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

• URL: http://arxiv.org/abs/2603.06608v1
• Date: Thu, 19 Feb 2026 04:13:14 GMT
• Title: Scaling Strategy, Not Compute: A Stand-Alone, Open-Source StarCraft II Benchmark for Accessible Reinforcement Learning Research
• Abstract summary: We present the Two-Bridge Map Suite, a benchmark for StarCraft IIs mini-games.<n>By disabling economy mechanics, the environment isolates two core tactical skills: long-range navigation and micro-combat.<n>Preliminary experiments show that agents learn coherent maneuvering and engagement behaviors without imposing full-game computational costs.
• Score: 2.5959683852997806
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents [5.173133826653683]
  We present TowerMind, a novel environment grounded in the tower defense subgenre of RTS games.<n>We design five benchmark levels to evaluate several widely used Large Language Models.<n>Results reveal a clear performance gap between LLMs and human experts across both capability and hallucination dimensions.
  arXiv  Detail & Related papers  (2026-01-09T16:18:08Z)
• StarCraft+: Benchmarking Multi-agent Algorithms in Adversary Paradigm [30.052231743944727]
  In this work, we establish a multi-agent algorithm-vs-algorithm environment, named StarCraft II battle arena (SC2BA)<n>Taking StarCraft as infrastructure, the SC2BA environment is specifically created for inter-algorithm adversary.<n>We benchmark classic MARL algorithms in two types of adversarial modes: dual-algorithm paired adversary and multi-algorithm mixed adversary.
  arXiv  Detail & Related papers  (2025-12-18T11:58:10Z)
• Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents [56.25101378553328]
  We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned keyboard-mouse inputs.<n>Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data.<n> Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks.
  arXiv  Detail & Related papers  (2025-10-27T17:43:51Z)
• SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks [24.84821125790223]
  Existing benchmarks for tasks like StarCraft II fail to capture the game's full complexity.<n>We present SC2Arena, a benchmark that fully supports all playable races, low-level action spaces, and optimize text-based observations to tackle spatial reasoning challenges.<n>We introduce StarEvolve, a hierarchical framework that integrates strategic planning with tactical execution.
  arXiv  Detail & Related papers  (2025-08-14T07:58:01Z)
• AVA: Attentive VLM Agent for Mastering StarCraft II [56.07921367623274]
  We introduce Attentive VLM Agent (AVA), a multimodal StarCraft II agent that aligns artificial agent perception with the human gameplay experience.<n>Our agent addresses this limitation by incorporating RGB visual inputs and natural language observations that more closely simulate human cognitive processes during gameplay.
  arXiv  Detail & Related papers  (2025-03-07T12:54:25Z)
• SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models [1.235958663217432]
  The purpose of this paper is to investigate the efficacy of large language models (LLMs) in executing real-time strategy war tasks. We introduce SwarmBrain, an embodied agent leveraging LLM for real-time strategy implementation in the StarCraft II game environment. Experimental results show the capacity of SwarmBrain to conduct economic augmentation, territorial expansion, and tactical formulation.
  arXiv  Detail & Related papers  (2024-01-31T11:14:29Z)
• SPRING: Studying the Paper and Reasoning to Play Games [102.5587155284795]
  We propose a novel approach, SPRING, to read the game's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM) In experiments, we study the quality of in-context "reasoning" induced by different forms of prompts under the setting of the Crafter open-world environment. Our experiments suggest that LLMs, when prompted with consistent chain-of-thought, have great potential in completing sophisticated high-level trajectories.
  arXiv  Detail & Related papers  (2023-05-24T18:14:35Z)
• Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II [0.0]
  We propose a neural network architecture for playing the full two-player match of StarCraft II trained with general-purpose supervised and reinforcement learning. Our implementation achieves a non-trivial performance when compared to the in-game scripted bots.
  arXiv  Detail & Related papers  (2021-09-26T20:08:10Z)
• The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors [62.9301667732188]
  We propose a second iteration of the MineRL Competition. The primary goal of the competition is to foster the development of algorithms which can efficiently leverage human demonstrations. The competition is structured into two rounds in which competitors are provided several paired versions of the dataset and environment. At the end of each round, competitors submit containerized versions of their learning algorithms to the AIcrowd platform.
  arXiv  Detail & Related papers  (2021-01-26T20:32:30Z)
• OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research [82.09426894653237]
  OpenHoldem is an integrated toolkit for large-scale imperfect-information game research using NLTH. OpenHoldem makes three main contributions to this research direction: 1) a standardized evaluation protocol for thoroughly evaluating different NLTH AIs, 2) three publicly available strong baselines for NLTH AI, and 3) an online testing platform with easy-to-use APIs for public NLTH AI evaluation.
  arXiv  Detail & Related papers  (2020-12-11T07:24:08Z)
• Efficient exploration of zero-sum stochastic games [83.28949556413717]
  We investigate the increasingly important and common game-solving setting where we do not have an explicit description of the game but only oracle access to it through gameplay. During a limited-duration learning phase, the algorithm can control the actions of both players in order to try to learn the game and how to play it well. Our motivation is to quickly learn strategies that have low exploitability in situations where evaluating the payoffs of a queried strategy profile is costly.
  arXiv  Detail & Related papers  (2020-02-24T20:30:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.