Skip to yearly menu bar Skip to main content


Paper Teaser
in
Workshop: Emergent Communication: New Frontiers

Which Language Evolves Between Heterogeneous Agents? - Communicating Movement Instructions With Widely Different Time Scopes

Marie Ossenkopf · Kevin Sebastian Luck · Kory Mathewson

Keywords: [ emergent communication ] [ reinforcement learning ]


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 analyze 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 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.

Chat is not available.