A challenge towards how far the emergence of higher functions can be explained by reinforcement learning using a neural network

高级功能的出现是基于使用从传感器连接到电机的神经网络的强化学习的自主学习。虽然符号处理的出现没有取得显著的成果，但通过只从奖励和惩罚中学习，“抽象”、“记忆”、“预测”或“探索”的出现已经被证明。例如，在使用可移动相机的任务的学习中，其中需要识别和记忆箭头方向以获得奖励，实现了从图像中提取箭头方向并对其进行记忆。

Emergence of higher functions has been aimed based on autonomous learning by reinforcement learning using a neural network that connects from sensors to motors. Although no significant fruits could be shown as for the emergence of symbol processing, but the emergence of "abstraction", "memory", "prediction", or "exploration" through the learning from only rewards and punishments has been shown. For example, in the learning of a task using a movable camera in which the identification and memorization of arrow direction are necessary to get a reward, extraction of arrow direction from images and memorization of it were realized.