Emergent Communication through Negotiation
This work addresses the challenge of emergent communication in AI agents, providing insights into negotiation and cooperation mechanisms, but it is incremental as it builds on existing multi-agent reinforcement learning frameworks.
The paper tackled the problem of how communication emerges in multi-agent negotiation environments, showing that self-interested agents can use grounded communication for fair negotiation but fail with ungrounded cheap talk, whereas prosocial agents learn to use cheap talk for optimal strategies, indicating cooperation is necessary for language emergence.
Multi-agent reinforcement learning offers a way to study how communication could emerge in communities of agents needing to solve specific problems. In this paper, we study the emergence of communication in the negotiation environment, a semi-cooperative model of agent interaction. We introduce two communication protocols -- one grounded in the semantics of the game, and one which is \textit{a priori} ungrounded and is a form of cheap talk. We show that self-interested agents can use the pre-grounded communication channel to negotiate fairly, but are unable to effectively use the ungrounded channel. However, prosocial agents do learn to use cheap talk to find an optimal negotiating strategy, suggesting that cooperation is necessary for language to emerge. We also study communication behaviour in a setting where one agent interacts with agents in a community with different levels of prosociality and show how agent identifiability can aid negotiation.