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

arXiv:2404.10174v1 Announce Type: new
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 …

abstract agent agents arxiv cs.cl effects environment environments fine-tuning interactive language language models natural natural language reinforcement reinforcement learning semantic text type understanding