{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:54Z","timestamp":1786120854791,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"The IBM Center for Advanced Studies &#x28;CAS&#x29;","award":["CAS-1168"],"award-info":[{"award-number":["CAS-1168"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818390","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"7911-7922","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EDA Job Scheduling Using Reinforcement Learning with Adaptive Macro Actions"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8345-7692","authenticated-orcid":false,"given":"Yiming","family":"Shao","sequence":"first","affiliation":[{"name":"Electrical Engineering and Computer Science, York University, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1765-5751","authenticated-orcid":false,"given":"Aijun","family":"An","sequence":"additional","affiliation":[{"name":"Electrical Engineering and Computer Science, York University, Toronto, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1421-863X","authenticated-orcid":false,"given":"Michael","family":"Spriggs","sequence":"additional","affiliation":[{"name":"IBM Spectrum Computing, International Business Machines (IBM), Markham, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7600-4805","authenticated-orcid":false,"given":"Michael","family":"Feiman","sequence":"additional","affiliation":[{"name":"IBM Spectrum Computing, International Business Machines (IBM), Markham, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3782-6902","authenticated-orcid":false,"given":"Hao","family":"Zhou","sequence":"additional","affiliation":[{"name":"IBM Spectrum Computing, International Business Machines (IBM), Markham, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2025.105138"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Yixin Bao Yanghua Peng Chuan Wu and Zongpeng Li. 2018. Online Job Scheduling in Distributed Machine Learning Clusters. arXiv:1801.00936 [cs.DC] https:\/\/arxiv.org\/abs\/1801.00936","DOI":"10.1109\/INFOCOM.2018.8486422"},{"key":"e_1_3_2_1_3_1","volume-title":"Joseph D Viviano, Micha? Koziarski, Moksh Jain, Nikolay Malkin, Emmanuel Bengio, Rim Assouel, and Yoshua Bengio.","author":"Boussif Oussama","year":"2024","unstructured":"Oussama Boussif, L\u00e9na N\u00e9hale Ezzine, Joseph D Viviano, Micha? Koziarski, Moksh Jain, Nikolay Malkin, Emmanuel Bengio, Rim Assouel, and Yoshua Bengio. 2024. Action abstractions for amortized sampling. arXiv:2410.15184 [cs.LG] https:\/\/arxiv.org\/abs\/2410.15184"},{"key":"e_1_3_2_1_4_1","unstructured":"Yekun Chai Haoran Sun Huang Fang Shuohuan Wang Yu Sun and Hua Wu. 2025. MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions. arXiv:2410.02743 [cs.CL] https:\/\/arxiv.org\/abs\/2410.02743"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05470--2"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698364.3709131"},{"key":"e_1_3_2_1_7_1","volume-title":"Deep Reinforcement Learning as a Job Shop Scheduling Solver: A Literature Review","author":"Cunha Bruno","unstructured":"Bruno Cunha, Ana M. Madureira, Benjamim Fonseca, and Duarte Coelho. 2020. Deep Reinforcement Learning as a Job Shop Scheduling Solver: A Literature Review. In Hybrid Intelligent Systems, Ana Maria Madureira, Ajith Abraham, Niketa Gandhi, and Maria Leonilde Varela (Eds.). Springer International Publishing, Cham, 350--359."},{"key":"e_1_3_2_1_8_1","volume-title":"Papka","author":"Fan Yuping","year":"2021","unstructured":"Yuping Fan, Zhiling Lan, Taylor Childers, Paul Rich, William Allcock, and Michael E. Papka. 2021. Deep Reinforcement Agent for Scheduling in HPC. arXiv:2102.06243 [cs.DC] https:\/\/arxiv.org\/abs\/2102.06243"},{"key":"e_1_3_2_1_9_1","unstructured":"Yan Gu Zhaoze Liu Shuhong Dai Cong Liu Ying Wang Shen Wang Georgios Theodoropoulos and Long Cheng. 2025. Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud Computing: An Algorithm-Level Review. arXiv:2501.01007 [cs.DC] https:\/\/arxiv.org\/abs\/2501.01007"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","unstructured":"Dan Hendrycks and Kevin Gimpel. 2023. Gaussian Error Linear Units (GELUs). arXiv:1606.08415 [cs.LG] https:\/\/arxiv.org\/abs\/1606.08415"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451179"},{"key":"e_1_3_2_1_13_1","unstructured":"IBM. 2024. Absolute Priority Scheduling (APS). https:\/\/www.ibm.com\/docs\/en\/spectrum-lsf\/10.1.0?topic=priorities-absolute-priority-scheduling. IBM Spectrum LSF 10.1.0 Documentation."},{"key":"e_1_3_2_1_14_1","volume-title":"IBM Spectrum LSF Documentation","author":"IBM.","unstructured":"IBM. 2024. IBM Spectrum LSF Documentation. IBM Corporation. https:\/\/www. ibm.com\/docs\/en\/spectrum-lsf."