Reinforcement learning when visual sensory signals are directly given as inputs
Reinforcement learning when visual sensory signals are directly given as inputs
复制标题
直接给出视觉感觉信号作为输入时的强化学习
DOI：
10.1109/icnn.1997.614154
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
Y. Okabe
中科院分区：
文献类型：
--
作者：
K. Shibata;Y. Okabe
研究表明，基于神经网络的学习系统直接从视觉传感器获取视觉信号作为输入，可以通过强化学习来修正其输出。即使每个视觉细胞只覆盖一个局部感受区，学习系统也可以整合这些视觉信号并获得平滑的评价函数。通过学习，平滑地表示隐含层中的空间信息，并在隐含神经元的空间中放大系统看似重要的状态区域。这种学习是如此的自适应，当系统中采用不同的运动特征时，即使环境相同，表示也会与先前的表示不同。
It is shown that a neural-network based learning system, which obtains visual signals as inputs directly from visual sensors, can modify its outputs by reinforcement learning. Even if each visual cell covered only a local receptive field, the learning system could integrate these visual signals and obtain a smooth evaluation function. It also represented the spatial information smoothly in the hidden layer through the learning, and the area of the state which seemed important for the system was magnified in the hidden neurons' space. The learning is so adaptive that when a different motion characteristic was employed in the system, the representation became different from the previous one, even if the environment was the same.