中文说明：[17,18,19,20,21] 的应用程序。智力不给外面，从系统，但系统通过学习获得的新方法已被证明更多成功的 [11,22]。与学习控制系统发展的一个主要困难是事实我们不知道一个先验期望的控制行动，即控制器的输出。然而，我们有评价整体系统性能的措施。为克服这个问题的各种方法已经使用 [22]。几个作品中尝试过识别植物或更好不过，识别的逆植物或伪逆的植物。模糊神经网络控制、 遗传优化的模糊控制，通过植物的反向传播和强化学习已经被成功地用于近年来 [22,23,24,25]。强化学习认知上更具基于的版本也制定一个评论家不断地评估驱动植物与选定的控件在任何给定的状态在总体目标方面的行动的后果或性能的措施和产生模拟加固提示它反过来指导学习控制器块 [22] 中。强化信号这个认知版本已被表示为一个情感线索，因为它的确是功能的情绪就像应力、 关注、 恐惧、 满意度、 幸福等衡量目标和公用事业方面的环境条件，并提供线索调节行动选择机制 [22,26]。是否被称为情绪控制或只是一个模拟版本的强化学习与批评 （评价控制），方法是越来越多地被使用控制工程师、 机器人设计师和决策支持系统开发人员和优秀成果 [27,28,29,30,31,32]。虽然很长时间，情感被认为是一个消极的因素，阻碍理性的决策制定过程中，情感在人类认知的重要作用活动逐步加以说明是由心理学家 [33，34]。它现在已经清楚不是一项负面特质在生物学中的，情感是重要的积极力量
English Description：
applications [17,18,19,20,21]. New approaches where intelligence is not given to the system from outside, but is acquired by the system through learning, have proven much more successful [11,22]. A major difficulty associated with development of learning control systems is the fact that we do not know a-priori the desired control action, i.e. the output of the controller. However, we do have measures for evaluating the performance of the overall system. Various methods for overcoming this problem have been used [22]. Identifying the plant or better yet, identifying the inverse plant or pseudo inverse plant, has been tried in several works. Neurofuzzy control, genetically optimized fuzzy control, back-propagation through plant and reinforcement learning have been successfully used in recent years [22,23,24,25]. A more cognitively based version of reinforcement learning has also been developed in which a critic constantly assesses the consequences of actuati