图 书 馆
具有简单递归时差网络的状态的原始预测表示Proto-Predictive Representation of States with Simple Recurrent Temporal-Difference Networks |
|
| 课程网址: | http://videolectures.net/icml09_makino_pprs/ |
| 主讲教师: | Takaki Makino |
| 开课单位: | 东京大学 |
| 开课时间: | 2009-09-17 |
| 课程语种: | 汉简 |
| 中文简介: |  |
| 课程简介: | We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable environments. SR-TDNs incorporate the structure of simple recurrent neural networks (SRNs) into temporal-difference (TD) networks to use proto-predictive representation of states. Although they deviate from the principle of predictive representations to ground state representations on observations, they follow the same learning strategy as TD networks, i.e., applying TD-learning to general predictions. Simulation experiments revealed that SR-TDNs can correctly represent states with incomplete set of core tests (question networks), and consequently, SR-TDNs have better on-line learning capacity than TD networks in various environments. |
| 关 键 词: | 神经网络架构; 简单递归时间差分网络; 问题网络 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-04-23：lxf |
| 阅读次数: | 37 |