Scaling Strategy, Not Compute: A Stand-Alone, Open-Source StarCraft II Benchmark for Accessible Reinforcement Learning Research

TL;DR

This paper introduces the Two-Bridge Map Suite, an open-source, intermediate benchmark for reinforcement learning in StarCraft II that isolates core tactical skills without full-game complexity, facilitating accessible research.

Contribution

It presents a novel intermediate benchmark environment for StarCraft II that simplifies the game to core skills, enabling efficient RL research under realistic compute constraints.

Findings

Agents learn coherent maneuvering behaviors

Benchmark is lightweight and easy to adopt

Facilitates RL research with reduced complexity

Abstract

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.