scholarly journals D-MG Tradeoff and Optimal Codes for a Class of AF and DF Cooperative Communication Protocols

2007 ◽  
Author(s):  
Petros Elia ◽  
K. Vinodh ◽  
M. Anand ◽  
P. Vijay Kumar
Keyword(s):  
Cooperative Communication ◽  
Communication Protocols ◽  
Optimal Codes

D-MG Tradeoff and Optimal Codes for a Class of AF and DF Cooperative Communication Protocols

2009 ◽  
Vol 55 (7) ◽  
pp. 3161-3185 ◽  
Author(s):  
Petros E. Elia ◽  
K. Vinodh ◽  
M. Anand ◽  
P. Vijay Kumar
Keyword(s):  
Cooperative Communication ◽  
Communication Protocols ◽  
Optimal Codes

scholarly journals Multi Agent Deep Learning with Cooperative Communication

2020 ◽  
Vol 10 (3) ◽  
pp. 189-207
Author(s):  
David Simões ◽  
Nuno Lau ◽  
Luís Paulo Reis
Keyword(s):  
Deep Learning ◽  
Cooperative Communication ◽  
State Of The Art ◽  
Communication Protocols ◽  
Relevant Information ◽  
Distributed Execution ◽  
Multi Agent ◽  
Multiple Environments ◽  
Partially Observable ◽  
Multi Agents

AbstractWe 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.

Sign in / Sign up

Export Citation Format

Share Document