XDQN: Inherently Interpretable DQN through Mimicking
Not on the map. Why?
Abstract (arXiv)
Although deep reinforcement learning (DRL) methods have been successfully applied in challenging tasks, their application in real-world operational settings is challenged by methods' limited ability to provide explanations. Among the paradigms for explainability in DRL is the interpretable box design paradigm, where interpretable models substitute inner constituent models of the DRL method, thus making the DRL method "inherently" interpretable. In this paper we explore this paradigm and we propose XDQN, an explainable variation of DQN, which uses an interpretable policy model trained through mimicking. XDQN is challenged in a complex, real-world operational multi-agent problem, where agents are independent learners solving congestion problems. Specifically, XDQN is evaluated in three MARL scenarios, pertaining to the demand-capacity balancing problem of air traffic management. XDQN achieves performance similar to that of DQN, while its abilities to provide global models' interpretations and interpretations of local decisions are demonstrated.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 8 Jan 2023.
Builds on
22 of 37 references.
References · 22
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
- 2015Prioritized Experience Replaycited by 1,070
- 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
- 2013Do Deep Nets Really Need to be Deep?cited by 466
- 2015Policy Distillationcited by 414
- 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
- 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
- 2019Interpretable machine learning: definitions, methods, and applicationscited by 303
- 2017Distilling a Neural Network Into a Soft Decision Treecited by 230
- 2019Explainable Reinforcement Learning Through a Causal Lenscited by 177
10 more
- 2018Verifiable Reinforcement Learning via Policy Extractioncited by 176
- 2020Principles and Practice of Explainable Machine Learningcited by 99
- 2019Towards Interpretable Reinforcement Learning Using Attention Augmented Agentscited by 82
- 2018Toward Interpretable Deep Reinforcement Learning with Linear Model U-Treescited by 65
- 2019DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systemscited by 44
- 2019Generation of Policy-Level Explanations for Reinforcement Learningcited by 37
- 2019Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policycited by 29
- 2018Towards Better Interpretability in Deep Q-Networkscited by 22
- 2019Resolving Congestions in the Air Traffic Management Domain via Multiagent Reinforcement Learning Methodscited by 2
- 2021Tree-based Focused Web Crawling with Reinforcement Learningcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.