为即时战略游戏研究提供中等难度基准,聚焦战术技能训练。
Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark
- 禁用资源采集与基地建造,专注远程导航和微操战斗
- 轻量级环境使智能体在低算力下学会有效作战行为
- 开源可复现,适合测试强化学习算法的实战能力
当前研究在《星际争霸2》完整游戏与微型任务之间缺乏中间层次。完整游戏状态-动作空间过大,导致奖励信号稀疏且嘈杂;而微型任务则过于简单,使智能体性能迅速饱和。这一复杂度断层阻碍了渐进式训练课程的设计,也限制了现代强化学习算法在真实算力条件下于即时战略环境中的实验。为此,我们提出两桥地图套件(Two-Bridge Map Suite),作为首个开源基准系列的首项成果,旨在填补该空白。通过禁用经济机制(如资源采集、基地建造、迷雾系统),环境聚焦于两大核心战术能力:远程导航与微操作战斗。初步实验表明,智能体可在不承担完整游戏计算成本的前提下,学会连贯的机动与交战行为。两桥以轻量级、Gym兼容形式封装于PySC2之上,地图、包装器与参考脚本全部开源,旨在推动其成为标准基准。
原文摘要 · Abstract (English)
The research community lacks a middle ground between StarCraft II full game and its mini-games. The full-game's sprawling state-action space renders reward signals sparse and noisy, but in mini-games simple agents saturate performance. This complexity gap hinders steady curriculum design and prevents researchers from experimenting with modern Reinforcement Learning algorithms in RTS environments under realistic compute budgets. To fill this gap, we present the Two-Bridge Map Suite, the first entry in an open-source benchmark series we purposely engineered as an intermediate benchmark to sit between these extremes. By disabling economy mechanics such as resource collection, base building, and fog-of-war, the environment isolates two core tactical skills: long-range navigation and micro-combat. Preliminary experiments show that agents learn coherent maneuvering and engagement behaviors without imposing full-game computational costs. Two-Bridge is released as a lightweight, Gym-compatible wrapper on top of PySC2, with maps, wrappers, and reference scripts fully open-sourced to encourage broad adoption as a standard benchmark.
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。