How Are Representations Affected by Scene Statistics in an Adaptive Active Vision System?

In a previous work (Ognibene et al., 2008) we presented a reinforcement-learning neuro-robotic architecture, based on neural population codes, which was able to develop attention control policies by interacting with the environment based on a rewarded reaching task it had to accomplish. In this paper the same architecture is used to investigate the types of internal representations that this same architecture develops when exposed to two classes of environments where objects are organised on the basis of contrasting spatial relations (Figure 1).