{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T08:12:26Z","timestamp":1779264746186,"version":"3.51.4"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neunet.2026.109107","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:04:30Z","timestamp":1778756670000},"page":"109107","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MaskCtrl: Training mask networks as self-explainable and performant controllers via deep reinforcement learning"],"prefix":"10.1016","volume":"203","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0177-4901","authenticated-orcid":false,"given":"Shi","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3578-7432","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dapeng","family":"Zhi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3241-0023","authenticated-orcid":false,"given":"Peixin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109107_bib0001","series-title":"ICLR","article-title":"Explain yourself, briefly! self-explaining neural networks with concise sufficient reasons","author":"Bassan","year":"2025"},{"key":"10.1016\/j.neunet.2026.109107_bib0002","series-title":"ICML","first-page":"2003","article-title":"Explaining reinforcement learning with shapley values","author":"Beechey","year":"2023"},{"key":"10.1016\/j.neunet.2026.109107_bib0003","series-title":"AAAI","first-page":"22857","article-title":"Improving autonomous separation assurance through distributed reinforcement learning with attention networks","volume":"vol. 38","author":"Brittain","year":"2024"},{"key":"10.1016\/j.neunet.2026.109107_bib0004","series-title":"CVPR","first-page":"3511","article-title":"Trustworthy multi-UAV collaboration: A self-supervised framework for explainable and adversarially robust decision-making","author":"Chen","year":"2025"},{"key":"10.1016\/j.neunet.2026.109107_bib0005","first-page":"62457","article-title":"Statemask: Explaining deep reinforcement learning through state mask","volume":"36","author":"Cheng","year":"2023","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109107_bib0006","series-title":"ICML","first-page":"8203","article-title":"Rice: Breaking through the training bottlenecks of reinforcement learning with explanation","author":"Cheng","year":"2024"},{"key":"10.1016\/j.neunet.2026.109107_bib0007","unstructured":"Cheng, Z., Yu, J., & Xing, X. (2025). A survey on explainable deep reinforcement learning. arXiv: 2502.06869."},{"key":"10.1016\/j.neunet.2026.109107_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2023.104057","article-title":"Evolving interpretable decision trees for reinforcement learning","volume":"327","author":"Costa","year":"2024","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109107_bib0009","series-title":"Proceedings of the 2022\u202fAAAI\/ACM conference on AI, ethics, and society","first-page":"203","article-title":"Fairness via explanation quality: Evaluating disparities in the quality of post hoc explanations","author":"Dai","year":"2022"},{"issue":"3","key":"10.1016\/j.neunet.2026.109107_bib0010","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1175\/1520-0493(2001)129<0540:EDAASM>2.0.CO;2","article-title":"Euclidean distance as a similarity metric for principal component analysis","volume":"129","author":"Elmore","year":"2001","journal-title":"Monthly Weather Review"},{"key":"10.1016\/j.neunet.2026.109107_bib0011","series-title":"Learning explainable models using attribution priors","author":"Erion","year":"2019"},{"key":"10.1016\/j.neunet.2026.109107_bib0012","series-title":"ICCV","first-page":"3429","article-title":"Interpretable explanations of black boxes by meaningful perturbation","author":"Fong","year":"2017"},{"key":"10.1016\/j.neunet.2026.109107_bib0013","series-title":"ICML","first-page":"1792","article-title":"Visualizing and understanding atari agents","author":"Greydanus","year":"2018"},{"key":"10.1016\/j.neunet.2026.109107_bib0014","series-title":"ICAIF","first-page":"1","article-title":"Explainable deep reinforcement learning for portfolio management: An empirical approach","author":"Guan","year":"2021"},{"key":"10.1016\/j.neunet.2026.109107_bib0015","series-title":"DASC","first-page":"1","article-title":"Explainable deep reinforcement learning for aircraft separation assurance","author":"Guo","year":"2022"},{"key":"10.1016\/j.neunet.2026.109107_bib0016","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1109\/OJITS.2021.3118972","article-title":"Adversarial attacks and defense in deep reinforcement learning (DRL)-based traffic signal controllers","volume":"2","author":"Haydari","year":"2021","journal-title":"IEEE Open Journal of Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.109107_bib0017","doi-asserted-by":"crossref","first-page":"4381","DOI":"10.1109\/TIV.2023.3296227","article-title":"Robust adversarial attacks detection based on explainable deep reinforcement learning for uav guidance and