Since they were proposed as an optimization method, the evolutionary algorithms have been successfully used for solving complex problems in several areas such as, for example, the automatic design of electronic circuits and equipments, task planning and scheduling, software engineering and data mining, among many others. This success is due, among many other things, to the fact that this class of algorithms does not need rigorous mathematical formulations regarding the problem to be optimized, and also because it offers a high degree of parallelism in the search process. However, some problems are computationally intensive when it concerns the evaluation of solutions during the search process, making the optimization by evolutionary algorithms a slow process for situations where a quick response from the algorithm is desired (for instance, in online optimization problems). Several ways to overcome this problem, by speeding up convergence time, were proposed, including Cultural Algorithms and Coevolutionary Algorithms. However, these algorithms still have the need to evaluate many solutions on each step of the optimization process. In problems where this evaluation is computationally expensive, the optimization might take a prohibitive time to reach optimal solutions. This work proposes a new evolutionary algorithm for numerical optimization problems (Quantum- Inspired Evolutionary Algorithm for Problems based on Numerical Representation - QIEA-R), inspired in the concept of quantum superposition, which allows the optimization process to be carried on with a smaller number of evaluations. The work presents the modelling for this algorithm for solving benchmark numerical optimization problems, and for training recurrent neural networks in supervised learning and reinforcement learning. The results show the good performance of this algorithm in solving these kinds of problems.