The capacity to apply knowledge in a context different than the one in which it was learned has become crucial within the area of autonomous agents. This paper specifically addresses the issue of transfer of knowledge acquired through online learning in partially observable environments. We investigate the discovery of relevant abstract concepts which help the transfer of knowledge in the context of an environment characterized by its 2D geographical configuration. The architecture proposed is tested in a simple grid-world environment where two agents duel each other. Results show that an agent’s performances are improved through learning, including when it is tested on a map it has not yet seen.