# Multi-level Explanation of Deep Reinforcement Learning-based Scheduling

arXiv: https://arxiv.org/abs/2209.09645 · HTML: https://mlsanity.com/paper/2209.09645/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 18 Sep 2022.

## Builds on (most cited first, 11 of 11)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [Learning to Perform Local Rewriting for Combinatorial Optimization](https://mlsanity.com/paper/1810.00337/) (2018)
- [Explainable Machine Learning for Scientific Insights and Discoveries](https://mlsanity.com/paper/1905.08883/) (2019)
- [Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning](https://mlsanity.com/paper/2010.12367/) (2020)
- [Learning Scheduling Algorithms for Data Processing Clusters](https://mlsanity.com/paper/1810.01963/) (2018)
- [Manufacturing Dispatching using Reinforcement and Transfer Learning](https://mlsanity.com/paper/1910.02035/) (2019)

## Abstract (arXiv)

Dependency-aware job scheduling in the cluster is NP-hard. Recent work shows that Deep Reinforcement Learning (DRL) is capable of solving it. It is difficult for the administrator to understand the DRL-based policy even though it achieves remarkable performance gain. Therefore the complex model-based scheduler is not easy to gain trust in the system where simplicity is favored. In this paper, we give the multi-level explanation framework to interpret the policy of DRL-based scheduling. We dissect its decision-making process to job level and task level and approximate each level with interpretable models and rules, which align with operational practices. We show that the framework gives the system administrator insights into the state-of-the-art scheduler and reveals the robustness issue in regards to its behavior pattern.