Reinforcement learning (RL) has been widely used to implement autonomous navigation in artificial agents, where the goal is to learn a behaviour which maximizes the reward, through interaction with the environment. Most of the recent architectures used in autonomous agents obtain information from the environment using visual modules implemented by convolutional neural networks, where the visual features resulting from learning are unknown or uncertain, which impose limitations considering the large number of parameters to be learned by the entire system. Research in retina physiology has been able to characterize it not as a single light-electrical transductor but as a complex device performing a variety of computations of the visual information, preparing the data for further stages of processing in the visual system. We propose an RL architecture that uses retina physiology knowledge to fed the convolutional neural network, avoiding the learning stage in the sensory input. The performance of the proposed architecture was evaluated using the DeepMind Lab environment simulating an agent moving inside two different maze scenarios. The results obtained reveal promising extension of the inclusion of biological- plausible mechanisms inside artificial intelligence applications.