{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T15:24:15Z","timestamp":1787844255047,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":80,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T00:00:00Z","timestamp":1628467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["1813487,1918757"],"award-info":[{"award-number":["1813487,1918757"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,9]]},"DOI":"10.1145\/3452296.3472902","type":"proceedings-article","created":{"date-parts":[[2021,8,9]],"date-time":"2021-08-09T18:13:15Z","timestamp":1628532795000},"page":"258-271","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":102,"title":["Network planning with deep reinforcement learning"],"prefix":"10.1145","author":[{"given":"Hang","family":"Zhu","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun","family":"Gupta","sequence":"additional","affiliation":[{"name":"Facebook Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satyajeet Singh","family":"Ahuja","sequence":"additional","affiliation":[{"name":"Facebook Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuandong","family":"Tian","sequence":"additional","affiliation":[{"name":"Facebook Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Facebook Inc."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,8,9]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"AlphaFold. https:\/\/deepmind.com\/blog\/article\/alphafold-a-solution-to-a-50-year-old-grand-challenge-in-biology.  AlphaFold. https:\/\/deepmind.com\/blog\/article\/alphafold-a-solution-to-a-50-year-old-grand-challenge-in-biology."},{"key":"e_1_3_2_2_2_1","unstructured":"Global state of the WAN Report 2020. https:\/\/info.aryaka.com\/state-of-the-wan-report-2020.html.  Global state of the WAN Report 2020. https:\/\/info.aryaka.com\/state-of-the-wan-report-2020.html."},{"key":"e_1_3_2_2_3_1","volume-title":"An actor-critic algorithm for sequence prediction. arXiv preprint arXiv:1607.07086","author":"Bahdanau D.","year":"2016","unstructured":"D. Bahdanau , P. Brakel , K. Xu , A. Goyal , R. Lowe , J. Pineau , A. Courville , and Y. Bengio . An actor-critic algorithm for sequence prediction. arXiv preprint arXiv:1607.07086 , 2016 . D. Bahdanau, P. Brakel, K. Xu, A. Goyal, R. Lowe, J. Pineau, A. Courville, and Y. Bengio. An actor-critic algorithm for sequence prediction. arXiv preprint arXiv:1607.07086, 2016."},{"key":"e_1_3_2_2_4_1","volume-title":"Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940","author":"Bello I.","year":"2016","unstructured":"I. Bello , H. Pham , Q. V. Le , M. Norouzi , and S. Bengio . Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940 , 2016 . I. Bello, H. Pham, Q. V. Le, M. Norouzi, and S. Bengio. Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940, 2016."},{"key":"e_1_3_2_2_5_1","author":"Bengio Y.","year":"2020","unstructured":"Y. Bengio , A. Lodi , and A. Prouvost . Machine learning for combinatorial optimization: a methodological tour d'horizon. European Journal of Operational Research , 2020 . Y. Bengio, A. Lodi, and A. Prouvost. Machine learning for combinatorial optimization: a methodological tour d'horizon. European Journal of Operational Research, 2020.","journal-title":"European Journal of Operational Research"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/1097029"},{"key":"e_1_3_2_2_7_1","volume-title":"Combining reinforcement learning and constraint programming for combinatorial optimization. arXiv preprint arXiv:2006.01610","author":"Cappart Q.","year":"2020","unstructured":"Q. Cappart , T. Moisan , L.-M. Rousseau , I. Pr\u00e9mont-Schwarz , and A. Cire . Combining reinforcement learning and constraint programming for combinatorial optimization. arXiv preprint arXiv:2006.01610 , 2020 . Q. Cappart, T. Moisan, L.-M. Rousseau, I. Pr\u00e9mont-Schwarz, and A. Cire. Combining reinforcement learning and constraint programming for combinatorial optimization. arXiv preprint arXiv:2006.01610, 2020."},{"key":"e_1_3_2_2_8_1","volume-title":"USENIX NSDI","author":"Chang Y.","year":"2017","unstructured":"Y. Chang , S. Rao , and M. Tawarmalani . Robust validation of network designs under uncertain demands and failures . In USENIX NSDI , 2017 . Y. Chang, S. Rao, and M. Tawarmalani. Robust validation of network designs under uncertain demands and failures. In USENIX NSDI, 2017."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"e_1_3_2_2_10_1","volume-title":"Advances in Neural Information Processing Systems","author":"Chen X.","year":"2019","unstructured":"X. Chen and Y. Tian . Learning to perform local rewriting for combinatorial optimization . Advances in Neural Information Processing Systems , 2019 . X. Chen and Y. Tian. Learning to perform local rewriting for combinatorial optimization. Advances in Neural Information Processing Systems, 2019."