Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908547303866368 |
|---|---|
| author | Sasso, Remo Conserva, Michelangelo Jeurissen, Dominik Rauber, Paulo |
| author_facet | Sasso, Remo Conserva, Michelangelo Jeurissen, Dominik Rauber, Paulo |
| contents | While reinforcement learning from scratch has shown impressive results in solving sequential decision-making tasks with efficient simulators, real-world applications with expensive interactions require more sample-efficient agents. Foundation models (FMs) are natural candidates to improve sample efficiency as they possess broad knowledge and reasoning capabilities, but it is yet unclear how to effectively integrate them into the reinforcement learning framework. In this paper, we anticipate and, most importantly, evaluate two promising strategies. First, we consider the use of foundation world models (FWMs) that exploit the prior knowledge of FMs to enable training and evaluating agents with simulated interactions. Second, we consider the use of foundation agents (FAs) that exploit the reasoning capabilities of FMs for decision-making. We evaluate both approaches empirically in a family of grid-world environments that are suitable for the current generation of large language models (LLMs). Our results suggest that improvements in LLMs already translate into better FWMs and FAs; that FAs based on current LLMs can already provide excellent policies for sufficiently simple environments; and that the coupling of FWMs and reinforcement learning agents is highly promising for more complex settings with partial observability and stochastic elements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15915 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds Sasso, Remo Conserva, Michelangelo Jeurissen, Dominik Rauber, Paulo Machine Learning Artificial Intelligence 68T05 I.2.6; I.2.8 While reinforcement learning from scratch has shown impressive results in solving sequential decision-making tasks with efficient simulators, real-world applications with expensive interactions require more sample-efficient agents. Foundation models (FMs) are natural candidates to improve sample efficiency as they possess broad knowledge and reasoning capabilities, but it is yet unclear how to effectively integrate them into the reinforcement learning framework. In this paper, we anticipate and, most importantly, evaluate two promising strategies. First, we consider the use of foundation world models (FWMs) that exploit the prior knowledge of FMs to enable training and evaluating agents with simulated interactions. Second, we consider the use of foundation agents (FAs) that exploit the reasoning capabilities of FMs for decision-making. We evaluate both approaches empirically in a family of grid-world environments that are suitable for the current generation of large language models (LLMs). Our results suggest that improvements in LLMs already translate into better FWMs and FAs; that FAs based on current LLMs can already provide excellent policies for sufficiently simple environments; and that the coupling of FWMs and reinforcement learning agents is highly promising for more complex settings with partial observability and stochastic elements. |
| title | Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds |
| topic | Machine Learning Artificial Intelligence 68T05 I.2.6; I.2.8 |
| url | https://arxiv.org/abs/2509.15915 |