Emergence of Grounded, Optimally Compositional Spatial Language among Homogeneous Agents
Abstract: A mechanism of effective communication is integral to human existence. An essential aspect of a functional communication scheme among a rational human population involves an efficient, unambiguous, adaptive, and coherent apparatus to convey one’s goal to others. Such an effective macro characteristic can emerge in a finite population through incremental learning via trial and error at the individual (micro) level, with nearly consistent individual learning faculty and experience across the population. In this paper, we study minimal yet pertinent aspects of glossogenetics, specifically primal human communication mechanisms, through computational modeling. In particular, we model the process as a language game within the fabric of a decentralized, multi-agent deep reinforcement learning setting, where the agents with local learning and neural cognitive faculties interact through a series of dialogues. Our model seeks to achieve the principle of least effort and overcome the poverty of stimulus among homogeneous agents through mirror networks. In our examinations, we observe the emergence of successful and efficient communication among static and dynamic agent populations through consistent learning.
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: We have incorporated the issues addressed by the reviewers.
Assigned Action Editor: ~Matthew_Walter1
Submission Number: 1872
Loading