{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:53:39Z","timestamp":1776182019290,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,11,9]],"date-time":"2016-11-09T00:00:00Z","timestamp":1478649600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2016,11,9]]},"DOI":"10.1145\/3005745.3005750","type":"proceedings-article","created":{"date-parts":[[2016,11,2]],"date-time":"2016-11-02T12:22:17Z","timestamp":1478089337000},"page":"50-56","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":943,"title":["Resource Management with Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Hongzi","family":"Mao","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology"}]},{"given":"Mohammad","family":"Alizadeh","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}]},{"given":"Ishai","family":"Menache","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]},{"given":"Srikanth","family":"Kandula","sequence":"additional","affiliation":[{"name":"Microsoft Research"}]}],"member":"320","published-online":{"date-parts":[[2016,11,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Terminator http:\/\/www.imdb.com\/title\/tt0088247\/. Terminator http:\/\/www.imdb.com\/title\/tt0088247\/."},{"key":"e_1_3_2_1_2_1","unstructured":"M. Abadi A. Agarwal P. Barham E. Brevdo Z. Chen C. Citro G. S. Corrado A. Davis J. Dean M. Devin et al. Tensorflow: Large-scale machine learning on heterogeneous systems 2015. Software available from tensorflow. org 2015. M. Abadi A. Agarwal P. Barham E. Brevdo Z. Chen C. Citro G. S. Corrado A. Davis J. Dean M. Devin et al. Tensorflow: Large-scale machine learning on heterogeneous systems 2015. Software available from tensorflow. org 2015."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"P. Abbeel A. Coates M. Quigley and A. Y. Ng. An application of reinforcement learning to aerobatic helicopter flight. Advances in neural information processing systems page 1 2007. P. Abbeel A. Coates M. Quigley and A. Y. Ng. An application of reinforcement learning to aerobatic helicopter flight. Advances in neural information processing systems page 1 2007.","DOI":"10.7551\/mitpress\/7503.003.0006"},{"key":"e_1_3_2_1_4_1","first-page":"281","volume-title":"NSDI","author":"Agarwal S.","year":"2012"},{"key":"e_1_3_2_1_5_1","first-page":"24","volume":"1","author":"Ananthanarayanan G.","year":"2010","journal-title":"In OSDI, number"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"M. Armbrust A. Fox R. Griffith A. D. Joseph R. Katz A. Konwinski G. Lee D. Patterson A. Rabkin I. Stoica etal A view of cloud computing. Communications of the ACM (4) 2010. M. Armbrust A. Fox R. Griffith A. D. Joseph R. Katz A. Konwinski G. Lee D. Patterson A. Rabkin I. Stoica et al. A view of cloud computing. Communications of the ACM (4) 2010.","DOI":"10.1145\/1721654.1721672"},{"key":"e_1_3_2_1_7_1","volume-title":"Decision and Control","author":"Bertsekas D. P.","year":"1995"},{"key":"e_1_3_2_1_8_1","unstructured":"J. A. Boyan and M. L. Littman. Packet routing in dynamically changing networks: A reinforcement learning approach. Advances in neural information processing systems 1994. J. A. Boyan and M. L. Littman. Packet routing in dynamically changing networks: A reinforcement learning approach. Advances in neural information processing systems 1994."},{"key":"e_1_3_2_1_9_1","first-page":"362","volume-title":"Machine Learning Proceedings","author":"Cassandra A. R.","year":"1995"},{"key":"e_1_3_2_1_10_1","first-page":"571","volume-title":"OSDI","author":"Chilimbi T.","year":"2014"},{"key":"e_1_3_2_1_11_1","first-page":"74","author":"Dean J.","year":"2013","journal-title":"The tail at scale. Communications of the ACM, pages"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541941"},{"key":"e_1_3_2_1_13_1","first-page":"395","volume-title":"NSDI","author":"Dong M.","year":"2015"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2168836.2168847"},{"key":"e_1_3_2_1_15_1","unstructured":"J. Gao and R. Evans. Deepmind ai reduces google data centre cooling bill by 40%. https:\/\/deepmind.com\/blog\/deepmind-ai-reduces-google-data-centre-cooling-bill-40\/. J. Gao and R. Evans. Deepmind ai reduces google data centre cooling bill by 40%. https:\/\/deepmind.com\/blog\/deepmind-ai-reduces-google-data-centre-cooling-bill-40\/."},{"key":"e_1_3_2_1_16_1","first-page":"323","volume-title":"NSDI'11","author":"Ghodsi A.","year":"2011"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626334"},{"key":"e_1_3_2_1_18_1","unstructured":"M. T. Hagan H. B. Demuth M. H. Beale and O. De Jes\u00fas. Neural network design. PWS publishing company Boston 1996. M. T. Hagan H. B. Demuth M. H. Beale and O. De Jes\u00fas. Neural network design . PWS publishing company Boston 1996."