Learning to Communicate in Multi-Agent Reinforcement Learning : A Review

11/13/2019
by   Mohamed Salah Zaïem, et al.
0

We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the recent algorithms developed to improve the agents' policy by allowing the sharing of information between agents and the learning of communication strategies, with a focus on Deep Recurrent Q-Network-based models. We also describe recent efforts to interpret the languages generated by these agents and study their properties in an attempt to generate human-language-like sentences. We discuss the metrics used to evaluate the generated communication strategies and propose a novel entropy-based evaluation metric. Finally, we address the issue of the cost of communication and introduce the idea of an experimental setup to expose this cost in cooperative-competitive game.

READ FULL TEXT
research
05/21/2022

Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel

In Multi-Agent Reinforcement Learning (MARL), specialized channels are o...
research
04/22/2021

Optimal communication and control strategies in a multi-agent MDP problem

The problem of controlling multi-agent systems under different models of...
research
01/25/2021

Emergent Communication under Competition

The literature in modern machine learning has only negative results for ...
research
11/28/2021

Emergent Graphical Conventions in a Visual Communication Game

Humans communicate with graphical sketches apart from symbolic languages...
research
08/27/2011

Providing information can be a stable non-cooperative evolutionary strategy

Human language is still an embarrassment for evolutionary theory, as the...
research
02/07/2014

Frequency-Based Patrolling with Heterogeneous Agents and Limited Communication

This paper investigates multi-agent frequencybased patrolling of interse...
research
01/19/2022

The Enforcers: Consistent Sparse-Discrete Methods for Constraining Informative Emergent Communication

Communication enables agents to cooperate to achieve their goals. Learni...

Please sign up or login with your details

Forgot password? Click here to reset