Several approaches have recently been proposed for learning decentralized deep multiagent policies that coordinate via a differentiable communication channel. While these policies are effective for many tasks, interpretation of their induced communication strategies has remained a challenge. Here we propose to interpret agents' messages by translating them. Unlike in typical machine translation problems, we have no parallel data to learn from. Instead we develop a translation model based on the insight that agent messages and natural language strings mean the same thing if they induce the same belief about the world in a listener. We present theoretical guarantees and empirical evidence that our approach preserves both the semantics and pragmatics of messages by ensuring that players communicating through a translation layer do not suffer a substantial loss in reward relative to players with a common language.
@article{arxiv.1704.06960,
title = {Translating Neuralese},
author = {Jacob Andreas and Anca Dragan and Dan Klein},
journal= {arXiv preprint arXiv:1704.06960},
year = {2018}
}
Comments
Fixes typos and cleans ups some model presentation details