Multi Agent Deep Learning with Cooperative Communication
Open Access
- 23 May 2020
- journal article
- research article
- Published by Walter de Gruyter GmbH in Journal of Artificial Intelligence and Soft Computing Research
- Vol. 10 (3) , 189-207
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.Keywords
This publication has 14 references indexed in Scilit:
- Cooperative Multi-agent Control Using Deep Reinforcement Learning2017
- Multiagent cooperation and competition with deep reinforcement learningPLOS ONE, 2017
- An Experimental Review of Reinforcement Learning Algorithms for Adaptive Traffic Signal Control2016
- Using multi-agent technology for the distributed management of a cluster of remote sensing satellites2016
- Vision-Based Cyclic Pursuit for Cooperative Target TrackingJournal of Guidance, Control, and Dynamics, 2013
- Multirobot Behavior Synchronization through Direct Neural Network Communication2012
- A Comprehensive Survey of Multiagent Reinforcement LearningIEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2008
- Markov games as a framework for multi-agent reinforcement learning1994
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992
- Learning representations by back-propagating errorsNature, 1986