Based on the above analysis , the research topic of this paper has been focused on 5 parts as follows : 1 ) the algorithms and theory of temporal difference learning ; 2 ) gradient learning algorithms for solving markov decision problems with continuous state or action space ; 3 ) hybrid learning methods for solving markov decision problems ; 4 ) the applications of reinforcement learning in the path tracking problems of mobile robots ; 5 ) reactive navigation methods based on reinforcement learning for mobile robots in unknown environments 在此基础上,本文的研究工作主要从5个方面展开,即:时域差值学习算法和理论;求解马氏决策问题的梯度增强学习算法;求解马氏决策问题的进化-梯度混合学习算法;增强学习在移动机器人路径跟踪控制器优化中的应用;基于增强学习的移动机器人反应式导航控制。
According to the characteristics of workflow process execution , a kind of reactive activity - centered process meta - model is defined and a kind of graphical notation is provided for it , at the same time , for this meta - model , a kind of dynamic semantics is specified , which represents the runtime behavior of the process and can be expressed as a finite state automata . finally , an example is given to illustrate how to apply it to analyze the semantic correctness of process models 根据过程执行的特点,定义了一种以活动为中心的反应式过程元模型,并为其提供了一种图形表示,同时为此元模型指定了一种体现过程运行时行为的动态语义,该语义可表示为一个有限状态自动机.最后举例说明了如何应用它分析过程模型的语义正确性