On Emergent Communication in Competitive Multi-Agent Teams

03/04/2020
by   Paul Pu Liang, et al.
10

Several recent works have found the emergence of grounded compositional language in the communication protocols developed by mostly cooperative multi-agent systems when learned end-to-end to maximize performance on a downstream task. However, human populations learn to solve complex tasks involving communicative behaviors not only in fully cooperative settings but also in scenarios where competition acts as an additional external pressure for improvement. In this work, we investigate whether competition for performance from an external, similar agent team could act as a social influence that encourages multi-agent populations to develop better communication protocols for improved performance, compositionality, and convergence speed. We start from Task Talk, a previously proposed referential game between two cooperative agents as our testbed and extend it into Task, Talk Compete, a game involving two competitive teams each consisting of two aforementioned cooperative agents. Using this new setting, we provide an empirical study demonstrating the impact of competitive influence on multi-agent teams. Our results show that an external competitive influence leads to improved accuracy and generalization, as well as faster emergence of communicative languages that are more informative and compositional.

READ FULL TEXT
research
06/26/2017

Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog

A number of recent works have proposed techniques for end-to-end learnin...
research
10/29/2021

Mixed Cooperative-Competitive Communication Using Multi-Agent Reinforcement Learning

By using communication between multiple agents in multi-agent environmen...
research
12/23/2018

Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

Learning when to communicate and doing that effectively is essential in ...
research
03/15/2017

Emergence of Grounded Compositional Language in Multi-Agent Populations

By capturing statistical patterns in large corpora, machine learning has...
research
08/09/2023

AI4GCC – Track 3: Consumption and the Challenges of Multi-Agent RL

The AI4GCC competition presents a bold step forward in the direction of ...
research
10/29/2020

Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations

Effective communication is an important skill for enabling information e...
research
01/25/2016

The Utility of Hedged Assertions in the Emergence of Shared Categorical Labels

We investigate the emergence of shared concepts in a community of langua...

Please sign up or login with your details

Forgot password? Click here to reset