Facility layout planning (FLP) involves a set of design problems related to the arrangement of the elements that shape industrial production systems in a physical space. The fact that they are considered one of the most important design decisions as part of business operation strategies, and their proven repercussion on production systems’ operation costs, efficiency and productivity, mean that this theme has been widely addressed in science. In this context, the present article offers a scientific literature review about FLP from the operations management perspective. The 232 reviewed articles were classified as a large taxonomy based on type of problem, approach and planning stage and characteristics of production facilities by configuring the material handling system and methods to generate and assess layout alternatives. We stress that the generation of layout alternatives was done mainly using mathematical optimisation models, specifically discrete quadratic programming models for similar sized departments, or continuous linear and non-linear mixed integer programming models for different sized departments. Other approaches followed to generate layout alternatives were expert’s knowledge and specialised software packages. Generally speaking, the most frequent solution algorithms were metaheuristics.

The objective of this paper is to examine the use and applications of reinforcement learning (RL) techniques in the production planning and control (PPC) field addressing the following PPC areas: facility resource planning, capacity planning, purchase and supply management, production scheduling and inventory management. The main RL characteristics, such as method, context, states, actions, reward and highlights, were analysed. The considered number of agents, applications and RL software tools, specifically, programming language, platforms, application programming interfaces and RL frameworks, among others, were identified, and 181 articles were sreviewed. The results showed that RL was applied mainly to production scheduling problems, followed by purchase and supply management. The most revised RL algorithms were model-free and single-agent and were applied to simplified PPC environments. Nevertheless, their results seem to be promising compared to traditional mathematical programming and heuristics/metaheuristics solution methods, and even more so when they incorporate uncertainty or non-linear properties. Finally, RL value-based approaches are the most widely used, specifically Q-learning and its variants and for deep RL, deep Q-networks. In recent years however, the most widely used approach has been the actor-critic method, such as the advantage actor critic, proximal policy optimisation, deep deterministic policy gradient and trust region policy optimisation.