Emergent Heterogeneous Strategies from Homogeneous Capabilities in Multi-Agent Systems

• Published in: Advances in Artificial Intelligence and Applied Cognitive Computing pp. 491 - 498
• Main Authors: Fernandez, Rolando, Zaroukian, Erin, Humann, James D., Perelman, Brandon, Dorothy, Michael R., Rodriguez, Sebastian S., Asher, Derrik E.
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing 2021
• Series: Transactions on Computational Science and Computational Intelligence
• Subjects: Heterogeneous; Homogeneous; Multi-agent reinforcement learning; predator–prey pursuit; Simulation; Strategy
• ISBN: 9783030702953; 3030702952
• ISSN: 2569-7072; 2569-7080
• DOI: 10.1007/978-3-030-70296-0_37

In multi-agent systems, agents’ abilities are often used to classify a system as either homogeneous or heterogeneous. In the context of multi-agent reinforcement learning (MARL) systems, the agents can also be homogeneous or heterogeneous in their strategies. In this work, we explore instances where agents with homogeneous capabilities must collaborate to achieve a common goal in a predator–prey pursuit task. We show that results from homogeneous and heterogeneous strategies associated with learning differ substantially from agents with fixed strategies that are analytically defined. Given that our agents are homogeneous in capability, here we explore the impact of homogeneous and heterogeneous strategies in a MARL paradigm.