Q-Learning-Based Teaching-Learning Optimization for Distributed Two-Stage Hybrid Flow Shop Scheduling with Fuzzy Processing Time

Two-stage hybrid flow shop scheduling has been extensively considered in single-factory settings.However,the distributed two-stage hybrid flow shop scheduling problem(DTHFSP)with fuzzy processing time is seldom investigated in multiple factories.Furthermore,the integration of reinforcement learning and metaheuristic is seldom applied to solve DTHFSP.In the current study,DTHFSP with fuzzy processing time was investigated,and a novel Q-learning-based teaching-learning based optimization(QTLBO)was constructed to minimize makespan.Several teachers were recruited for this study.The teacher phase,learner phase,teacher’s self-learning phase,and learner’s self-learning phase were designed.The Q-learning algorithm was implemented by 9 states,4 actions defined as combinations of the above phases,a reward,and an adaptive action selection,which were applied to dynamically adjust the algorithm structure.A number of experiments were conducted.The computational results demonstrate that the new strategies of QTLBO are effective;furthermore,it presents promising results on the considered DTHFSP.

Hybrid algorithms for handling the numerical noise in topology optimization

This paper presents new hybrid methods for the identification of optimal topologies by combining the teaching-learning based optimization(TLBO)and the method of moving asymptotes(MMA).The topology optimization problem is parameterizing with a low dimensional explicit method called moving morphable components(MMC),to make the use of evolutionary algorithms more efficient.Gradient-based solvers have good performance in solving large-scale topology optimization problems.However,in unconventional cases same as crashworthiness design in which there is numerical noise in the gradient information,the uses of these algorithms are unsuitable.The standard evolutionary algorithms can solve such problems since they don’t need gradient information.However,they have a high computational cost.This paper is based upon the idea of combining metaheuristics with mathematical programming to handle the probable noises and have faster convergence speed.Due to the ease of computations,the compliance minimization problem is considered as the case study and the artificial noise is added in gradient information.