Scaling Strategy, Not Compute: A Stand-Alone, Open-Source StarCraft II Benchmark for Accessible Reinforcement Learning Research
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918376055504896 |
|---|---|
| author | Panda, Sourav Kale, Shreyash Ambadkar, Tanmay Verma, Abhinav Dodge, Jonathan |
| author_facet | Panda, Sourav Kale, Shreyash Ambadkar, Tanmay Verma, Abhinav Dodge, Jonathan |
| contents | The research community lacks a middle ground between StarCraft IIs full game and its mini-games. The full-games 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06608 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Scaling Strategy, Not Compute: A Stand-Alone, Open-Source StarCraft II Benchmark for Accessible Reinforcement Learning Research Panda, Sourav Kale, Shreyash Ambadkar, Tanmay Verma, Abhinav Dodge, Jonathan Artificial Intelligence Machine Learning The research community lacks a middle ground between StarCraft IIs full game and its mini-games. The full-games 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. |
| title | Scaling Strategy, Not Compute: A Stand-Alone, Open-Source StarCraft II Benchmark for Accessible Reinforcement Learning Research |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.06608 |