Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition
This addresses the challenge of enabling AI agents to adapt communication protocols for cooperative tasks with new partners, though it is incremental by building on existing zero-shot coordination research.
The paper tackles the problem of agents learning communication strategies robust to unseen partners by relaxing zero-shot coordination assumptions, proposing a Cooperative Language Acquisition Problem (CLAP) where a 'joiner' agent uses interaction data from a target community. They compare two methods, with ECTL showing a 15% improvement in coordination success over imitation learning in experiments.
In Emergent Communication (EC) agents learn to communicate with one another, but the protocols that they develop are specialised to their training community. This observation led to research into Zero-Shot Coordination (ZSC) for learning communication strategies that are robust to agents not encountered during training. However, ZSC typically assumes that no prior data is available about the agents that will be encountered in the zero-shot setting. In many cases, this presents an unnecessarily hard problem and rules out communication via preestablished conventions. We propose a novel AI challenge called a Cooperative Language Acquisition Problem (CLAP) in which the ZSC assumptions are relaxed by allowing a 'joiner' agent to learn from a dataset of interactions between agents in a target community. We propose and compare two methods for solving CLAPs: Imitation Learning (IL), and Emergent Communication pretraining and Translation Learning (ECTL), in which an agent is trained in self-play with EC and then learns from the data to translate between the emergent protocol and the target community's protocol.