Towards Future-Based Explanations for Deep RL Network Controllers
Pages 100 - 102
Abstract
Lack of explainability is hindering the practical adoption of high-performance Deep Reinforcement Learning (DRL) controllers. Prior work focused on explaining the controller by identifying salient features of the controller's input. However, these feature-based methods focus solely on inputs and do not fully explain the controller's policy. In this paper, we put forward future-based explainers as an essential tool for providing insights into the controller's decision-making process and, thereby, facilitating the practical deployment of DRL controllers. We highlight two applications of futurebased explainers in the networking domain: online safety assurance and guided controller design. Finally, we provide a roadmap for the practical development and deployment of future-based explainers for DRL network controllers.
References
[1]
Nadia Burkart and Marco F Huber. A survey on the explainability of supervised machine learning. Journal of Artificial Intelligence Research, 70:245--317, 2021.
[2]
Francisco Cruz, Richard Dazeley, Peter Vamplew, and Ithan Moreira. Explainable robotic systems: Understanding goal-driven actions in a reinforcement learning scenario. Neural Computing and Applications, pages 1--18, 2021.
[3]
Arthur S Jacobs, Roman Beltiukov, Walter Willinger, Ronaldo A Ferreira, Arpit Gupta, and Lisandro Z Granville. Ai/ml for network security: The emperor has no clothes. In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pages 1537--1551, 2022.
[4]
Zoe Juozapaitis, Anurag Koul, Alan Fern, Martin Erwig, and Finale Doshi-Velez. Explainable reinforcement learning via reward decomposition. In IJCAI/ECAI Workshop on explainable artificial intelligence, 2019.
[5]
Zili Meng, Minhu Wang, Jiasong Bai, Mingwei Xu, Hongzi Mao, and Hongxin Hu. Interpreting deep learning-based networking systems. In Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication, pages 154--171, 2020.
[6]
Noga H Rotman, Michael Schapira, and Aviv Tamar. Online safety assurance for learning-augmented systems. In Proceedings of the 19th ACM Workshop on Hot Topics in Networks, pages 88--95, 2020.
[7]
Dylan Slack, Anna Hilgard, Sameer Singh, and Himabindu Lakkaraju. Reliable post hoc explanations: Modeling uncertainty in explainability. Advances in neural information processing systems, 34:9391--9404, 2021.
[8]
Dylan Slack, Sophie Hilgard, Emily Jia, Sameer Singh, and Himabindu Lakkaraju. Fooling lime and shap: Adversarial attacks on post hoc explanation methods. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pages 180--186, 2020.
Recommendations
Practical Control Design for the Deep Learning Age: Distillation of Deep RL-Based Controllers
2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton)Deep Reinforcement Learning (RL) methods produce often performance-leading controllers. Yet, in many applications (e.g., when safety and assurance are critical), they cannot be deployed. Deep Neural Nets (DNN) controllers are nearly impossible to verify ...
Designing PSO-Based PI-type Fuzzy Logic Controllers: A Typical Application to Load-Frequency Control Strategy of an Interconnected Hydropower System
ICACR 2019: Proceedings of the 2019 3rd International Conference on Automation, Control and RobotsRecently, a fuzzy logic technique - based control strategy has become one of the most efficient control schemes in dealing with complicated and nonlinear control systems. The working principle of a fuzzy logic controller (FLC) is based on experiences of ...
Control of a hydrolyzer in an oleochemical plant using neural network based controllers
Hydrolyzer is a commonly found unit operation in the splitting of crude palm oil into fatty acids and glycerol in the oleochemical industry of Malaysia. The control of this hydrolyzer has to be done carefully since efficiency in the control of this unit ...
Comments
Information & Contributors
Information
Published In
Copyright © 2023 Copyright is held by the owner/author(s).
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 02 October 2023
Published in SIGMETRICS Volume 51, Issue 2
Check for updates
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 51Total Downloads
- Downloads (Last 12 months)47
- Downloads (Last 6 weeks)7
Reflects downloads up to 09 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in