{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T03:02:01Z","timestamp":1769914921351,"version":"3.49.0"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021QY0500"],"award-info":[{"award-number":["2021QY0500"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Dependable and Secure Comput."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tdsc.2024.3518500","type":"journal-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T19:37:28Z","timestamp":1734377848000},"page":"2443-2459","source":"Crossref","is-referenced-by-count":5,"title":["APRIL: Towards Scalable and Transferable Autonomous Penetration Testing in Large Action Space via Action Embedding"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9686-3836","authenticated-orcid":false,"given":"Shicheng","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9506-6903","authenticated-orcid":false,"given":"Jingju","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8502-9907","authenticated-orcid":false,"given":"Yuliang","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6109-6737","authenticated-orcid":false,"given":"Jiahai","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Network Sciences and Cyberspace and the Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4400-4295","authenticated-orcid":false,"given":"Dongdong","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3570-2132","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shulong","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05732-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4253139"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"ref5","article-title":"Autonomous penetration testing using reinforcement learning","author":"Schwartz","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1049\/ise2.12107"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSPW51379.2020.00010"},{"key":"ref8","article-title":"Deep hierarchical reinforcement agents for automated penetration testing","author":"Tran","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-3380-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.103055"},{"key":"ref11","article-title":"Deep reinforcement learning in large discrete action spaces","author":"Dulac-Arnold","year":"2015"},{"key":"ref12","article-title":"Learning action-transferable policy with action embedding","author":"Chen","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.59"},{"key":"ref14","article-title":"Building computer network attacks","author":"Futoransky","year":"2010"},{"issue":"12","key":"ref15","first-page":"21","article-title":"Attack trees","volume":"24","author":"Schneier","year":"1999","journal-title":"Dr. Dobb\u2019s J."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SECPRI.2002.1004377"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref19","article-title":"NASim: Network attack simulator","author":"Schwartz","year":"2019"},{"key":"ref20","article-title":"Cyberbattlesim","year":"2021"},{"key":"ref21","article-title":"Deepexploit","author":"Takaesu","year":"2018"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2020.102108"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3160792"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8363"},{"key":"ref26","article-title":"MITRE ATT&CK\u00ae: Design and philosophy","author":"Strom","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108194"},{"key":"ref29","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref30","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref31","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref34","article-title":"CyGIL: A cyber gym for training autonomous agents over emulated network systems","author":"Li","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976465.72"},{"key":"ref36","first-page":"6131","article-title":"SUNRISE: A simple unified framework for ensemble learning in deep reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103500"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3207619"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3124337"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASE56229.2023.00126"},{"key":"ref42","article-title":"A definition of continual reinforcement learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Abel"},{"key":"ref43","first-page":"1","article-title":"Understanding domain randomization for sim-to-real transfer","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10270-022-01075-0"}],"container-title":["IEEE Transactions on Dependable and Secure Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8858\/10992672\/10804006.pdf?arnumber=10804006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T17:35:38Z","timestamp":1747330538000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10804006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tdsc.2024.3518500","relation":{},"ISSN":["1545-5971","1941-0018","2160-9209"],"issn-type":[{"value":"1545-5971","type":"print"},{"value":"1941-0018","type":"electronic"},{"value":"2160-9209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}