Re-conceptualising the Language Game Paradigm in the Framework of Multi-Agent Reinforcement Learning
This work addresses the problem of improving language emergence models for researchers in AI and linguistics, but it is incremental as it focuses on conceptual integration rather than new empirical results.
The paper tackles the challenge of integrating the language game experimental paradigm with multi-agent reinforcement learning (MARL) to enable cross-pollination between these fields, aiming to advance the modeling of emergent human-like language in multi-agent systems.
In this paper, we formulate the challenge of re-conceptualising the language game experimental paradigm in the framework of multi-agent reinforcement learning (MARL). If successful, future language game experiments will benefit from the rapid and promising methodological advances in the MARL community, while future MARL experiments on learning emergent communication will benefit from the insights and results gained from language game experiments. We strongly believe that this cross-pollination has the potential to lead to major breakthroughs in the modelling of how human-like languages can emerge and evolve in multi-agent systems.