公开(公告)号：US08290883B2

公开(公告)日：2012-10-16

申请号：US12556872

申请日：2009-09-10

申请人： Johane Takeuchi ,  Hiroshi Tsujino

发明人： Johane Takeuchi ,  Hiroshi Tsujino

IPC分类号： G06F15/18

CPC分类号： G06N99/005

摘要： A learning system according to the present invention includes an event list database for storing a plurality of event lists, each of the event lists being a set including a series of state-action pairs which reaches a state-action pair immediately before earning a reward, an event list managing section for classifying state-action pairs into the plurality of event lists for storing, and a learning control section for updating expectation of reward of a state-action pair which is an element of each of the event lists.

摘要翻译： 根据本发明的学习系统包括用于存储多个事件列表的事件列表数据库，每个事件列表是包括在获得奖励之前到达状态 - 动作对的一系列状态 - 动作对的集合， 用于将状态对对分为用于存储的多个事件列表的事件列表管理部分，以及用于更新作为每个事件列表的元素的状态对的奖励的期望的学习控制部分。

公开(公告)号：US20100070439A1

公开(公告)日：2010-03-18

申请号：US12556872

申请日：2009-09-10

申请人： Johane Takeuchi ,  Hiroshi Tsujino

发明人： Johane Takeuchi ,  Hiroshi Tsujino

IPC分类号： G06F15/18

CPC分类号： G06N99/005

摘要： A learning system according to the present invention includes an event list database for storing a plurality of event lists, each of the event lists being a set including a series of state-action pairs which reaches a state-action pair immediately before earning a reward, an event list managing section for classifying state-action pairs into the plurality of event lists for storing, and a learning control section for updating expectation of reward of a state-action pair which is an element of each of the event lists.

摘要翻译： 根据本发明的学习系统包括用于存储多个事件列表的事件列表数据库，每个事件列表是包括在获得奖励之前到达状态 - 动作对的一系列状态 - 动作对的集合， 用于将状态对对分为用于存储的多个事件列表的事件列表管理部分，以及用于更新作为每个事件列表的元素的状态对的奖励的期望的学习控制部分。