Enhancing Agent Learning through World Dynamics Modeling

Zhiyuan Sun, Haochen Shi, Marc-Alexandre Côté, Glen Berseth, Xingdi Yuan, Bang Liu


Abstract
Large language models (LLMs), trained on vast amounts of internet data, have developed a broad understanding of the world, enhancing the decision-making capabilities of embodied agents. This success is largely due to the comprehensive and in-depth domain knowledge within their training datasets. However, the extent of this knowledge can vary across different domains, and existing methods often assume that LLMs have a complete understanding of their environment, overlooking potential gaps in their grasp of actual world dynamics. To address this gap, we introduce Discover, Verify, and Evolve (DiVE), a framework that discovers world dynamics from a small number of demonstrations, verifies the correctness of these dynamics, and evolves new, advanced dynamics tailored to the current situation. Through extensive evaluations, we analyze the impact of each component on performance and compare the automatically generated dynamics from with human-annotated world dynamics. Our results demonstrate that LLMs guided by can make better decisions, achieving rewards comparable to human players in the Crafter environment.
Anthology ID:
2024.findings-emnlp.202
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3534–3568
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.202
DOI:
Bibkey:
Cite (ACL):
Zhiyuan Sun, Haochen Shi, Marc-Alexandre Côté, Glen Berseth, Xingdi Yuan, and Bang Liu. 2024. Enhancing Agent Learning through World Dynamics Modeling. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 3534–3568, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Enhancing Agent Learning through World Dynamics Modeling (Sun et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.202.pdf