Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Shunyu, Li, Yaoru, Zhang, Kongcheng, Cui, Zhenyu, Fang, Wenkai, Zheng, Yuxuan, Zheng, Tongya, Song, Mingli
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2407.15325
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916769651752960
author Liu, Shunyu
Li, Yaoru
Zhang, Kongcheng
Cui, Zhenyu
Fang, Wenkai
Zheng, Yuxuan
Zheng, Tongya
Song, Mingli
author_facet Liu, Shunyu
Li, Yaoru
Zhang, Kongcheng
Cui, Zhenyu
Fang, Wenkai
Zheng, Yuxuan
Zheng, Tongya
Song, Mingli
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15325
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Odyssey: Empowering Minecraft Agents with Open-World Skills
Liu, Shunyu
Li, Yaoru
Zhang, Kongcheng
Cui, Zhenyu
Fang, Wenkai
Zheng, Yuxuan
Zheng, Tongya
Song, Mingli
Artificial Intelligence
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.
title Odyssey: Empowering Minecraft Agents with Open-World Skills
topic Artificial Intelligence
url https://arxiv.org/abs/2407.15325