Paper ID: 2208.08613

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

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

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.

Submitted: Aug 18, 2022