Spiking Neural Networks are receiving a lot of attention as a powerful, computationally efficient, and hence energy efficient alternative to traditional artificial neural networks. In this paper, we present a new method to solve the lunar lander problem using a deep Q-learning approach with an Spiking Neural Network (SNN). Our contribution is a new spike encoding algorithm to encode the state vector. This makes it possible to achieve a good result in only one simulation step. In addition, we have tested several input layer sizes and network architectures. Our results are evaluated in terms of performance and runtime on a Graphics Processing Unit (GPU). Our SNN with one-hot encoding outperforms the state-of-the-art Artificial Neural Network (ANNs) with respect to its hardware requirements while still reaching a comparable accuracy.