提出了一种利用Q-学习解决动态单机调度环境下的自适应调度规则选择的方法。
Q-learning was applied to resolution of the adaptive dispatching rule selection problem under dynamic single-machine scheduling environment.
指出确定性环境下的最小化误工任务数单机调度问题是模糊情况的特例。
Also, the deterministic counterpart of this single machine scheduling problem is a special case of fuzzy version.
基于对问题的分析,证明了这一问题等价于单机调度中极小化类似的延迟量函数。
Through the analysis of the problem, it is proved that the problem is equivalent to a single-machine scheduling for minimizing an analogous function of delay.
应用推荐