{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:19:56Z","timestamp":1759335596346,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031744297"},{"type":"electronic","value":"9783031744303"}],"license":[{"start":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T00:00:00Z","timestamp":1734739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T00:00:00Z","timestamp":1734739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-74430-3_4","type":"book-chapter","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T07:45:33Z","timestamp":1734680733000},"page":"60-83","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Launchpad: Learning to\u00a0Schedule Using Offline and\u00a0Online RL Methods"],"prefix":"10.1007","author":[{"given":"Vanamala","family":"Venkataswamy","sequence":"first","affiliation":[]},{"given":"Jake","family":"Grigsby","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Grimshaw","sequence":"additional","affiliation":[]},{"given":"Yanjun","family":"Qi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,21]]},"reference":[{"unstructured":"Amazon EC2 spot instances. Accessed May 2022. https:\/\/aws.amazon.com\/ec2\/spot\/","key":"4_CR1"},{"unstructured":"Azure spot virtual machines. Accessed May 2022. https:\/\/azure.microsoft.com\/en-us\/pricing\/spot\/","key":"4_CR2"},{"doi-asserted-by":"publisher","unstructured":"Ambati, P., Bashir, N., Irwin, D., Shenoy, P.: Waiting game: optimally provisioning fixed resources for cloud-enabled schedulers. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314 (2020). https:\/\/doi.org\/10.1109\/SC41405.2020.00071","key":"4_CR3","DOI":"10.1109\/SC41405.2020.00071"},{"doi-asserted-by":"crossref","unstructured":"Chen, R., Shi, H., Li, Y., Liu, X., Wang, G.: OLPart: online learning based resource partitioning for colocating multiple latency-critical jobs on commodity computers. In: Proceedings of the Eighteenth European Conference on Computer Systems, EuroSys 2023. Association for Computing Machinery (2023)","key":"4_CR4","DOI":"10.1145\/3552326.3567490"},{"unstructured":"Christodoulou, P.: Soft actor-critic for discrete action settings. arXiv preprint arXiv:1910.07207 (2019)","key":"4_CR5"},{"doi-asserted-by":"publisher","unstructured":"Delande, D., Stolf, P., Feraud, R., Pierson, J.M., Bottaro, A.: Horizontal scaling in cloud using contextual bandits. In: Sousa, L., Roma, N., Tom\u00e1s, P. (eds.) Euro-Par 2021: Parallel Processing. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-85665-6_18","key":"4_CR6","DOI":"10.1007\/978-3-030-85665-6_18"},{"doi-asserted-by":"crossref","unstructured":"Fan, Y., Lan, Z., Rich, P., Allcock, W., Papka, M.E.: Hybrid workload scheduling on HPC systems. In: 2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE Computer Society (2022)","key":"4_CR7","DOI":"10.1109\/IPDPS53621.2022.00052"},{"issue":"12","key":"4_CR8","doi-asserted-by":"publisher","first-page":"4903","DOI":"10.1109\/TPDS.2022.3205325","volume":"33","author":"Y Fan","year":"2022","unstructured":"Fan, Y., et al.: DRAS: deep reinforcement learning for cluster scheduling in high performance computing. IEEE Trans. Parallel Distrib. Syst. 33(12), 4903\u20134917 (2022)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"4_CR9","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-88224-2_1","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"DG Feitelson","year":"2021","unstructured":"Feitelson, D.G.: Resampling with feedback: a new paradigm of using workload data for performance evaluation. In: Klus\u00e1\u010dek, D., Cirne, W., Rodrigo, G.P. (eds.) Job Scheduling Strategies for Parallel Processing, pp. 3\u201332. