Visual reinforcement learning (RL) suffers from poor sample efficiency due to high-dimensional observations in complex tasks. While existing works have shown that vision-language models (VLMs) can assist RL, they often focus on knowledge distillation from the VLM to RL, overlooking the potential of RL-generated interaction data to enhance the VLM. To address this, we propose COVR, a collaborative optimization framework that enables the mutual enhancement of the VLM and RL policies. Specifically, COVR fine-tunes the VLM with RL-generated data to enhance the semantic reasoning ability consistent with the target task, and uses the enhanced VLM to further guide policy learning via action priors. To improve fine-tuning efficiency, we introduce two key modules: (1) an Exploration-Driven Dynamic Filter module that preserves valuable exploration samples using adaptive thresholds based on the degree of exploration, and (2) a Return-Aware Adaptive Loss Weight module that improves the stability of training by quantifying the inconsistency of sampling actions via return signals of RL. We further design a progressive fine-tuning strategy to reduce resource consumption. Extensive experiments show that COVR achieves strong performance across various challenging visual control tasks.
@article{arxiv.2601.06122,
title = {COVR:Collaborative Optimization of VLMs and RL Agent for Visual-Based Control},
author = {Canming Xia and Peixi Peng and Guang Tan and Zhan Su and Haoran Xu and Zhenxian Liu and Luntong Li},
journal= {arXiv preprint arXiv:2601.06122},
year = {2026}
}
Comments
The paper was accepted by the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26)