{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:26:49Z","timestamp":1777058809538,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2008265"],"award-info":[{"award-number":["2008265"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3624062.3624201","type":"proceedings-article","created":{"date-parts":[[2023,11,10]],"date-time":"2023-11-10T13:53:39Z","timestamp":1699624419000},"page":"1316-1323","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["A Reinforcement Learning Based Backfilling Strategy for HPC Batch Jobs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1366-9028","authenticated-orcid":false,"given":"Elliot","family":"Kolker-Hicks","sequence":"first","affiliation":[{"name":"University of North Carolina at Charlotte, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3115-0276","authenticated-orcid":false,"given":"Di","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of North Carolina at Charlotte, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4078-8149","authenticated-orcid":false,"given":"Dong","family":"Dai","sequence":"additional","affiliation":[{"name":"University of North Carolina, Charlotte, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,11,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"2019. Slurm. https:\/\/slurm.schedmd.com\/sched-config.html\/."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Cynthia Bailey\u00a0Lee Yael Schwartzman Jennifer Hardy and Allan Snavely. 2005. Are user runtime estimates inherently inaccurate?. In Job Scheduling Strategies for Parallel Processing (JSSPP\u201905).","DOI":"10.1007\/11407522_14"},{"key":"e_1_3_2_2_3_1","unstructured":"G.\u00a0Bruce Berriman and John\u00a0C. Good. 2023. Montage An Astronomical Image Mosaic Engine. http:\/\/montage.ipac.caltech.edu\/"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126955"},{"key":"e_1_3_2_2_5_1","unstructured":"C.S. Chang. 2023. XGC Multiphysics Magnetic Fusion Reactor Simulator from Hot Core to Cold Wall. https:\/\/www.olcf.ornl.gov\/caar\/xgc\/."},{"key":"e_1_3_2_2_6_1","volume-title":"Deep Reinforcement Agent for Scheduling in HPC. 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS\u201921)","author":"Fan Yuping","year":"2021","unstructured":"Yuping Fan, Zhiling Lan, J.\u00a0Taylor Childers, Paul\u00a0M. Rich, William\u00a0E. Allcock, and Michael\u00a0E. Papka. 2021. Deep Reinforcement Agent for Scheduling in HPC. 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS\u201921)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2017.11"},{"key":"e_1_3_2_2_8_1","unstructured":"Dror Feitelson. 2005. Parallel Workloads Archive."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Dror\u00a0G Feitelson and Larry Rudolph. 1998. Metrics and benchmarking for parallel job scheduling. In Job Scheduling Strategies for Parallel Processing (JSSPP\u201998).","DOI":"10.1007\/BFb0053977"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Dror\u00a0G. Feitelson Dan Tsafrir and David Krakov. 2014. Experience with using the Parallel Workloads Archive. J. Parallel and Distrib. Comput. (2014).","DOI":"10.1016\/j.jpdc.2014.06.013"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807646"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00054"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/646376.689366"},{"key":"e_1_3_2_2_14_1","volume-title":"The workload on parallel supercomputers: modeling the characteristics of rigid jobs. Journal of Parallel and Distributed Computing (JPDC)","author":"Lublin Uri","year":"2003","unstructured":"Uri Lublin and Dror\u00a0G Feitelson. 2003. The workload on parallel supercomputers: modeling the characteristics of rigid jobs. Journal of Parallel and Distributed Computing (JPDC) (2003)."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.932708"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Bill Nitzberg Jennifer\u00a0M Schopf and James\u00a0Patton Jones. 2004. PBS Pro: Grid computing and scheduling attributes. In Grid resource management.","DOI":"10.1007\/978-1-4615-0509-9_13"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Michael Pinedo. 2012. Scheduling. Springer.","DOI":"10.1007\/978-1-4614-2361-4"},{"key":"e_1_3_2_2_18_1","volume-title":"Proximal policy optimization algorithms. arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_2_19_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2023. OpenAI PPO. https:\/\/openai.com\/research\/openai-baselines-ppo."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Srividya Srinivasan Rajkumar Kettimuthu Vijay Subramani and Ponnuswamy Sadayappan. 2002. Selective Reservation Strategies for Backfill Job Scheduling. In Job Scheduling Strategies for Parallel Processing (JSSPP\u201902).","DOI":"10.1007\/3-540-36180-4_4"},{"key":"e_1_3_2_2_21_1","unstructured":"Richard\u00a0S Sutton David McAllester Satinder Singh and Yishay Mansour. 1999. Policy Gradient Methods for Reinforcement Learning with Function Approximation. In Advances in Neural Information Processing Systems (NIPS\u201999)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/645608.662010"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332186.3333041"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289206"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2007.70606"},{"key":"e_1_3_2_2_26_1","volume-title":"RLSchert: An HPC Job Scheduler Using Deep Reinforcement Learning and Remaining Time Prediction. Applied Sciences","author":"Wang Qiqi","year":"2021","unstructured":"Qiqi Wang, Hongjie Zhang, Cheng Qu, Yu Shen, Xiaohui Liu, and Jing Li. 2021. RLSchert: An HPC Job Scheduler Using Deep Reinforcement Learning and Remaining Time Prediction. Applied Sciences (2021)."},{"key":"e_1_3_2_2_27_1","volume-title":"Predictive performance modeling for distributed batch processing using black box monitoring and machine learning. Information Systems","author":"Witt Carl","year":"2019","unstructured":"Carl Witt, Marc Bux, Wladislaw Gusew, and Ulf Leser. 2019. Predictive performance modeling for distributed batch processing using black box monitoring and machine learning. Information Systems (2019)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00035"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531470"}],"event":{"name":"SC-W 2023: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis","location":"Denver CO USA","acronym":"SC-W 2023"},"container-title":["Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624201","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624201","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3624062.3624201","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:05:19Z","timestamp":1755745519000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3624062.3624201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,12]]},"references-count":29,"alternative-id":["10.1145\/3624062.3624201","10.1145\/3624062"],"URL":"https:\/\/doi.org\/10.1145\/3624062.3624201","relation":{},"subject":[],"published":{"date-parts":[[2023,11,12]]},"assertion":[{"value":"2023-11-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}