.png){kind=icon}
Return
Explaining Imitation Learning Through Frames
.png){kind=icon}
OA
AI
DOI：10.1109/MIS.2024.3404988.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
As one of the prevalent methods to achieve automation systems, imitation learning (IL) presents a promising performance in a wide range of domains. However, despite the considerable improvement in policy performance, the corresponding research on the explainability of IL models is still limited. Inspired by the recent approaches in explainable AI, we proposed a model-agnostic explaining framework for IL models called Remove and Retrain via Randomized Input Sampling for Explanation (R2RISE). R2RISE aims to explain the importance of frames with respect to the overall policy performance. It iteratively retrains the black-box IL model from the randomized masked demonstrations and uses the conventional evaluation outcome environment returns as the coefficient to build an importance map. We also conducted experiments to investigate three major questions concerning frames' importance equality, the effectiveness of the importance map, and connections in importance maps from different IL models. The result shows that R2RISE distinguishes important frames from the demonstrations effectively.
Keywords:
Computational modeling
Intelligent systems
Trajectory
Closed box
Australia
Degradation
Decision making
Journal
IF:
6.1
Papers:
1.6K
Citations:
4.5K
Organization
Cited Papers
The Clinical Efficacy of Radium-223 for Bone Metastasis in Patients with Castration-Resistant Prostate Cancer: An Italian Clinical Experience.png)
Oncology
OncologyIF0
PREAI
ShareSave no more
no more