A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning

Understand

Large Language Models (LLMs) have shown significant potential in designing reward functions for Reinforcement Learning (RL) tasks.

• However, obtaining high-quality reward code often involves human intervention, numerous LLM queries, or repetitive RL training.
• To address these issues, we propose CARD, a LLM-driven Reward Design framework that iteratively generates and improves reward function code.
• Specifically, CARD includes a Coder that generates and verifies the code, while a Evaluator provides dynamic feedback to guide the Coder in improving the code, eliminating the need for human feedback.