arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.08613cs.RO
收藏

基于注意分支微调的深度Q网络机器人导航可视化解释

Visual Explanation of Deep Q-Network for Robot Navigation by Fine-tuning Attention Branch

Chubu University(中部大学);Keio University(庆应义塾大学)

Yuya Maruyama, Hiroshi Fukui, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, Komei Sugiura

摘要:

深度强化学习(RL)的机器人导航具有更高的性能,在复杂环境下表现良好。与此同时,深度强化学习模型的决策解释成为提高自主机器人安全性和可靠性的关键问题。在本文中,我们提出了一种基于注意力分支的深度RL模型的可视化解释方法。我们将注意力分支与预先训练好的深度强化学习模型连接起来,并以监督学习的方式将训练好的深度强化学习模型选择的动作作为正确的标签来训练注意力分支。由于注意分支被训练为输出与深度RL模型相同的结果,因此获得的注意图对应于具有更高可解释性的Agent动作。机器人导航任务的实验结果表明,所提出的方法可以产生可解释的注意力地图的视觉解释。

英文摘要:

Robot navigation with deep reinforcement learning (RL) achieves higher performance and performs well under complex environment. Meanwhile, the interpretation of the decision-making of deep RL models becomes a critical problem for more safety and reliability of autonomous robots. In this paper, we propose a visual explanation method based on an attention branch for deep RL models. We connect attention branch with pre-trained deep RL model and the attention branch is trained by using the selected action by the trained deep RL model as a correct label in a supervised learning manner. Because the attention branch is trained to output the same result as the deep RL model, the obtained attention maps are corresponding to the agent action with higher interpretability. Experimental results with robot navigation task show that the proposed method can generate interpretable attention maps for a visual explanation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