Emergence of Multi-Step Discrete State Transition through Reinforcement Learning with a Recurrent Neural Network

Emergence of Multi-Step Discrete State Transition through Reinforcement Learning with a Recurrent Neural Network
复制标题

通过循环神经网络强化学习实现多步离散状态转换

DOI:
--
复制
发表时间:
2012
期刊:
LNCS(Lecture Notes in Computer Science), Neural Information Processing, Proc. of ICONIP (Int'l Conf. on Neural Information Processing)
影响因子:
--
通讯作者:
Yoshito Sawatsubashi and Katsunari Shibata
Yoshito Sawatsubashi and Katsunari Shibata
中科院分区:
--
文献类型:
--
作者:
Mohamad Faizal bin Samsudin;Yoshito Sawatsubashi and Katsunari Shibata

文献摘要

相似文献