公开(公告)号：US08175982B2

公开(公告)日：2012-05-08

申请号：US12065558

申请日：2006-08-18

申请人： Tomoki Hamagami ,  Takesi Shibuya

发明人： Tomoki Hamagami ,  Takesi Shibuya

IPC分类号： G06F15/18 ,  G06E1/00

CPC分类号： G06N99/005

摘要： Reinforcement learning is one of the intellectual operations applied to autonomously moving robots etc. It is a system having excellent sides, for example, enabling operation in unknown environments. However, it has the basic problem called the “incomplete perception problem”. A variety of solution has been proposed, but none has been decisive. The systems also become complex. A simple and effective method of solution has been desired.A complex value function defining a state-action value by a complex number is introduced. Time series information is introduced into a phase part of the complex number value. Due to this, the time series information is introduced into the value function without using a complex algorithm, so the incomplete perception problem is effectively solved by simple loading of the method.

摘要翻译： 加固学习是应用于自主移动机器人等的智力操作之一。它是具有优异方面的系统，例如，在未知环境中运行。 但是，它有一个基本的问题叫做“不完全的感知问题”。 已经提出了各种解决方案，但没有一个是决定性的。 系统也变得复杂。 希望有一种简单有效的解决方法。 介绍了通过复数定义状态动作值的复数值函数。 时间序列信息被引入复数值的相位部分。 由此，将时间序列信息引入到值函数中而不使用复杂的算法，因此通过简单的方法加载有效地解决了不完全的感知问题。

公开(公告)号：US20090234783A1

公开(公告)日：2009-09-17

申请号：US12065558

申请日：2006-08-18

申请人： Tomoki Hamagami ,  Takeshi Shibuya

发明人： Tomoki Hamagami ,  Takeshi Shibuya

IPC分类号： G06F15/18

CPC分类号： G06N99/005

摘要： Reinforcement learning is one of the intellectual operations applied to autonomously moving robots etc. It is a system having excellent sides, for example, enabling operation in unknown environments. However, it has the basic problem called the “incomplete perception problem”. A variety of solution has been proposed, but none has been decisive. The systems also become complex. A simple and effective method of solution has been desired.A complex value function defining a state-action value by a complex number is introduced. Time series information is introduced into a phase part of the complex number value. Due to this, the time series information is introduced into the value function without using a complex algorithm, so the incomplete perception problem is effectively solved by simple loading of the method.

摘要翻译： 加固学习是应用于自主移动机器人等的智力操作之一。它是具有优异方面的系统，例如，在未知环境中运行。 但是，它有一个基本的问题叫做“不完全的感知问题”。 已经提出了各种解决方案，但没有一个是决定性的。 系统也变得复杂。 希望有一种简单有效的解决方法。 介绍了通过复数定义状态动作值的复数值函数。 时间序列信息被引入复数值的相位部分。 由此，将时间序列信息引入到值函数中而不使用复杂的算法，因此通过简单的方法加载有效地解决了不完全的感知问题。