MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models

2026-08-19

AI Summary

为解决强化学习中奖励函数设计的问题，提出MLREF框架，通过模块池重用有效组件，并结合三种机制优化奖励函数。

Abstract

Reward function design remains a bottleneck in reinforcement learning. While large language models (LLMs) have enabled automated reward generation, existing methods generate and revise reward functions as monolithic programs, making it difficult to reliably preserve and reuse effective components discovered in earlier iterations, leading to unstable performance across iterations. To address this, we propose Module Level Reward Evolution Framework (MLREF). At the core of MLREF is a module pool, a persistent repository of reusable reward components. MLREF treats the module pool as the primary optimization object: the pool evolves across iterations by accumulating successful modules, refining underperforming ones, and reusing proven components; while reward functions are constructed as linear combinations of modules drawn from this pool. To drive this evolution, MLREF integrates three mechanisms: reflection-based refinement, hybrid credit assignment, and a merge strategy with rollback, which together improve the effectiveness and robustness of reward optimization. Experiments on 17 tasks show that MLREF outperforms strong baselines by 25.2% in locomotion and 6.6% in manipulation, with more stable optimization dynamics.

Problem

• reward function design
• reinforcement learning
• large language models
• module reuse
• performance instability

Innovation

• Module Level Reward Evolution Framework
• module pool
• reward function design
• large language models
• reinforcement learning