The antagonistic behavior of the crowd often exacerbates the seriousness of the situation in sudden riots, where the spreading of antagonistic emotion and behavioral decision making in the crowd play very important roles. However, the mechanism of complex emotion influencing decision making, especially in the environment of sudden confrontation, has not yet been explored clearly. In this paper, we propose one new antagonistic crowd simulation model by combing emotional contagion and deep reinforcement learning (ACSED). Firstly, we build a group emotional contagion model based on the improved SIS contagion disease model, and estimate the emotional state of the group at each time step during the simulation. Then, the tendency of group antagonistic behavior is modeled based on Deep Q Network (DQN), where the agent can learn the combat behavior autonomously, and leverages the mean field theory to quickly calculate the influence of other surrounding individuals on the central one. Finally, the rationality of the predicted behaviors by the DQN is further analyzed in combination with group emotion, and the final combat behavior of the agent is determined. The method proposed in this paper is verified through several different settings of experiments. The results prove that emotions have a vital impact on the group combat, and positive emotional states are more conducive to combat. Moreover, by comparing the simulation results with real scenes, the feasibility of the method is further verified, which can provide good reference for formulating battle plans and improving the winning rate of righteous groups battles in a variety of situations.

中文翻译：

---

融合情绪传染和深度强化学习的对抗人群模拟模型

人群的拮抗行为经常加剧突发暴动中局势的严重性，在人群中，对抗性情绪的传播和行为决策在人群中起着非常重要的作用。然而，复杂情绪影响决策的机制，尤其是在突然冲突的环境中，尚未得到清晰的探索。在本文中，我们通过结合情绪传染和深度强化学习（ACSED）提出了一种新的对抗性人群模拟模型。首先，我们基于改进的SIS传染病模型建立了群体情绪传染模型，并在仿真过程中的每个时间步估计了群体的情绪状态。然后，基于Deep Q Network（DQN）对群体对抗行为的趋势进行建模，在这里，特工可以自主学习战斗行为，并利用平均场理论快速计算周围其他个体对中心人员的影响。最后，结合群体情感进一步分析了DQN预测行为的合理性，确定了特工的最终战斗行为。本文提出的方法通过几种不同的实验设置得到了验证。结果表明，情绪对小组战斗有至关重要的影响，积极的情绪状态更有利于战斗。此外，通过将仿真结果与真实场景进行比较，进一步验证了该方法的可行性，可为制定战斗计划，提高义军在各种情况下的战斗获胜率提供参考。并利用平均场理论快速计算周围其他个体对中心个体的影响。最后，结合群体情感进一步分析了DQN预测行为的合理性，确定了特工的最终战斗行为。本文提出的方法通过几种不同的实验设置得到了验证。结果表明，情绪对小组战斗有至关重要的影响，积极的情绪状态更有利于战斗。此外，通过将仿真结果与真实场景进行比较，进一步验证了该方法的可行性，可为制定战斗计划，提高义军在各种情况下的战斗获胜率提供参考。并利用平均场理论快速计算周围其他个体对中心个体的影响。最后，结合群体情感进一步分析了DQN预测行为的合理性，确定了特工的最终战斗行为。本文提出的方法通过几种不同的实验设置得到了验证。结果表明，情绪对小组战斗有至关重要的影响，积极的情绪状态更有利于战斗。此外，通过将仿真结果与真实场景进行比较，进一步验证了该方法的可行性，可为制定战斗计划，提高义军在各种情况下的战斗获胜率提供参考。