打造轻量版游戏智能体训练平台，支持快速构建通用智能体。
CrafterDojo: A Suite of Foundation Models for Building Open-Ended Embodied Agents in Crafter
- 引入视觉-语言-行为三类基础模型，实现跨模态理解与决策。
- 提供数据生成工具与基准评估，支持开放任务研究。
- 适合希望快速迭代智能体的开发者和研究者使用。
构建通用具身智能体是人工智能的核心挑战。Minecraft 拥有丰富的复杂性和互联网规模的数据，但其运行缓慢且工程开销大，不适于快速原型开发。Crafter 提供了一个轻量级替代方案，保留了 Minecraft 的关键挑战，但由于缺乏推动 Minecraft 领域进展的基础模型，其应用仍局限于狭窄任务。本文提出 CrafterDojo，一套基础模型与工具集，使 Crafter 环境成为轻量、易用、类 Minecraft 的通用具身智能体研究测试平台。CrafterDojo 引入 CrafterVPT（行为先验）、CrafterCLIP（视觉-语言对齐）和 CrafterSteve-1（指令遵循）三类模型，并提供 CrafterPlay 和 CrafterCaption 数据集生成工具、参考智能体实现、基准评估及完整开源代码库。
原文摘要 · Abstract (English)
Developing general-purpose embodied agents is a core challenge in AI. Minecraft provides rich complexity and internet-scale data, but its slow speed and engineering overhead make it unsuitable for rapid prototyping. Crafter offers a lightweight alternative that retains key challenges from Minecraft, yet its use has remained limited to narrow tasks due to the absence of foundation models that have driven progress in the Minecraft setting. In this paper, we present CrafterDojo, a suite of foundation models and tools that unlock the Crafter environment as a lightweight, prototyping-friendly, and Minecraft-like testbed for general-purpose embodied agent research. CrafterDojo addresses this by introducing CrafterVPT, CrafterCLIP, and CrafterSteve-1 for behavior priors, vision-language grounding, and instruction following, respectively. In addition, we provide toolkits for generating behavior and caption datasets (CrafterPlay and CrafterCaption), reference agent implementations, benchmark evaluations, and a complete open-source codebase.
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。