航海家：具有大型語言模型的開放式具身代理程序

摘要

我們介紹了Voyager，這是第一個以LLM為動力的具體化終身學習代理人，在Minecraft中持續探索世界、獲得多樣技能並在無人干預下進行新的發現。Voyager由三個關鍵組件組成：1）最大化探索的自動課程，2）用於存儲和檢索複雜行為的可執行代碼的不斷增長技能庫，以及3）一種新的迭代提示機制，該機制融合了環境反饋、執行錯誤和自我驗證以改進程序。Voyager通過黑盒查詢與GPT-4進行交互，從而避免了對模型參數進行微調的需要。Voyager所發展的技能在時間上是延長的、可解釋的和組合的，這迅速增強了代理人的能力並減輕了災難性遺忘。從實證上看，Voyager展現了強大的上下文終身學習能力，並在玩Minecraft方面表現出色。它獲得了比先前最先進技術更多的獨特物品（3.3倍）、行進距離更長（2.3倍），並比先前最先進技術快達15.3倍的速度解鎖關鍵技術樹里程碑。Voyager能夠在新的Minecraft世界中利用所學的技能庫從頭解決新任務，而其他技術則難以泛化。我們在https://voyager.minedojo.org/上開源了完整的代碼庫和提示。

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/.

航海家：具有大型語言模型的開放式具身代理程序

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

摘要

Support