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/35043.35047"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00085"},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Machine Learning Based Framework for Fast Resource Estimation of RTL Designs Targeting FPGAs","volume":"28","author":"Li Benzheng","year":"2022","unstructured":"Benzheng Li, Xi Zhang, Hailong You, Zhongdong Qi, and Yuming Zhang. 2022. Machine Learning Based Framework for Fast Resource Estimation of RTL Designs Targeting FPGAs. ACM Transactions on Design Automation of Electronic Systems 28 (2022), 1 -- 16. https:\/\/api.semanticscholar.org\/CorpusID:252568668","journal-title":"ACM Transactions on Design Automation of Electronic Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-016-0825--8"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.932708"},{"key":"e_1_3_2_1_21_1","volume-title":"Heuristics for Vector Bin Packing. (January","author":"Panigrahy Rina","year":"2011","unstructured":"Rina Panigrahy, Kunal Talwar, Lincoln Uyeda, and Udi Wieder. 2011. Heuristics for Vector Bin Packing. (January 2011). https:\/\/www.microsoft.com\/en-us\/ research\/publication\/heuristics-for-vector-bin-packing\/"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3008904.3009050"},{"key":"e_1_3_2_1_23_1","unstructured":"Yanghua Peng Yixin Bao Yangrui Chen Chuan Wu Chen Meng and Wei Lin. 2019. DL2: A Deep Learning-driven Scheduler for Deep Learning Clusters. arXiv:1909.06040 [cs.LG] https:\/\/arxiv.org\/abs\/1909.06040"},{"key":"e_1_3_2_1_24_1","unstructured":"Andrew M. Saxe James L. McClelland and Surya Ganguli. 2013. Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. arXiv:1312.6120 [cs.NE] https:\/\/arxiv.org\/abs\/1312.6120"},{"key":"e_1_3_2_1_25_1","volume-title":"EDA for IC System Design, Verification, and Testing (Electronic Design Automation for Integrated Circuits Handbook)","author":"Scheffer Louis","unstructured":"Louis Scheffer, Luciano Lavagno, and Grant Martin. 2006. EDA for IC System Design, Verification, and Testing (Electronic Design Automation for Integrated Circuits Handbook). CRC Press, Inc., USA."},{"key":"e_1_3_2_1_26_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs.LG] https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_1_27_1","volume-title":"Job Scheduling Strategies for Parallel Processing, Dror G","author":"Skovira Joseph","unstructured":"Joseph Skovira, Waiman Chan, Honbo Zhou, and David Lifka. 1996. The EASY \u2014 LoadLeveler API project. In Job Scheduling Strategies for Parallel Processing, Dror G. Feitelson and Larry Rudolph (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 41--47."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 13th International Conference on Neural Information Processing Systems","author":"Sutton Richard S.","year":"1999","unstructured":"Richard S. Sutton, David McAllester, Satinder Singh, and Yishay Mansour. 1999. Policy gradient methods for reinforcement learning with function approximation. In Proceedings of the 13th International Conference on Neural Information Processing Systems (Denver, CO) (NIPS'99). MIT Press, Cambridge, MA, USA, 1057--1063."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004--3702(99)00052--1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-1360(199907)8:4<221::AID-MCDA247>3.0.CO;2-O"},{"key":"e_1_3_2_1_32_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez Lukasz Kaiser and Illia Polosukhin. 2023. Attention Is All You Need. arXiv:1706.03762 [cs.CL] https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3432588"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-025-07396--3"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599241"},{"key":"e_1_3_2_1_36_1","volume-title":"SLURM: Simple Linux Utility for Resource Management. In Job Scheduling Strategies for Parallel Processing","author":"Yoo Andy B.","year":"2003","unstructured":"Andy B. Yoo, Morris A. Jette, and Mark Grondona. 2003. SLURM: Simple Linux Utility for Resource Management. In Job Scheduling Strategies for Parallel Processing, Dror Feitelson, Larry Rudolph, and Uwe Schwiegelshohn (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 44--60."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380231203"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:14:52Z","timestamp":1786065292000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818390"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":38,"alternative-id":["10.1145\/3770855.3818390","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818390","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}