A simple rule how to make a reward for learning with human interaction
A simple rule how to make a reward for learning with human interaction
复制标题
一个简单的规则，如何通过人际互动来奖励学习
DOI：
10.1109/cira.2007.382921
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
K. Kurashige
中科院分区：
文献类型：
--
作者：
K. Kurashige
实验机器人采用了多种学习方法。我们可以通过向机器人发出示教信号来使机器人运动。但对于操作员来说，定义如何发出示教信号通常是繁重的，因为操作员必须猜测和考虑一个任务和环境，并定义一个函数来做到这一点。在这里，作者的目标是为每个任务和环境自动创建教学信号。在本文中，作者提出了一个简单的规则，它独立于任何任务和环境的信息，为每个任务和环境创建教学信号。这条规则是，经常发生的情况就是好情况。在本文中，作者采用强化学习作为学习方法，并以小型仿人机器人为应用对象。作者展示了通过调整规则来创造奖励，并展示了机器人可以学习和移动。
Various learning methods are adapted for experimental robot. We can make movement of a robot by giving teaching signals to a robot. But it is heavy for operator to define how to give teaching signals generally because operator must guess and think of a task and environment and define a function to do that. Here the author aim to create teaching signals automatically for each task and environment. In this paper, the author suggest a simple rule which is independent of information about any task and environment to create teaching signals for each task and environment. This rule is that a situation which is often happened is good situation. In this paper, the author adopt reinforcement learning as learning method and a small-sized humanoid robot as application. The author show creating a reward by adapting a rule and show that a robot can learn and make movement.