Go to:
Logótipo
Você está em: Start > Publications > View > Exploring communication protocols and centralized critics in multi-agent deep learning
Map of Premises
Principal
Publication

Exploring communication protocols and centralized critics in multi-agent deep learning

Title
Exploring communication protocols and centralized critics in multi-agent deep learning
Type
Article in International Scientific Journal
Year
2020
Authors
Simoes, D
(Author)
Other
The person does not belong to the institution. The person does not belong to the institution. The person does not belong to the institution. Without AUTHENTICUS Without ORCID
lau, n
(Author)
Other
View Personal Page You do not have permissions to view the institutional email. Search for Participant Publications View Authenticus page Without ORCID
Journal
Vol. 27
Pages: 333-351
ISSN: 1069-2509
Publisher: IOS PRESS
Other information
Authenticus ID: P-00S-X73
Abstract (EN): Tackling multi-agent environments where each agent has a local limited observation of the global state is a non-trivial task that often requires hand-tuned solutions. A team of agents coordinating in such scenarios must handle the complex underlying environment, while each agent only has partial knowledge about the environment. Deep reinforcement learning has been shown to achieve super-human performance in single-agent environments, and has since been adapted to the multi-agent paradigm. This paper proposes A3C3, a multi-agent deep learning algorithm, where agents are evaluated by a centralized referee during the learning phase, but remain independent from each other in actual execution. This referee's neural network is augmented with a permutation invariance architecture to increase its scalability to large teams. A3C3 also allows agents to learn communication protocols with which agents share relevant information to their team members, allowing them to overcome their limited knowledge, and achieve coordination. A3C3 and its permutation invariant augmentation is evaluated in multiple multi-agent test-beds, which include partially-observable scenarios, swarm environments, and complex 3D soccer simulations.
Language: English
Type (Professor's evaluation): Scientific
No. of pages: 19
Documents
We could not find any documents associated to the publication.
Related Publications

Of the same authors

Multi-agent actor centralized-critic with communication (2020)
Article in International Scientific Journal
Simoes, D; lau, n; reis, lp
MULTI AGENT DEEP LEARNING WITH COOPERATIVE COMMUNICATION (2020)
Article in International Scientific Journal
Simoes, D; lau, n; reis, lp
Multi-agent Double Deep Q-Networks (2017)
Article in International Conference Proceedings Book
Simoes, D; lau, n; reis, lp
Learning Low-Level Behaviors and High-Level Strategies in Humanoid Soccer (2020)
Article in International Conference Proceedings Book
Simoes, D; Amaro, P; Maria Teresa Andrade; lau, n; reis, lp
Guided Deep Reinforcement Learning in the GeoFriends2 Environment (2018)
Article in International Conference Proceedings Book
Simoes, D; lau, n; reis, lp

See all (6)

Of the same journal

Stream-based explainable recommendations via blockchain profiling (2022)
Article in International Scientific Journal
Leal, F; Veloso, B; Malheiro, B; Burguillo, JC; Chis, AE; Gonzalez Velez, H
Recommend this page Top
Copyright 1996-2025 © Faculdade de Medicina Dentária da Universidade do Porto  I Terms and Conditions  I Acessibility  I Index A-Z
Page created on: 2025-07-31 at 17:19:22 | Privacy Policy | Personal Data Protection Policy | Whistleblowing | Electronic Yellow Book