Year: 2017
Type: conference-paper
Abstract: 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.1
DOI: 10.18653/v1/p17-1022
Authors: Jacob Andreas, Anca Dragan, Dan Klein
Institution: University of California, Berkeley
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W3089050900
