智能体在数千款3D视频游戏中展开竞技

Agents Play Thousands of 3D Video Games

March 17, 2025

作者: Zhongwen Xu, Xianliang Wang, Siyi Li, Tao Yu, Liang Wang, Qiang Fu, Wei Yang

cs.AI

摘要

我们推出PORTAL，一个创新框架，旨在开发能够通过语言引导策略生成来玩数千款3D电子游戏的人工智能代理。通过将决策问题转化为语言建模任务，我们的方法利用大型语言模型（LLMs）生成以领域特定语言（DSL）表示的行为树。这一方法消除了传统强化学习方法的计算负担，同时保持了战略深度与快速适应能力。PORTAL框架引入了一种混合策略结构，结合了基于规则的节点与神经网络组件，实现了高层战略推理与精确底层控制的双重能力。通过整合定量游戏指标与视觉-语言模型分析的双重反馈机制，促进了战术与战略层面的迭代策略优化。生成的策略可即时部署、易于人类理解，并能在多样化的游戏环境中泛化。实验结果表明，PORTAL在数千款第一人称射击（FPS）游戏中展现出卓越效能，相较于传统方法，在开发效率、策略泛化及行为多样性方面均有显著提升。PORTAL标志着游戏AI开发的一大进步，为创建能在数千款商业视频游戏中运行、且开发成本极低的复杂代理提供了实用解决方案。有关3D视频游戏的实验结果，请访问https://zhongwen.one/projects/portal 以获得最佳观看体验。

English

We present PORTAL, a novel framework for developing artificial intelligence agents capable of playing thousands of 3D video games through language-guided policy generation. By transforming decision-making problems into language modeling tasks, our approach leverages large language models (LLMs) to generate behavior trees represented in domain-specific language (DSL). This method eliminates the computational burden associated with traditional reinforcement learning approaches while preserving strategic depth and rapid adaptability. Our framework introduces a hybrid policy structure that combines rule-based nodes with neural network components, enabling both high-level strategic reasoning and precise low-level control. A dual-feedback mechanism incorporating quantitative game metrics and vision-language model analysis facilitates iterative policy improvement at both tactical and strategic levels. The resulting policies are instantaneously deployable, human-interpretable, and capable of generalizing across diverse gaming environments. Experimental results demonstrate PORTAL's effectiveness across thousands of first-person shooter (FPS) games, showcasing significant improvements in development efficiency, policy generalization, and behavior diversity compared to traditional approaches. PORTAL represents a significant advancement in game AI development, offering a practical solution for creating sophisticated agents that can operate across thousands of commercial video games with minimal development overhead. Experiment results on the 3D video games are best viewed on https://zhongwen.one/projects/portal .