DeepAI AI Chat
Log In Sign Up

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

by   Yuya Maruyama, et al.
Keio University

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.


page 1

page 3

page 4

page 5

page 6

page 8


Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning

Deep reinforcement learning (RL) has recently led to many breakthroughs ...

Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning

Deep reinforcement learning (DRL) has great potential for acquiring the ...

Embedding Human Knowledge in Deep Neural Network via Attention Map

Human-in-the-loop (HITL), which introduces human knowledge to machine le...

Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition

In this paper we propose an extension of the Attention Branch Network (A...

DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation

Traffic accident anticipation aims to accurately and promptly predict th...

Branch Prediction as a Reinforcement Learning Problem: Why, How and Case Studies

Recent years have seen stagnating improvements to branch predictor (BP) ...

Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning

In this paper we introduce the first reinforcement learning (RL) based r...