technical paper

AAMAS 2020

May 11, 2020

Live on Underline

Learning and Testing Resilience in Cooperative Multi-Agent Systems

DOI: 10.48448/zrfx-ja26

State-of-the-art multi-agent reinforcement learning has achieved remarkable success in recent years. The success has been mainly based on the assumption that all teammates perfectly cooperate to optimize a global objective in order to achieve a common goal. While this may be true in the ideal case, these approaches could fail in practice, since in multi-agent systems (MAS), all agents may be a potential source of failure. In this presentation, we focus on resilience in cooperative MAS and propose an Antagonist-Ratio Training Scheme (ARTS) by reformulating the original target MAS as a mixed cooperative-competitive game between a group of protagonists which represent agents of the target MAS and a group of antagonists which represent failures in the MAS. While the protagonists can learn robust policies to ensure resilience against failures, the antagonists can learn malicious behavior to provide an adequate test suite for other MAS. We empirically evaluate ARTS in a cyber physical production domain and show the effectiveness of ARTS w.r.t. resilience and testing capabilities.

Downloads

Slides

Next from AAMAS 2020

technical paper

Fair Allocation of Resources with Uncertain Availability

AAMAS 2020

Jan Buermann and 2 other authors

11 May 2020

Similar lecture

keynote

Swarm Intelligence in Distributed Systems' Use-cases

IJCCI 2019

Vesna Sesum-Cavic

18 September 2019

Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2020 Underline - All rights reserved

Made with ❤️ in New York City