Multi-agent Neural Reinforcement-Learning System with Communication

• Type: Article in International Conference Proceedings Book
• Date: 2019

Authors

David Simões (Author) Other; Nuno Lau (Author) Other; Luís Paulo Reis (Author) FEUP

Conference proceedings International

Title: Advances in Intelligent Systems and Computing

Pages: 3-12

World Conference on Information Systems and Technologies, WorldCIST 2019

16 April 2019 through 19 April 2019

Indexing

Scopus - 3 Citations

Other information

Authenticus ID: P-00Q-K9P

DOI: 10.1007/978-3-030-16184-2_1

Abstract (EN): Deep learning models have as of late risen as popular function approximators for single-agent reinforcement learning challenges, by accurately estimating the value function of complex environments and being able to generalize to new unseen states. For multi-agent fields, agents must cope with the non-stationarity of the environment, due to the presence of other agents, and can take advantage of information sharing techniques for improved coordination. We propose an neural-based actor-critic algorithm, which learns communication protocols between agents and implicitly shares information during the learning phase. Large numbers of agents communicate with a self-learned protocol during distributed execution, and reliably learn complex strategies and protocols for partially observable multi-agent environments. © Springer Nature Switzerland AG 2019.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 10