Emergent Cooperation in Quantum Multi-Agent Reinforcement Learning Using Communication
This addresses the limited research on extending cooperation mechanisms to quantum multi-agent systems, which is an incremental step for researchers in quantum AI and multi-agent learning.
The paper tackled the problem of fostering emergent cooperation in Quantum Multi-Agent Reinforcement Learning by applying communication protocols like MATE and MEDIATE to quantum Q-Learning agents in Sequential Social Dilemmas, achieving high cooperation levels across all tested dilemmas.
Emergent cooperation in classical Multi-Agent Reinforcement Learning has gained significant attention, particularly in the context of Sequential Social Dilemmas (SSDs). While classical reinforcement learning approaches have demonstrated capability for emergent cooperation, research on extending these methods to Quantum Multi-Agent Reinforcement Learning remains limited, particularly through communication. In this paper, we apply communication approaches to quantum Q-Learning agents: the Mutual Acknowledgment Token Exchange (MATE) protocol, its extension Mutually Endorsed Distributed Incentive Acknowledgment Token Exchange (MEDIATE), the peer rewarding mechanism Gifting, and Reinforced Inter-Agent Learning (RIAL). We evaluate these approaches in three SSDs: the Iterated Prisoner's Dilemma, Iterated Stag Hunt, and Iterated Game of Chicken. Our experimental results show that approaches using MATE with temporal-difference measure (MATE\textsubscript{TD}), AutoMATE, MEDIATE-I, and MEDIATE-S achieved high cooperation levels across all dilemmas, demonstrating that communication is a viable mechanism for fostering emergent cooperation in Quantum Multi-Agent Reinforcement Learning.