GIST: Guided Interpretable Large Language Model Strategy Transfer for Multi-Task Reinforcement Learning

Bo Zhao, Zhuo TangICASSP 2025 · OpenReview

Abstract

Multi-task reinforcement learning (MTRL) presents critical challenges, such as the complexities of task-switching and maintaining knowledge retention across various tasks, especially within control tasks. These challenges frequently result in sub-optimal decision-making and catastrophic forgetting during task transitions. To mitigate these challenges, we introduce a framework that leverages large language models for strategic guidance, optimizing decision-making and action selection. The framework integrates a Kolmogorov-Arnold Network to ensure interpretability via symbolic regression, enabling effective strategy transfer across diverse environments. Adaptive Elastic Weight Consolidation is employed to prevent catastrophic forgetting, preserving task-specific knowledge across training. A caching mechanism reduces computational overhead linked to large language model queries, enhancing overall efficiency. Experimental evaluations indicate competitive performance, robust interpretability, and effective strategy transfer.
BibTeX
@inproceedings{zhao2025gist,
  author = {Bo Zhao and Zhuo Tang},
  title = {{GIST: Guided Interpretable Large Language Model Strategy Transfer for Multi-Task Reinforcement Learning}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2025},
  url = {https://openreview.net/forum?id=W0f1EYEG01},
}

Loading related content...

Figure