航海者：具有大型语言模型的开放式具身代理

摘要

我们介绍了Voyager，这是第一个由LLM驱动的基于Minecraft的具身式终身学习代理，它在不需要人类干预的情况下持续探索世界、获得多样化技能，并进行新颖发现。Voyager由三个关键组件组成：1）最大化探索的自动课程设置，2）用于存储和检索复杂行为的不断增长的可执行代码技能库，以及3）结合环境反馈、执行错误和自我验证的新的迭代提示机制，用于程序改进。Voyager通过黑盒查询与GPT-4进行交互，从而避免了对模型参数进行微调的需要。Voyager开发的技能具有时间上的延伸性、可解释性和组合性，这加速了代理的能力并减轻了灾难性遗忘。从经验上看，Voyager展现出强大的上下文终身学习能力，并在玩Minecraft方面表现出色。它获得了比之前最先进技术更多的独特物品（3.3倍）、行进距离更长（2.3倍），并且解锁关键技术树里程碑的速度高达之前的15.3倍。Voyager能够在新的Minecraft世界中利用学到的技能库从零开始解决新任务，而其他技术则难以泛化。我们在https://voyager.minedojo.org/开放了完整的代码库和提示。

English

We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The skills developed by Voyager are temporally extended, interpretable, and compositional, which compounds the agent's abilities rapidly and alleviates catastrophic forgetting. Empirically, Voyager shows strong in-context lifelong learning capability and exhibits exceptional proficiency in playing Minecraft. It obtains 3.3x more unique items, travels 2.3x longer distances, and unlocks key tech tree milestones up to 15.3x faster than prior SOTA. Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize. We open-source our full codebase and prompts at https://voyager.minedojo.org/.

航海者：具有大型语言模型的开放式具身代理

Voyager: An Open-Ended Embodied Agent with Large Language Models

摘要

Support