Mitsopoulos Konstantinos, Baker Lawrence, Lebiere Christian, Pirolli Peter, Orr Mark, Vardavas Raffaele
Florida Institute for Human and Machine Cognition, Pensacola, FL, United States.
RAND Corporation, Boston, MA, United States.
Front Epidemiol. 2025 Jul 28;5:1563731. doi: 10.3389/fepid.2025.1563731. eCollection 2025.
Human behavior shapes the transmission of infectious diseases and determines the effectiveness of public health measures designed to mitigate transmission. To accurately reflect these dynamics, epidemiological simulation models should endogenously account for both disease transmission and behavioral dynamics. Traditional agent-based models (ABMs) often rely on simplified rules to represent behavior, limiting their ability to capture complex decision-making processes and cognitive dynamics.
Reinforcement Learning (RL) provides a framework for modeling how agents adapt their behavior based on experience and feedback. However, implementing cognitively plausible RL in ABMs is challenging due to high-dimensional state spaces. We propose a novel framework based on Adaptive Control of Thought-Rational (ACT-R) principles and Instance-Based Learning (IBL), which enables agents to dynamically adapt their behavior using nonparametric RL without requiring extensive training on large datasets.
To demonstrate this framework, we model mask-wearing behavior during the COVID-19 pandemic, highlighting how individual decisions and social network structures influence disease transmission. Simulations reveal that local social cues drive tightly clustered masking behavior (slope = 0.54, Pearson = 0.76), while reliance on global cues alone produces weakly disassortative patterns (slope = 0.05, Pearson = 0.09), underscoring the role of local information in coordinating public health compliance.
Our results show that this framework provides a scalable and cognitively interpretable approach to integrating adaptive decision-making into epidemiological simulations, offering actionable insights for public health policy.
人类行为塑造了传染病的传播方式，并决定了旨在减轻传播的公共卫生措施的有效性。为了准确反映这些动态，流行病学模拟模型应内生地考虑疾病传播和行为动态。传统的基于主体的模型（ABM）通常依靠简化规则来表示行为，限制了它们捕捉复杂决策过程和认知动态的能力。
强化学习（RL）提供了一个框架，用于模拟主体如何根据经验和反馈调整其行为。然而，由于高维状态空间，在ABM中实现具有认知合理性的RL具有挑战性。我们提出了一个基于思维自适应控制-理性（ACT-R）原则和基于实例学习（IBL）的新颖框架，该框架使主体能够使用非参数RL动态调整其行为，而无需在大型数据集上进行广泛训练。
为了演示这个框架，我们对COVID-19大流行期间的戴口罩行为进行建模，突出了个人决策和社会网络结构如何影响疾病传播。模拟结果表明，局部社会线索驱动紧密聚集的戴口罩行为（斜率 = 0.54，皮尔逊相关系数 = 0.76），而仅依赖全局线索则产生弱异配模式（斜率 = 0.05，皮尔逊相关系数 = 0.09），强调了局部信息在协调公共卫生合规方面的作用。
我们的结果表明，这个框架提供了一种可扩展且具有认知可解释性的方法，将自适应决策整合到流行病学模拟中，为公共卫生政策提供了可操作的见解。
