• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Robot Intelligence Technology and Applications >Reinforcement Learning of a Memory Task Using an Echo State Network with Multi-layer Readout
【24h】

Reinforcement Learning of a Memory Task Using an Echo State Network with Multi-layer Readout

机译：使用具有多层读数的回声状态网络加强存储器任务的学习

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Training a neural network (NN) through reinforcement learning (RL) has been focused on recently, and a recurrent NN (RNN) is used in learning tasks that require memory. Meanwhile, to cover the shortcomings in learning an RNN, the reservoir network (RN) has been often employed mainly in supervised learning. The RN is a special RNN and has attracted much attention owing to its rich dynamic representations. An approach involving the use of a multi-layer readout (MLR), which comprises a multi-layer NN, was studied for acquiring complex representations using the RN. This study demonstrates that an RN with MLR can learn a "memory task" through RL with back propagation. In addition, non-linear representations required to clear the task are not observed in the RN but are constructed by learning in the MLR. The results suggest that the MLR can make up for the limited computational ability in an RN.
机译：最近一直专注于加强学习（RL）的神经网络（NN），并且反复间NN（RNN）用于需要存储器的学习任务。同时，为了涵盖学习RNN的缺点，储层网络（RN）通常主要用于受监督学习。由于其丰富的动态表示，RN是一个特殊的RNN，引起了很多关注。研究了一种使用包括多层NN的多层读数（MLR）的方法，用于使用RN获取复杂表示。本研究表明，带有MLR的RN可以通过RL来学习“存储器任务”，并通过RL向后传播。此外，在RN中未观察到清除任务所需的非线性表示，但是通过在MLR中学习来构建。结果表明，MLR可以弥补RN中的有限计算能力。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号