On-line Training of ESN and IP Tuning Effect
On-line Training of ESN and IP Tuning Effect
复制标题
DOI：
10.1007/978-3-319-11179-7_4
复制
发表时间：
2014-09
期刊：
影响因子：
--
通讯作者：
P. Koprinkova-Hristova
中科院分区：
文献类型：
--
作者：
P. Koprinkova-Hristova
在本文中，我们研究了回声状态网络（ESN）水库的IP调谐对在线训练的自适应评论网络的整体行为的影响。实验中使用自适应临界设计（ACD）计划与在线可训练的ESN评论真实的时间控制的移动的实验室机器人。通过比较有无IP调整的ESN批评者的行为，发现IP算法显著改善了批评者的行为。据观察，IP调谐防止不受控制的增加水库输出权重在线训练期间。
In the present paper we investigate influence of IP tuning of Echo state network (ESN) reservoir on the overall behavior of the on-line trained adaptive critic network. The experiments were done using Adaptive Critic Design (ACD) scheme with on-line trainable ESN critic for real time control of a mobile laboratory robot. Comparison of behavior of ESN critics trained with and without IP tuning showed that IP algorithm improved critic behavior significantly. It was observed that IP tuning prevents uncontrolled increase of reservoir output weights during on-line training.