让游戏AI听懂战术指令，灵活调整作战风格。
TacticCraft: Natural Language-Driven Tactical Adaptation for StarCraft II
- 用轻量适配模块控制策略，不改动原模型核心
- 在保持竞争力前提下实现攻防、扩张等多维度变化
- 适合需要自定义战术的RTS游戏开发者或研究者
我们提出一种基于适配器的方法，用于对《星际争霸2》人工智能代理进行战术调控。现有智能体虽强大，但无法根据高层战术指令调整策略。本方法冻结预训练策略网络（DI-Star），在每个动作头附加轻量适配模块，由编码战略偏好的战术张量驱动。通过引入KL散度约束训练这些适配器，确保策略保留核心能力的同时实现战术多样性。实验表明，该方法成功在攻击性、扩张模式和技术偏好等战术维度上调节代理行为，同时维持竞争性表现。该方法以极低计算开销实现灵活战术控制，为复杂实时策略游戏提供实用的策略定制方案。
原文摘要 · Abstract (English)
We present an adapter-based approach for tactical conditioning of StarCraft II AI agents. Current agents, while powerful, lack the ability to adapt their strategies based on high-level tactical directives. Our method freezes a pre-trained policy network (DI-Star) and attaches lightweight adapter modules to each action head, conditioned on a tactical tensor that encodes strategic preferences. By training these adapters with KL divergence constraints, we ensure the policy maintains core competencies while exhibiting tactical variations. Experimental results show our approach successfully modulates agent behavior across tactical dimensions including aggression, expansion patterns, and technology preferences, while maintaining competitive performance. Our method enables flexible tactical control with minimal computational overhead, offering practical strategy customization for complex real-time strategy games.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。