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/.

翻译：本文介绍Voyager——首个在Minecraft中由大语言模型驱动的具身终身学习智能体，它能在无需人工干预的情况下持续探索世界、习得多样化技能并发现新知识。Voyager包含三个关键组件：1）最大化探索能力的自动课程设计；2）用于存储和检索复杂行为的可执行代码库（动态增长的技能库）；3）融合环境反馈、执行错误与自我验证的新型迭代提示机制以优化程序。Voyager通过黑盒查询与GPT-4交互，无需模型参数微调。其生成的技能具备时间延展性、可解释性和组合性，能快速增强智能体能力并缓解灾难性遗忘。实验表明，Voyager展现出强大的上下文终身学习能力与卓越的Minecraft游戏表现：相较先前最优方法，其获取独特物品数量提升3.3倍，移动距离延长2.3倍，解锁关键科技树里程碑速度提升15.3倍。Voyager能在全新Minecraft世界中利用已学技能库从头解决新任务，而其他方法难以实现泛化。我们已在https://voyager.minedojo.org/ 开源完整代码库与提示词。