On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning

Mauricio Gruppi, Soham Dan, Keerthiram Murugesan, Subhajit Chaudhury


Abstract
Text-based reinforcement learning involves an agent interacting with a fictional environment using observed text and admissible actions in natural language to complete a task. Previous works have shown that agents can succeed in text-based interactive environments even in the complete absence of semantic understanding or other linguistic capabilities. The success of these agents in playing such games suggests that semantic understanding may not be important for the task. This raises an important question about the benefits of LMs in guiding the agents through the game states. In this work, we show that rich semantic understanding leads to efficient training of text-based RL agents. Moreover, we describe the occurrence of semantic degeneration as a consequence of inappropriate fine-tuning of language models in text-based reinforcement learning (TBRL). Specifically, we describe the shift in the semantic representation of words in the LM, as well as how it affects the performance of the agent in tasks that are semantically similar to the training games. These results may help develop better strategies to fine-tune agents in text-based RL scenarios.
Anthology ID:
2025.coling-main.445
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6649–6658
Language:
URL:
https://aclanthology.org/2025.coling-main.445/
DOI:
Bibkey:
Cite (ACL):
Mauricio Gruppi, Soham Dan, Keerthiram Murugesan, and Subhajit Chaudhury. 2025. On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning. In Proceedings of the 31st International Conference on Computational Linguistics, pages 6649–6658, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning (Gruppi et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.445.pdf