题机器人学研究室
通讯作者Li DC(李德才)
作者单位State Key Laboratory of Robotics, Shenyang Institute of Automation, The Chinese Academy of Sciences, Shenyang, China
推荐引用方式
GB/T 7714
Li DC,He YQ. Autonomic Learning Framework Based on Behavior Policy[C]. Berlin:Springer Verlag,2016:501-509.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Autonomic Learning F(501KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li DC(李德才)]的文章
[He YQ(何玉庆)]的文章
百度学术
百度学术中相似的文章
[Li DC(李德才)]的文章
[He YQ(何玉庆)]的文章
必应学术
必应学术中相似的文章
[Li DC(李德才)]的文章
[He YQ(何玉庆)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Autonomic Learning Framework Based on Behavior Policy.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。