},{"key":"e_1_3_2_2_11_1","unstructured":"CPLEX Optimizer. https:\/\/www.ibm.com\/analytics\/cplex-optimizer.  CPLEX Optimizer. https:\/\/www.ibm.com\/analytics\/cplex-optimizer."},{"key":"e_1_3_2_2_12_1","volume-title":"Convolutional networks on graphs for learning molecular fingerprints. arXiv preprint arXiv:1509.09292","author":"Duvenaud D.","year":"2015","unstructured":"D. Duvenaud , D. Maclaurin , J. Aguilera-Iparraguirre , R. G\u00f3mez-Bombarelli , T. Hirzel , A. Aspuru-Guzik , and R. P. Adams . Convolutional networks on graphs for learning molecular fingerprints. arXiv preprint arXiv:1509.09292 , 2015 . D. Duvenaud, D. Maclaurin, J. Aguilera-Iparraguirre, R. G\u00f3mez-Bombarelli, T. Hirzel, A. Aspuru-Guzik, and R. P. Adams. Convolutional networks on graphs for learning molecular fingerprints. arXiv preprint arXiv:1509.09292, 2015."},{"key":"e_1_3_2_2_13_1","volume-title":"Fast graph representation learning with pytorch geometric. arXiv preprint arXiv:1903.02428","author":"Fey M.","year":"2019","unstructured":"M. Fey and J. E. Lenssen . Fast graph representation learning with pytorch geometric. arXiv preprint arXiv:1903.02428 , 2019 . M. Fey and J. E. Lenssen. Fast graph representation learning with pytorch geometric. arXiv preprint arXiv:1903.02428, 2019."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2000.832225"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2014.6710063"},{"key":"e_1_3_2_2_16_1","volume-title":"Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850","author":"Graves A.","year":"2013","unstructured":"A. Graves . Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 , 2013 . A. Graves. Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850, 2013."},{"key":"e_1_3_2_2_17_1","author":"Gu L.","year":"2019","unstructured":"L. Gu , D. Zeng , W. Li , S. Guo , A. Y. Zomaya , and H. Jin . Intelligent vnf orchestration and flow scheduling via model-assisted deep reinforcement learning. IEEE Journal on Selected Areas in Communications , 2019 . L. Gu, D. Zeng, W. Li, S. Guo, A. Y. Zomaya, and H. Jin. Intelligent vnf orchestration and flow scheduling via model-assisted deep reinforcement learning. IEEE Journal on Selected Areas in Communications, 2019.","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"e_1_3_2_2_18_1","volume-title":"Hybrid models for learning to branch. arXiv preprint arXiv:2006.15212","author":"Gupta P.","year":"2020","unstructured":"P. Gupta , M. Gasse , E. B. Khalil , M. P. Kumar , A. Lodi , and Y. Bengio . Hybrid models for learning to branch. arXiv preprint arXiv:2006.15212 , 2020 . P. Gupta, M. Gasse, E. B. Khalil, M. P. Kumar, A. Lodi, and Y. Bengio. Hybrid models for learning to branch. arXiv preprint arXiv:2006.15212, 2020."},{"key":"e_1_3_2_2_19_1","unstructured":"Gurobi solver. https:\/\/www.gurobi.com\/.  Gurobi solver. https:\/\/www.gurobi.com\/."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787495"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"e_1_3_2_2_22_1","volume-title":"Autophase: Juggling hls phase orderings in random forests with deep reinforcement learning. arXiv preprint arXiv:2003.00671","author":"Huang Q.","year":"2020","unstructured":"Q. Huang , A. Haj-Ali , W. Moses , J. Xiang , I. Stoica , K. Asanovic , and J. Wawrzynek . Autophase: Juggling hls phase orderings in random forests with deep reinforcement learning. arXiv preprint arXiv:2003.00671 , 2020 . Q. Huang, A. Haj-Ali, W. Moses, J. Xiang, I. Stoica, K. Asanovic, and J. Wawrzynek. Autophase: Juggling hls phase orderings in random forests with deep reinforcement learning. arXiv preprint arXiv:2003.00671, 2020."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486019"},{"key":"e_1_3_2_2_24_1","volume-title":"International Conference on Machine Learning","author":"Jay N.","year":"2019","unstructured":"N. Jay , N. Rotman , B. Godfrey , M. Schapira , and A. Tamar . A deep reinforcement learning perspective on internet congestion control . In International Conference on Machine Learning , 2019 . N. Jay, N. Rotman, B. Godfrey, M. Schapira, and A. Tamar. A deep reinforcement learning perspective on internet congestion control. In International Conference on Machine Learning, 2019."},{"key":"e_1_3_2_2_25_1","volume-title":"Beyond data and model parallelism for deep neural networks. arXiv preprint arXiv:1807.05358","author":"Jia Z.","year":"2018","unstructured":"Z. Jia , M. Zaharia , and A. Aiken . Beyond data and model parallelism for deep neural networks. arXiv preprint arXiv:1807.05358 , 2018 . Z. Jia, M. Zaharia, and A. Aiken. Beyond data and model parallelism for deep neural networks. arXiv preprint arXiv:1807.05358, 2018."