Incorporating Pragmatic Reasoning Communication into Emergent Language
This work addresses the challenge of improving communication efficiency and naturalness in AI agents, though it appears incremental as it builds on existing linguistics and multi-agent reinforcement learning frameworks.
The paper tackled the problem of combining short-term pragmatic reasoning with long-term emergent language in multi-agent communication, showing that this integration leads to more natural, accurate, robust, fine-grained, and succinct utterances in referential games and Starcraft II.
Emergentism and pragmatics are two research fields that study the dynamics of linguistic communication along substantially different timescales and intelligence levels. From the perspective of multi-agent reinforcement learning, they correspond to stochastic games with reinforcement training and stage games with opponent awareness. Given that their combination has been explored in linguistics, we propose computational models that combine short-term mutual reasoning-based pragmatics with long-term language emergentism. We explore this for agent communication referential games as well as in Starcraft II, assessing the relative merits of different kinds of mutual reasoning pragmatics models both empirically and theoretically. Our results shed light on their importance for making inroads towards getting more natural, accurate, robust, fine-grained, and succinct utterances.