Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Attributation Analysis of Reinforcement Learning Based Highway Driver

Version 1 : Received: 13 September 2022 / Approved: 14 September 2022 / Online: 14 September 2022 (08:13:44 CEST)

A peer-reviewed article of this Preprint also exists.

Pankiewicz, N.; Kowalczyk, P. Attributation Analysis of Reinforcement Learning-Based Highway Driver. Electronics 2022, 11, 3599. Pankiewicz, N.; Kowalczyk, P. Attributation Analysis of Reinforcement Learning-Based Highway Driver. Electronics 2022, 11, 3599.

Abstract

While machine learning models are powering more and more everyday devices, there is a growing need for explaining them. This especially applies to the use of Deep Reinforcement Learning in solutions that require security, such as vehicle motion planning. In this paper, we propose a method of understanding what the RL agent’s decision is based on. The method relies on conducting statistical analysis on a massive set of state-decisions samples. It indicates which input features have an impact on the agent’s decision and the relationships between decisions, the significance of the input features, and their values. The method allows us for determining whether the process of making a decision by the agent is coherent with human intuition and what contradicts it. We applied the proposed method to the RL motion planning agent which is supposed to drive a vehicle safely and efficiently on a highway. We find out that making such analysis allows for a better understanding agent’s decisions, inspecting its behavior, debugging the ANN model, and verifying the correctness of input values, which increases its credibility.

Keywords

Autonomous Vehicles; Reinforcement Learning; Explainable Reinforcement Learning; XRL

Subject

Computer Science and Mathematics, Artificial Intelligence and Machine Learning

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.