{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T04:51:34Z","timestamp":1788929494765,"version":"build-2803163510"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP200103494"],"award-info":[{"award-number":["DP200103494"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tpds.2022.3218649","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:55:38Z","timestamp":1667526938000},"page":"346-357","source":"Crossref","is-referenced-by-count":7,"title":["Robustness Analysis and Enhancement of Deep Reinforcement Learning-Based Schedulers"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7749-2363","authenticated-orcid":false,"given":"Shaojun","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3119-4763","authenticated-orcid":false,"given":"Chen","family":"Wang","sequence":"additional","affiliation":[{"name":"CSIRO Data61, Eveleigh, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3090-1059","authenticated-orcid":false,"given":"Albert Y.","family":"Zomaya","sequence":"additional","affiliation":[{"name":"School of Computer Science, The University of Sydney, Camperdown, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/669"},{"key":"ref38","year":"2019"},{"key":"ref33","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014","journal-title":"arXiv 1412 6572"},{"key":"ref32","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref31","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2013","journal-title":"arXiv 1312 6199"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2020.24178"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref34","article-title":"OpenAI Gym","author":"brockman","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00021"},{"key":"ref40","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1128817.1128824"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_25"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7_19"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref15","first-page":"2040","article-title":"Robust deep reinforcement learning with adversarial attacks","author":"pattanaik","year":"2018","journal-title":"Proc Int Conf Auton Agents Multi-Agent Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2016.95"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2017.12"},{"key":"ref18","first-page":"1","article-title":"Adversarial attacks in a deep reinforcement learning based cloud scheduler","author":"zhang","year":"2020","journal-title":"Proc Model Anal Simul Comput Telecommun Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref28","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Conf Neural Informat Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00366-015-0396-z"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICAC.2006.1662383"},{"key":"ref3","article-title":"Spark: Cluster computing with working sets","author":"zaharia","year":"2010","journal-title":"Proc 2nd USENIX Conf Hot Top cloud Comput"},{"key":"ref6","first-page":"24","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","author":"ghodsi","year":"2011","journal-title":"Proc USENIX Symp Netw Syst Des Implementation"},{"key":"ref29","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref5","first-page":"81","article-title":"GRAPHENE: Packing and dependency-aware scheduling for data-parallel clusters","author":"grandl","year":"2016","journal-title":"Proc USENIX Symp on Operating System Design and Implementation"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017570"},{"key":"ref2","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00159"},{"key":"ref1","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2749473"},{"key":"ref20","article-title":"Adversarial attacks on neural network policies","author":"huang","year":"2017","journal-title":"arXiv 1702 02284"},{"key":"ref45","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","author":"boyan","year":"1993","journal-title":"Proc Conf Neural Informat Process Syst"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.11"},{"key":"ref41","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref44","year":"2022"},{"key":"ref26","first-page":"1314","article-title":"Resource allocation in the grid using reinforcement learning","author":"galstyan","year":"2004","journal-title":"Proc 3rd Int Joint Conf Auton Agents Multiagent Syst"},{"key":"ref43","first-page":"5089","article-title":"Statistically efficient off-policy policy gradients","author":"kallus","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9956797\/09937194.pdf?arnumber=9937194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T19:46:53Z","timestamp":1671479213000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9937194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":46,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2022.3218649","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,1]]}}}