Fast and Stable Learning in Direct-Vision-Based Reinforcement learning
Fast and Stable Learning in Direct-Vision-Based Reinforcement learning
复制标题
基于直接视觉的强化学习中快速稳定的学习
DOI：
--
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
K. Ito
中科院分区：
文献类型：
--
作者：
K. Shibata;M. Sugisaka;K. Ito
基于直接视觉的强化学习（Direct-Vision-Based Reinforcement Learning，简称Direct-Vision-Based Reinforcement Learning）不仅适用于机器人的运动规划，而且适用于机器人从传感器到电机的整个过程的学习，包括识别、注意等，它将原始视觉感知信号直接输入到一个分层神经网络中，并利用基于强化学习产生的训练信号对网络进行训练。另一方面，有人指出，神经网络和TD型强化学习的结合有时会导致学习的不稳定性。在本文中，它表明，每个视觉感觉细胞，使我们的连续三维空间的定位的作用，它有助于学习是快速和稳定的。进一步通过在分层神经网络中处理局部输入信号，通过学习在隐藏层中自适应地重建全局表示，如先前的论文所示。
Direct-Vision-Based Reinforcement Learning has been proposed not only for the motion planning but for the learning of the whole process from sensors to motors in robots, including recognition, attention and so on. In this learning, raw visual sensory signals are put into a layered neural network directly, and the network is trained by the training signals generated based on reinforcement learning. On the other hand, it has been pointed out that the combination of neural network and TD-type reinforcement learning sometimes leads to instability of learning. In this paper, it is shown that each visual sensory cell makes a role of localization of our continuous 3-dimensional space and it helps the learning to be fast and stable. Further by processing the localized input signals in the layered neural network, a global representation is reconstructed adaptively in the hidden layer through learning as shown in the previous papers.