ERFSL: An Efficient Reward Function Searcher via Large Language Models for Custom-Environment Multi-Objective Reinforcement Learning (Student Abstract)

We propose ERFSL, an efficient reward function searcher using large language models (LLMs) for custom-environment, multi-objective reinforcement learning (RL). ERFSL generates reward components based on explicit user requirements and rectifies them, and iteratively optimizes the weights of these components based on textual context. Applied to an underwater data collection RL task, ERFSL corrects reward codes with only one feedback iteration per requirement, and acquires diverse reward functions within the Pareto set. ERFSL also presents robust capability for deviated weights and small-size LLMs such as GPT-4o mini. The full-text prompts, examples of LLM-generated answers, and source code are available at https://360zmem.github.io/LLMRsearcher/.

Authors

• Guanwen Xie Massachusetts Institute of Technology
• Jingzehua Xu Massachusetts Institute of Technology
• Yiyuan Yang University of Oxford
• Yimian Ding Massachusetts Institute of Technology
• Shuai Zhang New Jersey Institute of Technology

Keywords

No keywords are indexed for this paper.