planning","volume":"8","author":"Hickling","year":"2023","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"issue":"2","key":"10.1016\/j.neunet.2026.109107_bib0018","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/TAI.2021.3111139","article-title":"Challenges and countermeasures for adversarial attacks on deep reinforcement learning","volume":"3","author":"Ilahi","year":"2021","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2026.109107_bib0019","series-title":"AIES","first-page":"144","article-title":"Transparency and explanation in deep reinforcement learning neural networks","author":"Iyer","year":"2018"},{"key":"10.1016\/j.neunet.2026.109107_bib0020","series-title":"CAV","first-page":"193","article-title":"Trainify: A cegar-driven training and verification framework for safe deep reinforcement learning","author":"Jin","year":"2022"},{"key":"10.1016\/j.neunet.2026.109107_bib0021","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109107_bib0022","series-title":"ICLR","article-title":"Contrastive explanations for reinforcement learning via embedded self predictions","author":"Lin","year":"2021"},{"key":"10.1016\/j.neunet.2026.109107_bib0023","series-title":"ECML-KDD","first-page":"414","article-title":"Toward interpretable deep reinforcement learning with linear model u-trees","author":"Liu","year":"2018"},{"key":"10.1016\/j.neunet.2026.109107_bib0024","unstructured":"Lundberg, S. M., Erion, G. G., & Lee, S.-I. (2018). Consistent individualized feature attribution for tree ensembles. arXiv."},{"key":"10.1016\/j.neunet.2026.109107_bib0025","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109107_bib0026","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013). Playing atari with deep reinforcement learning. arXiv."},{"key":"10.1016\/j.neunet.2026.109107_bib0027","article-title":"Towards interpretable reinforcement learning using attention augmented agents","volume":"32","author":"Mott","year":"2019","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2026.109107_bib0028","unstructured":"OpenAI (2024). Gym. https:\/\/www.gymlibrary.dev\/."},{"key":"10.1016\/j.neunet.2026.109107_bib0029","series-title":"ICASSP","first-page":"3501","article-title":"Identifying critical states via action consensus","author":"Peng","year":"2026"},{"key":"10.1016\/j.neunet.2026.109107_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107749","article-title":"Ata: An abstract-train-abstract approach for explanation-friendly deep reinforcement learning","author":"Peng","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109107_bib0031","unstructured":"Petsiuk, V., Das, A., & Saenko, K. (2018). Rise: Randomized input sampling for explanation of black-box models. arXiv."},{"key":"10.1016\/j.neunet.2026.109107_bib0032","series-title":"ICLR","article-title":"Explain your move: Understanding agent actions using specific and relevant feature attribution","author":"Puri","year":"2019"},{"key":"10.1016\/j.neunet.2026.109107_bib0033","series-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","first-page":"1135","article-title":"\u201c Why should I trust you?\u201d Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"key":"10.1016\/j.neunet.2026.109107_bib0034","series-title":"CIKM","first-page":"1661","article-title":"Xpm: An explainable deep reinforcement learning framework for portfolio management","author":"Shi","year":"2021"},{"key":"10.1016\/j.neunet.2026.109107_bib0035","series-title":"ICML","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"Sundararajan","year":"2017"},{"key":"10.1016\/j.neunet.2026.109107_bib0036","series-title":"Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"6073","article-title":"Xrl-bench: A benchmark for evaluating and comparing explainable reinforcement learning techniques","author":"Xiong","year":"2024"},{"key":"10.1016\/j.neunet.2026.109107_bib0037","series-title":"ICLR","article-title":"Deep reinforcement learning with relational inductive biases","author":"Zambaldi","year":"2019"},{"key":"10.1016\/j.neunet.2026.109107_bib0038","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Duan, T., Lin, Z., Huang, D., Fang, Z., Sun, Z., Xiong, L., Liang, H., Cui, H., & Cui, Y. (2025). State-aware perturbation optimization for robust deep reinforcement learning. arXiv.","DOI":"10.36227\/techrxiv.174320032.22893766\/v1"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005678?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026005678?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T07:46:00Z","timestamp":1779263160000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026005678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":38,"alternative-id":["S0893608026005678"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109107","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MaskCtrl: Training mask networks as self-explainable and performant controllers via deep reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109107","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109107"}}