Keywords: Emergent Communication, Dreaming, Reinforcement Learning, Plan Execution, Topographic Similarity
TL;DR: We show that the emergent communication between agents with different time scopes and perception, trained with imagination-based learning is not predestined.
Abstract: This paper studies the evolving communication between two agents, a listener and speaker, in a plan execution task in which the speaker needs to communicate the plan to the acting agent, while operating on different time scales. We analyse the topographic similarity of the resulting language learned by the proposed imagination-based learning process. As the speaker agent perceives the movement space strictly in absolute coordinates and the actor can only choose relative actions in the movement space, we can show that the structure of their emergent communication is not predestined. Both relative and absolute encodings of desired movements can develop by chance in this setting, but we can alter the chance by using a population of learners. We conclude that our imagination-based learning strategy successfully breaks the strict hierarchy between planner and executioner.