Mastering emergent language: learning to guide in simulated navigation
This work addresses the need for scalable and interactive cooperation between virtual agents and humans, though it is incremental as it builds on existing emergent language methods.
The paper tackled the problem of enabling virtual agents to understand and execute language instructions by introducing an autonomous agent that uses a trainable, emergent communication protocol to guide other agents in simulated navigation, resulting in faster learning, generalization across tasks, and high interpretability.
To cooperate with humans effectively, virtual agents need to be able to understand and execute language instructions. A typical setup to achieve this is with a scripted teacher which guides a virtual agent using language instructions. However, such setup has clear limitations in scalability and, more importantly, it is not interactive. Here, we introduce an autonomous agent that uses discrete communication to interactively guide other agents to navigate and act on a simulated environment. The developed communication protocol is trainable, emergent and requires no additional supervision. The emergent language speeds up learning of new agents, it generalizes across incrementally more difficult tasks and, contrary to most other emergent languages, it is highly interpretable. We demonstrate how the emitted messages correlate with particular actions and observations, and how new agents become less dependent on this guidance as training progresses. By exploiting the correlations identified in our analysis, we manage to successfully address the agents in their own language.