Abstract
Enemy strategies in turn-based games should be surprising and unpredictable. This study introduces Mirror Mode, a new game mode where the enemy AI mimics the personal strategy of a player to challenge them to keep changing their gameplay. A simplified version of the Nintendo strategy video game Fire Emblem Heroes has been built in Unity, with a Standard Mode and a Mirror Mode. Our first set of experiments find a suitable model for the task to imitate player demonstrations, using Reinforcement Learning and Imitation Learning: combining Generative Adversarial Imitation Learning, Behavioral Cloning, and Proximal Policy Optimization. The second set of experiments evaluates the constructed model with player tests, where models are trained on demonstrations provided by participants. The gameplay of the participants indicates good imitation in defensive behavior, but not in offensive strategies. Participant's surveys indicated that they recognized their own retreating tactics, and resulted in an overall higher player-satisfaction for Mirror Mode. Refining the model further may improve imitation quality and increase player's satisfaction, especially when players face their own strategies. The full code and survey results are stored at: this https URL
Abstract (translated)
在回合制游戏中，敌人的策略应该具有惊喜性和不可预测性。这项研究介绍了一种新模式——镜像模式（Mirror Mode），在这种模式中，敌人的人工智能会模仿玩家的个人策略来挑战他们不断改变游戏玩法。研究人员使用Unity构建了一个简化版的《火焰之纹章：英雄》（Fire Emblem Heroes）视频游戏版本，其中包括标准模式和镜像模式。 研究的第一阶段实验找到了一个适合任务的模型，用于模仿玩家演示，该模型结合了强化学习（Reinforcement Learning）、模仿学习（Imitation Learning），具体包括生成对抗性模仿学习（Generative Adversarial Imitation Learning）、行为克隆（Behavioral Cloning）和近端策略优化（Proximal Policy Optimization）。第二阶段实验通过玩家测试评估所构建的模型，其中模型在参与者提供的演示基础上进行训练。 实验结果显示，在防守行为方面，模型表现出良好的模仿能力，但在进攻策略上表现较差。参与者的问卷调查显示他们认识到了自己撤退战术被模仿的情况，并且总体而言对镜像模式表现出更高的满意度。 进一步优化该模型可能会提高其模仿质量并增加玩家的满意度，尤其是在玩家面对自己的策略时。完整的代码和调查结果存储在：[提供的URL]（请将"this https URL"替换为实际链接）。
URL
https://arxiv.org/abs/2512.11902
