Translating Neuralese

04/23/2017
by   Jacob Andreas, et al.
0

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.

READ FULL TEXT

page 1

page 7

research
02/22/2020

Emergent Communication with World Models

We introduce Language World Models, a class of language-conditional gene...
research
03/07/2022

Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning

For communication to happen successfully, a common language is required ...
research
02/25/2017

Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations

We introduce AI rationalization, an approach for generating explanations...
research
07/03/2023

Learning to Communicate using Contrastive Learning

Communication is a powerful tool for coordination in multi-agent RL. But...
research
05/31/2017

Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols

Learning to communicate through interaction, rather than relying on expl...
research
08/30/2017

Automatically Generating Commit Messages from Diffs using Neural Machine Translation

Commit messages are a valuable resource in comprehension of software evo...
research
12/15/2017

CoDraw: Visual Dialog for Collaborative Drawing

In this work, we propose a goal-driven collaborative task that contains ...

Please sign up or login with your details

Forgot password? Click here to reset