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.
@article{arxiv.2411.15998,
title = {PIANIST: Learning Partially Observable World Models with LLMs for Multi-Agent Decision Making},
author = {Jonathan Light and Sixue Xing and Yuanzhe Liu and Weiqin Chen and Min Cai and Xiusi Chen and Guanzhi Wang and Wei Cheng and Yisong Yue and Ziniu Hu},
journal= {arXiv preprint arXiv:2411.15998},
year = {2024}
}
Comments
Published at Language Gamification Workshop 2024 @ NeurIPS