Odyssey：赋予Minecraft智能体开放世界技能
Odyssey: Empowering Minecraft Agents with Open-World Skills
AI总结：
提出Odyssey框架，通过开放世界技能库、微调LLaMA-3模型和全新能力基准，赋予Minecraft智能体长程规划与自主探索能力，有效评估LLM智能体表现。
摘要：
近期的研究深入探索了为Minecraft等开放世界环境构建通用智能体。尽管取得了令人鼓舞的成果，但现有的努力主要集中在解决基础程序化任务上，例如遵循Minecraft科技树进行材料收集和工具制作，并将ObtainDiamond任务视为最终目标。这一局限性源于智能体可用动作集合定义过于狭窄，要求它们从零开始学习有效的长程策略。因此，，在开放世界中发现多样化的游戏玩法机会变得极具挑战性。在本研究中，我们提出了Odyssey，一个新框架，赋予基于大型语言模型（LLM）的智能体开放世界技能，以探索广阔的Minecraft世界。Odyssey包含三个关键部分：（1）一个具备开放世界技能库的交互式智能体，该技能库包含4040个基础技能和183个组合技能。（2）一个微调的LLaMA-3模型，该模型在从Minecraft Wiki提取的包含39万+条指令条目的大型问答数据集上进行训练。（3）一个新的智能体能力基准，包括长程规划任务、动态即时规划任务和自主探索任务。大量实验表明，所提出的Odyssey框架能够有效评估基于LLM的智能体的不同能力。所有数据集、模型权重和代码均公开可用，以推动未来关于更先进自主智能体解决方案的研究。
英文摘要：
Recent studies have delved into constructing generalist agents for open-world environments like Minecraft. Despite the encouraging results, existing efforts mainly focus on solving basic programmatic tasks, e.g., material collection and tool-crafting following the Minecraft tech-tree, treating the ObtainDiamond task as the ultimate goal. This limitation stems from the narrowly defined set of actions available to agents, requiring them to learn effective long-horizon strategies from scratch. Consequently, discovering diverse gameplay opportunities in the open world becomes challenging. In this work, we introduce Odyssey, a new framework that empowers Large Language Model (LLM)-based agents with open-world skills to explore the vast Minecraft world. Odyssey comprises three key parts: (1) An interactive agent with an open-world skill library that consists of 40 primitive skills and 183 compositional skills. (2) A fine-tuned LLaMA-3 model trained on a large question-answering dataset with 390k+ instruction entries derived from the Minecraft Wiki. (3) A new agent capability benchmark includes the long-term planning task, the dynamic-immediate planning task, and the autonomous exploration task. Extensive experiments demonstrate that the proposed Odyssey framework can effectively evaluate different capabilities of LLM-based agents. All datasets, model weights, and code are publicly available to motivate future research on more advanced autonomous agent solutions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