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-88224-2_1"},{"unstructured":"Florence, P., et al.: Implicit behavioral cloning. In: 5th Annual Conference on Robot Learning (2021)","key":"4_CR10"},{"unstructured":"Fu, J., Kumar, A., Nachum, O., Tucker, G., Levine, S.: D4RL: datasets for deep data-driven reinforcement learning (2021)","key":"4_CR11"},{"unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning (2018)","key":"4_CR12"},{"doi-asserted-by":"crossref","unstructured":"Gabel, T., Lange, S., Riedmiller, M.: Batch Reinforcement Learning. Springer, Cham (2012)","key":"4_CR13","DOI":"10.1007\/978-3-642-27645-3_2"},{"unstructured":"Gao, Y., Chen, L., Li, B.: Spotlight: optimizing device placement for training deep neural networks. In: Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, PMLR (2018)","key":"4_CR14"},{"unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor (2018)","key":"4_CR15"},{"unstructured":"Hahn, M., Chaplot, D.S., Tulsiani, S., Mukadam, M., Rehg, J.M., Gupta, A.: No RL, no simulation: learning to navigate without navigating. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021)","key":"4_CR16"},{"doi-asserted-by":"crossref","unstructured":"Hessel, M., Soyer, H., Espeholt, L., Czarnecki, W., Schmitt, S., van Hasselt, H.: Multi-task deep reinforcement learning with PopArt. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)","key":"4_CR17","DOI":"10.1609\/aaai.v33i01.33013796"},{"doi-asserted-by":"crossref","unstructured":"Hu, Z., Tu, J., Li, B.: Spear: optimized dependency-aware task scheduling with deep reinforcement learning. In: 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS) (2019)","key":"4_CR18","DOI":"10.1109\/ICDCS.2019.00201"},{"doi-asserted-by":"crossref","unstructured":"Jain, T., Cooperman, G.: CRAC: checkpoint-restart architecture for CUDA with streams and UVM. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020. IEEE Press (2020)","key":"4_CR19","DOI":"10.1109\/SC41405.2020.00081"},{"unstructured":"Jay, N., Rotman, N., Godfrey, B., Schapira, M., Tamar, A.: A deep reinforcement learning perspective on internet congestion control. In: Proceedings of the 36th International Conference on Machine Learning (2019)","key":"4_CR20"},{"doi-asserted-by":"crossref","unstructured":"Krishnakumar, A., et al.: Runtime task scheduling using imitation learning for heterogeneous many-core systems. IEEE Trans. Comput.-Aided Des. Integr. Circ. Syst. 39(11), 4064\u20134077 (2020)","key":"4_CR21","DOI":"10.1109\/TCAD.2020.3012861"},{"unstructured":"Kumar, A., Fu, J., Soh, M., Tucker, G., Levine, S.: Stabilizing off-policy Q-learning via bootstrapping error reduction. In: Advances in Neural Information Processing Systems (2019)","key":"4_CR22"},{"unstructured":"Levin, S.: Lecture notes. https:\/\/cs182sp21.github.io\/static\/slides\/lec-14.pdf","key":"4_CR23"},{"doi-asserted-by":"crossref","unstructured":"Li, B., Basu\u00a0Roy, R., Wang, D., Samsi, S., Gadepally, V., Tiwari, D.: Toward sustainable HPC: carbon footprint estimation and environmental implications of HPC systems. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2023. ACM (2023)","key":"4_CR24","DOI":"10.1145\/3581784.3607035"},{"doi-asserted-by":"crossref","unstructured":"Mandal, S.K., Bhat, G., Patil, C.A., Doppa, J.R., Pande, P.P., Ogras, U.Y.: Dynamic resource management of heterogeneous mobile platforms via imitation learning. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 27(12), 2842\u20132854 (2019)","key":"4_CR25","DOI":"10.1109\/TVLSI.2019.2926106"},{"unstructured":"Mandlekar, A., et al.: What matters in learning from offline human demonstrations for robot manipulation (2021)","key":"4_CR26"},{"doi-asserted-by":"crossref","unstructured":"Mao, H., Alizadeh, M., Menache, I., Kandula, S.: Resource management with deep reinforcement learning. In: Proceedings of the 15th ACM Workshop on Hot Topics in Networks (2016)","key":"4_CR27","DOI":"10.1145\/3005745.3005750"},{"unstructured":"Mao, H., et al.: Park: an open platform for learning-augmented computer systems. In: Advances in Neural Information Processing Systems. Curran Associates, Inc. (2019)","key":"4_CR28"},{"unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research. PMLR (2016)","key":"4_CR29"},{"unstructured":"Nair, A., Dalal, M., Gupta, A., Levine, S.: Accelerating online reinforcement learning with offline datasets. arXiv preprint arXiv:2006.09359 (2020)","key":"4_CR30"},{"unstructured":"Nair, A., Dalal, M., Gupta, A., Levine, S.: AWAC: accelerating online reinforcement learning with offline datasets (2021)","key":"4_CR31"},{"unstructured":"Narayanan, D., Santhanam, K., Kazhamiaka, F., Phanishayee, A., Zaharia, M.: Heterogeneity-aware cluster scheduling policies for deep learning workloads. