Implicit Repair with Reinforcement Learning in Emergent Communication

TL;DR

This paper investigates how reinforcement learning can foster implicit repair in emergent communication, enabling agents to add redundancy and maintain effective communication despite environmental noise.

Contribution

It introduces a reinforcement learning approach to promote implicit repair through redundancy in emergent communication protocols under noisy conditions.

Findings

Agents add redundancy to mitigate noise effects.

Communication protocols generalize well to deterministic and noisy environments.

The method produces robust protocols handling both noisy and noise-free scenarios.

Abstract

Conversational repair is a mechanism used to detect and resolve miscommunication and misinformation problems when two or more agents interact. One particular and underexplored form of repair in emergent communication is the implicit repair mechanism, where the interlocutor purposely conveys the desired information in such a way as to prevent misinformation from any other interlocutor. This work explores how redundancy can modify the emergent communication protocol to continue conveying the necessary information to complete the underlying task, even with additional external environmental pressures such as noise. We focus on extending the signaling game, called the Lewis Game, by adding noise in the communication channel and inputs received by the agents. Our analysis shows that agents add redundancy to the transmitted messages as an outcome to prevent the negative impact of noise on the task success. Additionally, we observe that the emerging communication protocol's generalization capabilities remain equivalent to architectures employed in simpler games that are entirely deterministic. Additionally, our method is the only one suitable for producing robust communication protocols that can handle cases with and without noise while maintaining increased generalization performance levels.