Autonomic Learning Framework Based on Behavior Policy
文献类型：会议论文
| 作者 | Li DC(李德才) ; He YQ(何玉庆)
|
| 出版日期 | 2016 |
| 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 |
| 关键词 | Complex natural environment Autonomous learning framework Behavior policy Inverse reinforcement learning |
| 页码 | 501-509 |
| 通讯作者 | 李德才 |
| 中文摘要 | 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. |
| 收录类别 | CPCI（ISTP） |
| 产权排序 | 1 |
| 会议录 | Advances in Cognitive Neurodynamics (V) : Proceedings of the Fifth International Conference on Cognitive Neurodynamics
 |
| 会议录出版者 | Springer Verlag |
| 会议录出版地 | Berlin |
| 语种 | 英语 |
| ISSN号 | 2213-3569 |
| ISBN号 | 978-981-10-0205-2 |
| WOS记录号 | WOS:000387956200068 |
| 源URL | [http://ir.sia.cn/handle/173321/19243]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 推荐引用方式 GB/T 7714 | Li DC,He YQ. Autonomic Learning Framework Based on Behavior Policy[C]. 见:5th International Conference on Cognitive Neurodynamics (ICCN). Sanya, China. June 3-7, 2015. |
入库方式： OAI收割
来源：沈阳自动化研究所
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。