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2020), pp. 481\u2013498. USENIX Association, November 2020. https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/narayanan-deepak","key":"4_CR32"},{"issue":"1","key":"4_CR33","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1162\/neco.1991.3.1.88","volume":"3","author":"DA Pomerleau","year":"1991","unstructured":"Pomerleau, D.A.: Efficient training of artificial neural networks for autonomous navigation. Neural Comput. 3(1), 88\u201397 (1991)","journal-title":"Neural Comput."},{"issue":"1","key":"4_CR34","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/LCA.2020.2992182","volume":"19","author":"AL Sartor","year":"2020","unstructured":"Sartor, A.L., Krishnakumar, A., Arda, S.E., Ogras, U.Y., Marculescu, R.: HiLITE: hierarchical and lightweight imitation learning for power management of embedded SoCs. IEEE Comput. Archit. Lett. 19(1), 63\u201367 (2020)","journal-title":"IEEE Comput. Archit. Lett."},{"unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: Proceedings of the 32nd International Conference on Machine Learning (2015)","key":"4_CR35"},{"unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017)","key":"4_CR36"},{"doi-asserted-by":"publisher","unstructured":"Souza, A., Pelckmans, K., Tordsson, J.: A HPC co-scheduler with reinforcement learning. In: Klus\u00e1\u010dek, D., Cirne, W., Rodrigo, G.P. (eds.) Job Scheduling Strategies for Parallel Processing. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-88224-2_7","key":"4_CR37","DOI":"10.1007\/978-3-030-88224-2_7"},{"unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)","key":"4_CR38"},{"doi-asserted-by":"publisher","unstructured":"Venkataswamy, V.: Scheduling to ensure performance and cost effectiveness in power-modulated datacenters (2023). https:\/\/doi.org\/10.18130\/efrq-c210","key":"4_CR39","DOI":"10.18130\/efrq-c210"},{"doi-asserted-by":"crossref","unstructured":"Venkataswamy, V., Grigsby, J., Grimshaw, A., Qi, Y.: RARE: renewable energy aware resource management in datacenters. In: Job Scheduling Strategies for Parallel Processing, JSSPP 2022 (2022)","key":"4_CR40","DOI":"10.1007\/978-3-031-22698-4_6"},{"unstructured":"Venkataswamy, V., Grimshaw, A.: Job scheduling in datacenters using constraint controlled RL. arXiv https:\/\/arxiv.org\/abs\/2211.05338 (2022)","key":"4_CR41"},{"unstructured":"Wang, Z., et\u00a0al.: Critic regularized regression. In: Advances in Neural Information Processing Systems (2020)","key":"4_CR42"},{"unstructured":"Zhou, Y., et al.: Carbink: fault-tolerant far memory. In: 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2022). USENIX Association (2022)","key":"4_CR43"}],"container-title":["Lecture Notes in Computer Science","Job Scheduling Strategies for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-74430-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T08:03:49Z","timestamp":1734681829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-74430-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,21]]},"ISBN":["9783031744297","9783031744303"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-74430-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,21]]},"assertion":[{"value":"21 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"JSSPP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Workshop on Job Scheduling Strategies for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Francisco","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 May 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 May 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"jsspp2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}