{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:38:15Z","timestamp":1743104295531,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319700861"},{"type":"electronic","value":"9783319700878"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-70087-8_87","type":"book-chapter","created":{"date-parts":[[2017,10,23]],"date-time":"2017-10-23T21:10:19Z","timestamp":1508793019000},"page":"849-859","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Policy Gradient Reinforcement Learning for I\/O Reordering on Storage Servers"],"prefix":"10.1007","author":[{"given":"Kumar","family":"Dheenadayalan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gopalakrishnan","family":"Srinivasaraghavan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V. N.","family":"Muralidhara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,24]]},"reference":[{"key":"87_CR1","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing Atari with deep reinforcement learning. In: NIPS Deep Learning Workshop (2013)"},{"issue":"11","key":"87_CR2","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238\u20131274 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"87_CR3","unstructured":"Wang, Y., Merchant, A.: Proportional-share scheduling for distributed storage systems. In: Proceedings of the 5th USENIX Conference on File and Storage Technologies, FAST 2007 (2007)"},{"key":"87_CR4","unstructured":"Vengerov, D.: A reinforcement learning approach to dynamic resource allocation. Technical report, Sun Microsystems (2005)"},{"key":"87_CR5","doi-asserted-by":"crossref","unstructured":"Ipek, E., Mutlu, O., Mart\u00ednez, J.F., Caruana, R.: Self-optimizing memory controllers: a reinforcement learning approach. In: Proceedings of the 35th Annual International Symposium on Computer Architecture, ISCA 2008, pp. 39\u201350 (2008)","DOI":"10.1109\/ISCA.2008.21"},{"issue":"5","key":"87_CR6","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1016\/j.future.2010.10.009","volume":"27","author":"J Wu","year":"2011","unstructured":"Wu, J., Xu, X., Zhang, P., Liu, C.: A novel multi-agent reinforcement learning approach for job scheduling in grid computing. Future Gener. Comput. Syst. 27(5), 430\u2013439 (2011)","journal-title":"Future Gener. Comput. Syst."},{"key":"87_CR7","unstructured":"Singh, S., Bertsekas, D.: Reinforcement learning for dynamic channel allocation in cellular telephone systems. In: Advances in Neural Information Processing Systems, NIPS 96"},{"key":"87_CR8","unstructured":"Zhang, W., Dietterich, T.G.: A reinforcement learning approach to job-shop scheduling. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence, vol. 2, IJCAI 1995 (1995)"},{"issue":"3","key":"87_CR9","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1109\/71.674317","volume":"9","author":"AY Zomaya","year":"1998","unstructured":"Zomaya, A.Y., Clements, M., Olariu, S.: A framework for reinforcement-based scheduling in parallel processor systems. IEEE Trans. Parallel Distrib. Syst. 9(3), 249\u2013260 (1998)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"87_CR10","unstructured":"Vengerov, D.: Dynamic tuning of online data migration policies in hierarchical storage systems using reinforcement learning. Technical report (2006)"},{"key":"87_CR11","doi-asserted-by":"crossref","unstructured":"Deshpande, S., Dheenadayalan, K., Srinivasaraghavan, G., Muralidhara, V.: Filer response time prediction using adaptively-learned forecasting models based on counter time series data. In: 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 13\u201318 (2016)","DOI":"10.1109\/ICMLA.2016.0012"},{"key":"87_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/978-3-319-57529-2_39","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"K Dheenadayalan","year":"2017","unstructured":"Dheenadayalan, K., Srinivasaraghavan, G., Muralidhara, V.N.: Self-tuning filers \u2014 overload prediction and preventive tuning using pruned random forest. In: Kim, J., Shim, K., Cao, L., Lee, J.-G., Lin, X., Moon, Y.-S. (eds.) PAKDD 2017. LNCS (LNAI), vol. 10235, pp. 495\u2013507. Springer, Cham (2017). doi:10.1007\/978-3-319-57529-2_39"},{"issue":"4","key":"87_CR13","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.neunet.2008.02.003","volume":"21","author":"J Peters","year":"2008","unstructured":"Peters, J., Schaal, S.: Reinforcement learning of motor skills with policy gradients. Neural Netw. 21(4), 682\u2013697 (2008)","journal-title":"Neural Netw."},{"key":"87_CR14","unstructured":"Sutton, R.S., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Proceedings of the 12th International Conference on Neural Information Processing Systems, NIPS 1999, pp. 1057\u20131063. MIT Press (1999)"},{"key":"87_CR15","volume-title":"The Linux Programming Interface: A Linux and UNIX System Programming Handbook","author":"M Kerrisk","year":"2010","unstructured":"Kerrisk, M.: The Linux Programming Interface: A Linux and UNIX System Programming Handbook, 1st edn. No Starch Press, San Francisco (2010)","edition":"1"},{"key":"87_CR16","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2010, pp. 249\u2013256 (2010)"},{"key":"87_CR17","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5\u2014RmsProp: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4, 26\u201331 (2012)","journal-title":"COURSERA: Neural Netw. Mach. Learn."},{"key":"87_CR18","unstructured":"Norcott, W., Capps, D.: IOzone file system benchmark (2006). www.iozone.org"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-70087-8_87","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T15:25:59Z","timestamp":1710343559000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-70087-8_87"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319700861","9783319700878"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-70087-8_87","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"24 October 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.iconip2017.org\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}