# Explaining the Decisions of Deep Policy Networks for Robotic Manipulations

arXiv: https://arxiv.org/abs/2310.19432 · HTML: https://mlsanity.com/paper/2310.19432/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 17 of 17)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer](https://mlsanity.com/paper/1609.07088/) (2016)
- [Towards Best Practice in Explaining Neural Network Decisions with LRP](https://mlsanity.com/paper/1910.09840/) (2019)
- [Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks](https://mlsanity.com/paper/1904.00605/) (2019)
- [Learning Contact-Rich Manipulation Skills with Guided Policy Search](https://mlsanity.com/paper/1501.05611/) (2015)
- [Explaining Predictions of Non-Linear Classifiers in NLP](https://mlsanity.com/paper/1606.07298/) (2016)
- [Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning](https://mlsanity.com/paper/1703.03078/) (2017)
- [An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks](https://mlsanity.com/paper/1912.05827/) (2019)

## Built on by (most cited first, 1 of 1)

- [PnPXAI: A Universal XAI Framework Providing Automatic Explanations Across Diverse Modalities and Models](https://mlsanity.com/paper/2505.10515/) (2025)

## Abstract (arXiv)

Deep policy networks enable robots to learn behaviors to solve various real-world complex tasks in an end-to-end fashion. However, they lack transparency to provide the reasons of actions. Thus, such a black-box model often results in low reliability and disruptive actions during the deployment of the robot in practice. To enhance its transparency, it is important to explain robot behaviors by considering the extent to which each input feature contributes to determining a given action. In this paper, we present an explicit analysis of deep policy models through input attribution methods to explain how and to what extent each input feature affects the decisions of the robot policy models. To this end, we present two methods for applying input attribution methods to robot policy networks: (1) we measure the importance factor of each joint torque to reflect the influence of the motor torque on the end-effector movement, and (2) we modify a relevance propagation method to handle negative inputs and outputs in deep policy networks properly. To the best of our knowledge, this is the first report to identify the dynamic changes of input attributions of multi-modal sensor inputs in deep policy networks online for robotic manipulation.