综合考虑再励学习的两个重要子问题 :连续空间及语言评价问题 ,提出了一种新的学习方法 ,即面向语言评价的 Takagi-Sugeno(T-S)模糊再励学习。该学习智能体构建在 Q-学习方法和 Takagi-Sugeno模糊推理系统的基础上 ,适于处理连续域的复杂学习任务 ,亦可用于设计 Takagi-Sugeno模糊逻辑控制器。以二级倒立摆控制系统为例 ,仿真研究验证了学习算法的有效性 Considering two important sub-problems of re-energizing learning, such as continuous space and language evaluation, a new learning method is proposed, namely Takagi-Sugeno (T-S) fuzzy re-learning for linguistic assessment. Based on the Q-learning method and the Takagi-Sugeno fuzzy reasoning system, this learning agent is suitable for the complicated learning tasks in continuous domains and also for designing Takagi-Sugeno fuzzy logic controllers. Take the two inverted pendulum control system as an example, the simulation study verifies the effectiveness of the learning algorithm