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"W. K. Hastings. Monte carlo sampling methods using markov chains and their applications. Biometrika (1) 1970. W. K. Hastings. Monte carlo sampling methods using markov chains and their applications. Biometrika (1) 1970.","DOI":"10.1093\/biomet\/57.1.97"},{"key":"e_1_3_2_1_20_1","volume-title":"NSDI'10","author":"Heller B.","year":"2010"},{"key":"e_1_3_2_1_21_1","unstructured":"G. Hinton. Overview of mini-batch gradient descent. Neural Networks for Machine Learning. G. Hinton. Overview of mini-batch gradient descent. Neural Networks for Machine Learning ."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629575.1629601"},{"key":"e_1_3_2_1_23_1","volume-title":"SIGCOMM '15","author":"Junchen J.","year":"2015"},{"key":"e_1_3_2_1_24_1","author":"Kaelbling L. P.","year":"1996","journal-title":"Journal of artificial intelligence research"},{"key":"e_1_3_2_1_25_1","author":"Kober J.","year":"2013","journal-title":"Reinforcement learning in robotics: A survey. The International Journal of Robotics Research"},{"key":"e_1_3_2_1_26_1","volume-title":"FLAIRS Conference","author":"Mahadevan S.","year":"1998"},{"key":"e_1_3_2_1_27_1","author":"Menache I.","year":"2005","journal-title":"Basis function adaptation in temporal difference reinforcement learning. Annals of Operations Research, (1)"},{"key":"e_1_3_2_1_28_1","volume-title":"CoRR","author":"Mnih V.","year":"2016"},{"key":"e_1_3_2_1_29_1","volume-title":"CoRR","author":"Mnih V.","year":"2013"},{"key":"e_1_3_2_1_30_1","volume-title":"Nature","author":"Mnih V.","year":"2015"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"G. E. Monahan. State of the art - a survey of partially observable markov decision processes: theory models and algorithms. Management Science (1) 1982. G. E. Monahan. State of the art - a survey of partially observable markov decision processes: theory models and algorithms. Management Science (1) 1982.","DOI":"10.1287\/mnsc.28.1.1"},{"key":"e_1_3_2_1_32_1","unstructured":"J. Schulman S. Levine P. Moritz M. I. Jordan and P. Abbeel. Trust region policy optimization. CoRR abs\/1502.05477 2015. J. Schulman S. Levine P. Moritz M. I. Jordan and P. Abbeel. Trust region policy optimization. CoRR abs\/1502.05477 2015."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"D. Silver A. Huang C. J. Maddison A. Guez L. Sifre G. van den Driessche J. Schrittwieser I. Antonoglou V. Panneershevlvam M. Lanctot S. Dieleman D. Grewe J. Nham N. Kalchbrenner I. Sutskever T. Lillicrap M. Leach K. Kavukcuoglu T. Graepel and D. Hassabis. Mastering the game of go with deep neural networks and tree search. Nature 2016. D. Silver A. Huang C. J. Maddison A. Guez L. Sifre G. van den Driessche J. Schrittwieser I. Antonoglou V. Panneershevlvam M. Lanctot S. Dieleman D. Grewe J. Nham N. Kalchbrenner I. Sutskever T. Lillicrap M. Leach K. Kavukcuoglu T. Graepel and D. Hassabis. Mastering the game of go with deep neural networks and tree search. Nature 2016.","DOI":"10.1038\/nature16961"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_1_35_1","volume-title":"NIPS","author":"Sutton R. S.","year":"1999"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2523616.2523633"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"e_1_3_2_1_38_1","first-page":"459","volume-title":"NSDI","author":"Winstein K.","year":"2013"},{"key":"e_1_3_2_1_39_1","volume-title":"SIGCOMM","author":"Yi S.","year":"2016"},{"key":"e_1_3_2_1_40_1","volume-title":"SIGCOMM '16","author":"Yin X.","year":"2016"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1755913.1755940"},{"key":"e_1_3_2_1_42_1","volume-title":"IJCAI. Citeseer","author":"Zhang W.","year":"1995"}],"event":{"name":"HotNets-XV: The 15th ACM Workshop on Hot Topics in Networks","location":"Atlanta GA USA","acronym":"HotNets-XV","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 15th ACM Workshop on Hot Topics in Networks"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3005745.3005750","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3005745.3005750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:39:38Z","timestamp":1750217978000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3005745.3005750"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,9]]},"references-count":42,"alternative-id":["10.1145\/3005745.3005750","10.1145\/3005745"],"URL":"https:\/\/doi.org\/10.1145\/3005745.3005750","relation":{},"subject":[],"published":{"date-parts":[[2016,11,9]]},"assertion":[{"value":"2016-11-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}