Operating autonomous agents inside a 3D workspace is a challenging problem domain in real-time for dynamic environments since it involves online interaction with ever-changing decision constraints. This study proposes a neuroscience inspired architecture to simulate autonomous agents with interaction capabilities inside a 3D virtual world. The environment stimulates the operating agents based on their place and course of action. They are expected to form a life cycle composed of behavior chunks inside this environment and continuously optimize it around the stimulated reward. The architecture is composed of specialized units that run Cortical Learning Algorithm (CLA) which models functional properties of layers II and III as in six layer theory of neocortex. This work focuses on extending it with functional properties of layers IV, V and basal ganglia to obtain voluntary behavior that is suitable for an autonomous agent. Through experimental scenarios, the architecture is observed and evaluated in order to obtain an apparent learning process. The communication between layers and internal connectivity of embedded CLA units are able to capture sequential and causal relations from the environment and the first evaluation of the implementation has high potential for future directions.