Autonomous learning and adaptation of robotic trajectories by complex robots in unstructured environments, for example with the use of reinforcement learning, very quickly encounters problems where the dimensionality of the search space is beyond the range of practical use. Different methods of reducing the dimensionality have been proposed in the literature. In this paper we explore the use of deep autoencoders, where the dimensionality of autoencoder latent space is low. However, a database of actions is required to train a deep autoencoder network. The paper presents a study on the number of required database samples in order to achieve dimensionality reduction without much loss of information.