MULTI AGENT DEEP LEARNING WITH COOPERATIVE COMMUNICATION

• Type: Article in International Scientific Journal
• Date: 2020

Authors

Simoes, D (Author) Other; lau, n (Author) Other; reis, lp (Author) FEUP

Journal

Title: Journal of Artificial Intelligence and Soft Computing Research

Vol. 10

Pages: 189-207

ISSN: 2083-2567

Publisher: Walter De Gruyter

Indexing

ISI Web of Knowledge - 7 Citations

Scopus - 9 Citations

Other information

Authenticus ID: P-00T-BSB

DOI: 10.2478/jaiscr-2020-0013

Abstract (EN): 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.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 19