<abstract xmlns="http://www.w3.org/1999/xhtml"><p>We consider the problem of multi agents cooperating in a partially-observable environment. Agents must learn to coordinate and share relevant information to solve the tasks successfully. This article describes Asynchronous Advantage Actor-Critic with Communication (A3C2), an end-to-end differentiable approach where agents learn policies and communication protocols simultaneously. A3C2 uses a centralized learning, distributed execution paradigm, supports independent agents, dynamic team sizes, partially-observable environments, and noisy communications. We compare and show that A3C2 outperforms other state-of-the-art proposals in multiple environments.</p></abstract>

We consider the problem of multi agents cooperating in a partially-observable environment. Agents must learn to coordinate and share relevant information to solve the tasks successfully. This article describes Asynchronous Advantage Actor-Critic with Communication (A3C2), an end-to-end differentiable approach where agents learn policies and communication protocols simultaneously. A3C2 uses a centralized learning, distributed execution paradigm, supports independent agents, dynamic team sizes, partially-observable environments, and noisy communications. We compare and show that A3C2 outperforms other state-of-the-art proposals in multiple environments.

Multi Agent Deep Learning with Cooperative Communication

Electronics, Telecommunications and Informatics Department

Artificial Intelligence and Computer Science Lab

Faculty of Engineering of the University of Porto

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

{"article-title":"Multi Agent Deep Learning with Cooperative Communication"}

We consider the problem of multi agents cooperating in a partially-observable environment. Agents must learn to coordinate and share relevant information to...

Multi Agent Deep Learning with Cooperative Communication

Data publikacji: 23 maj 2020

Zakres stron: 189 - 207

Otrzymano: 01 lis 2019

Przyjęty: 26 mar 2020

DOI: https://doi.org/10.2478/jaiscr-2020-0013

Słowa kluczowe
multi-agent systems, deep reinforcement learning, centralized learning

© 2020 David Simões et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Multi Agent Deep Learning with Cooperative Communication

Data publikacji: 23 maj 2020

Zakres stron: 189 - 207

Otrzymano: 01 lis 2019

Przyjęty: 26 mar 2020

DOI: https://doi.org/10.2478/jaiscr-2020-0013

Słowa kluczowemulti-agent systems, deep reinforcement learning, centralized learning

© 2020 David Simões et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Słowa kluczowe
multi-agent systems, deep reinforcement learning, centralized learning