系统神经多样性：多智能体学习中的行为多样性测量（英文版）

英文标题：System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning中文摘要：本论文研究了多智能体系统的行为异质性问题，提出了一种名为 System Neural Diversity（SND）的度量方法，通过对多智能体系统的模拟实验，证明了 SND 在评估系统韧性和稳健性方面的重要性。英文摘要：Evolutionary science provides evidence that diversity confers resilience.Yet, traditional multi-agent reinforcement learning techniques commonly enforcehomogeneity to increase training sample efficiency. When a system of learningagents is not constrained to homogeneous policies, individual agents