{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:45:27Z","timestamp":1743025527105,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030917012"},{"type":"electronic","value":"9783030917029"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-91702-9_6","type":"book-chapter","created":{"date-parts":[[2021,11,27]],"date-time":"2021-11-27T20:02:46Z","timestamp":1638043366000},"page":"79-93","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Impact of MDP Design for Reinforcement Learning Agents in Resource Management"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3196-3008","authenticated-orcid":false,"given":"Renato Luiz","family":"de Freitas Cunha","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8156-9941","authenticated-orcid":false,"given":"Luiz","family":"Chaimowicz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,11,28]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.future.2016.08.010","volume":"67","author":"RL Cunha","year":"2017","unstructured":"Cunha, R.L., Rodrigues, E.R., Tizzei, L.P., Netto, M.A.S.: Job placement advisor based on turnaround predictions for HPC hybrid clouds. Future Gener. Comput. Syst. 67, 35\u201346 (2017). ISSN 0167\u2013739X","journal-title":"Future Gener. Comput. Syst."},{"doi-asserted-by":"crossref","unstructured":"de Freitas Cunha, R.L., Chaimowicz, L.: Towards a common environment for learning scheduling algorithms. In: 2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), pp. 1\u20138 (2020)","key":"6_CR2","DOI":"10.1109\/MASCOTS50786.2020.9285940"},{"unstructured":"Domeniconi, G., Lee, E.K., Morari, A.: CuSH: cognitive scheduler for heterogeneous high performance computing system. In: Proceedings of DRL4KDD 19: Workshop on Deep Reinforcement Learning for Knowledge Discovery (DRL4KDD), vol. 12 (2019)","key":"6_CR3"},{"doi-asserted-by":"crossref","unstructured":"Fan, Y., Lan, Z., Childers, T., Rich, P., Allcock, W., Papka, M.E.: Deep reinforcement agent for scheduling in HPC. arXiv preprint arXiv:2102.06243 (2021)","key":"6_CR4","DOI":"10.1109\/IPDPS49936.2021.00090"},{"key":"6_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BFb0022284","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"DG Feitelson","year":"1996","unstructured":"Feitelson, D.G., Rudolph, L.: Toward convergence in job schedulers for parallel supercomputers. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1996. LNCS, vol. 1162, pp. 1\u201326. Springer, Heidelberg (1996). https:\/\/doi.org\/10.1007\/BFb0022284"},{"unstructured":"Liang, Y., Machado, M.C., Talvitie, E., Bowling, M.: State of the art control of atari games using shallow reinforcement learning. In AAMAS (2016)","key":"6_CR6"},{"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, pp. 50\u201356 (2016)","key":"6_CR7","DOI":"10.1145\/3005745.3005750"},{"unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)","key":"6_CR8"},{"doi-asserted-by":"crossref","unstructured":"Nishida, C.E.H., Costa, A.H.R., da Costa Bianchi, R.A.: Control of gene regulatory networks basin of attractions with batch reinforcement learning. In: 2018 7th Brazilian Conference on Intelligent Systems (BRACIS), pp. 127\u2013132 (2018)","key":"6_CR9","DOI":"10.1109\/BRACIS.2018.00030"},{"unstructured":"Raffin, A., Hill, A., Ernestus, M., Gleave, A., Kanervisto, A., Dormann, N.: Stable baselines3 (2019). https:\/\/github.com\/DLR-RM\/stable-baselines3","key":"6_CR10"},{"doi-asserted-by":"crossref","unstructured":"Ramos, W., Silva, M., Araujo, E., Marcolino, L.S., Nascimento, E.: Straight to the point: fast-forwarding videos via reinforcement learning using textual data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10931\u201310940 (2020)","key":"6_CR11","DOI":"10.1109\/CVPR42600.2020.01094"},{"unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)","key":"6_CR12"},{"issue":"6419","key":"6_CR13","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"issue":"1","key":"6_CR14","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1), 181\u2013211 (1999). https:\/\/doi.org\/10.1016\/S0004-3702(99)00052-1. ISSN 0004\u20133702","journal-title":"Artif. Intell."},{"issue":"2","key":"6_CR15","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G Tesauro","year":"1994","unstructured":"Tesauro, G.: TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput. 6(2), 215\u2013219 (1994)","journal-title":"Neural Comput."},{"doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, D., He, Y., Bao, F.S., Xie, B.: RLScheduler: an automated HPC batch job scheduler using reinforcement learning. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315. IEEE (2020)","key":"6_CR16","DOI":"10.1109\/SC41405.2020.00035"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-91702-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T12:02:32Z","timestamp":1709812952000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-91702-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030917012","9783030917029"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-91702-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"28 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/c4ai.inova.usp.br\/bracis\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"192","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.1","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to COVID-19, the conference was held as an online event.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}