Re-conceptualising the Language Game Paradigm in the Framework of Multi-Agent Reinforcement Learning

04/09/2020
by   Paul Van Eecke, et al.
0

In this paper, we formulate the challenge of re-conceptualising the language game experimental paradigm in the framework of multi-agent reinforcement learning (MARL). If successful, future language game experiments will benefit from the rapid and promising methodological advances in the MARL community, while future MARL experiments on learning emergent communication will benefit from the insights and results gained from language game experiments. We strongly believe that this cross-pollination has the potential to lead to major breakthroughs in the modelling of how human-like languages can emerge and evolve in multi-agent systems.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/09/2023

SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning

There is a lack of standard benchmarks for Multi-Agent Reinforcement Lea...
research
02/07/2018

From Game-theoretic Multi-agent Log Linear Learning to Reinforcement Learning

Multi-agent Systems (MASs) have found a variety of industrial applicatio...
research
07/20/2020

Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loop

We present the Battlesnake Challenge, a framework for multi-agent reinfo...
research
01/26/2019

Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning

Humans are capable of attributing latent mental contents such as beliefs...
research
05/23/2016

Towards Multi-Agent Communication-Based Language Learning

We propose an interactive multimodal framework for language learning. In...
research
11/17/2018

Emergence of linguistic conventions in multi-agent reinforcement learning

Recently, emergence of signaling conventions, among which language is a ...

Please sign up or login with your details

Forgot password? Click here to reset