论文提出一种模糊强化学习算法,通过模糊推理系统将连续的状态空间映射到连续的动作空间,然后通过学习得到一个完整的规则库。
In this paper, we propose a fuzzy reinforcement algorithm, which map continuous state Spaces to continuous action Spaces by fuzzy inference system and then learn a rule base.
首先,提出一种模糊Q学习算法,通过模糊推理系统将连续的状态空间映射到连续的动作空间,然后通过学习得到一个完整的规则库。
A fuzzy Q learning algorithm is proposed in this dissertation, which map continuous state Spaces to continuous action Spaces by fuzzy inference system and then learn a rule base.
该系统采用状态映照平面初始化方法、未知模式标定技术和在线识别技术,并结合知识库和规则推理的运用,有效地实现设备状态的分类。
The system adopts the techniques of initialization of state mapping plane, calibration of unknown pattern and on-line identification and this makes plant condition clustering efficiently.
应用推荐