PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Light, Jonathan, Xing, Sixue, Liu, Yuanzhe, Chen, Weiqin, Cai, Min, Chen, Xiusi, Wang, Guanzhi, Cheng, Wei, Yue, Yisong, Hu, Ziniu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929603776348160
author Light, Jonathan
Xing, Sixue
Liu, Yuanzhe
Chen, Weiqin
Cai, Min
Chen, Xiusi
Wang, Guanzhi
Cheng, Wei
Yue, Yisong
Hu, Ziniu
author_facet Light, Jonathan
Xing, Sixue
Liu, Yuanzhe
Chen, Weiqin
Cai, Min
Chen, Xiusi
Wang, Guanzhi
Cheng, Wei
Yue, Yisong
Hu, Ziniu
contents Effective extraction of the world knowledge in LLMs for complex decision-making tasks remains a challenge. We propose a framework PIANIST for decomposing the world model into seven intuitive components conducive to zero-shot LLM generation. Given only the natural language description of the game and how input observations are formatted, our method can generate a working world model for fast and efficient MCTS simulation. We show that our method works well on two different games that challenge the planning and decision making skills of the agent for both language and non-language based action taking, without any training on domain-specific training data or explicitly defined world model.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15998
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making
Light, Jonathan
Xing, Sixue
Liu, Yuanzhe
Chen, Weiqin
Cai, Min
Chen, Xiusi
Wang, Guanzhi
Cheng, Wei
Yue, Yisong
Hu, Ziniu
Artificial Intelligence
Machine Learning
Multiagent Systems
Effective extraction of the world knowledge in LLMs for complex decision-making tasks remains a challenge. We propose a framework PIANIST for decomposing the world model into seven intuitive components conducive to zero-shot LLM generation. Given only the natural language description of the game and how input observations are formatted, our method can generate a working world model for fast and efficient MCTS simulation. We show that our method works well on two different games that challenge the planning and decision making skills of the agent for both language and non-language based action taking, without any training on domain-specific training data or explicitly defined world model.
title PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making
topic Artificial Intelligence
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2411.15998