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTQE.2004.826575"},{"key":"e_1_3_2_2_27_1","volume-title":"Advances in Neural Information Processing Systems","author":"Kakade S. M.","year":"2001","unstructured":"S. M. Kakade . A natural policy gradient . Advances in Neural Information Processing Systems , 2001 . S. M. Kakade. A natural policy gradient. Advances in Neural Information Processing Systems, 2001."},{"key":"e_1_3_2_2_28_1","volume-title":"Advances in Neural Information Processing Systems","author":"Khalil E.","year":"2017","unstructured":"E. Khalil , H. Dai , Y. Zhang , B. Dilkina , and L. Song . Learning combinatorial optimization algorithms over graphs . Advances in Neural Information Processing Systems , 2017 . E. Khalil, H. Dai, Y. Zhang, B. Dilkina, and L. Song. Learning combinatorial optimization algorithms over graphs. Advances in Neural Information Processing Systems, 2017."},{"key":"e_1_3_2_2_29_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf T. N.","year":"2016","unstructured":"T. N. Kipf and M. Welling . Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 , 2016 . T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016."},{"key":"e_1_3_2_2_30_1","author":"Kirilin V.","year":"2020","unstructured":"V. Kirilin , A. Sundarrajan , S. Gorinsky , and R. K. Sitaraman . Rl-cache: Learning-based cache admission for content delivery. IEEE Journal on Selected Areas in Communications , 2020 . V. Kirilin, A. Sundarrajan, S. Gorinsky, and R. K. Sitaraman. Rl-cache: Learning-based cache admission for content delivery. IEEE Journal on Selected Areas in Communications, 2020.","journal-title":"Rl-cache: Learning-based cache admission for content delivery. IEEE Journal on Selected Areas in Communications"},{"key":"e_1_3_2_2_31_1","volume-title":"Advances in Neural Information Processing Systems","author":"Konda V. R.","year":"2000","unstructured":"V. R. Konda and J. N. Tsitsiklis . Actor-critic algorithms . In Advances in Neural Information Processing Systems , 2000 . V. R. Konda and J. N. Tsitsiklis. Actor-critic algorithms. In Advances in Neural Information Processing Systems, 2000."},{"key":"e_1_3_2_2_32_1","volume-title":"Attention, learn to solve routing problems! arXiv preprint arXiv:1803.08475","author":"Kool W.","year":"2018","unstructured":"W. Kool , H. Van Hoof , and M. Welling . Attention, learn to solve routing problems! arXiv preprint arXiv:1803.08475 , 2018 . W. Kool, H. Van Hoof, and M. Welling. Attention, learn to solve routing problems! arXiv preprint arXiv:1803.08475, 2018."},{"key":"e_1_3_2_2_33_1","volume-title":"Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493","author":"Li Y.","year":"2015","unstructured":"Y. Li , D. Tarlow , M. Brockschmidt , and R. Zemel . Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 , 2015 . Y. Li, D. Tarlow, M. Brockschmidt, and R. Zemel. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493, 2015."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342221"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132759"},{"key":"e_1_3_2_2_37_1","volume-title":"IEEE INFOCOM","author":"Liu Y.","year":"2005","unstructured":"Y. Liu , H. Zhang , W. Gongt , and D. Towsley . On the interaction between overlay routing and underlay routing . In IEEE INFOCOM , 2005 . Y. Liu, H. Zhang, W. Gongt, and D. Towsley. On the interaction between overlay routing and underlay routing. In IEEE INFOCOM, 2005."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"e_1_3_2_2_40_1","volume-title":"Reinforcement learning for combinatorial optimization: A survey. arXiv preprint arXiv:2003.03600","author":"Mazyavkina N.","year":"2020","unstructured":"N. Mazyavkina , S. Sviridov , S. Ivanov , and E. Burnaev . Reinforcement learning for combinatorial optimization: A survey. arXiv preprint arXiv:2003.03600 , 2020 . N. Mazyavkina, S. Sviridov, S. Ivanov, and E. Burnaev. Reinforcement learning for combinatorial optimization: A survey. arXiv preprint arXiv:2003.03600, 2020."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405859"},{"key":"e_1_3_2_2_42_1","unstructured":"Mininet. http:\/\/mininet.org.  Mininet. http:\/\/mininet.org."},{"key":"e_1_3_2_2_43_1","volume-title":"Chip placement with deep reinforcement learning. arXiv preprint arXiv:2004.10746","author":"Mirhoseini A.","year":"2020","unstructured":"A. Mirhoseini , A. Goldie , M. Yazgan , J. Jiang , E. Songhori , S. Wang , Y.-J. Lee , E. Johnson , O. Pathak , S. Bae , Chip placement with deep reinforcement learning. arXiv preprint arXiv:2004.10746 , 2020 . A. Mirhoseini, A. Goldie, M. Yazgan, J. Jiang, E. Songhori, S. Wang, Y.-J. Lee, E. Johnson, O. Pathak, S. Bae, et al. Chip placement with deep reinforcement learning. arXiv preprint arXiv:2004.10746, 2020."},{"key":"e_1_3_2_2_44_1","volume-title":"Branch-and-cut algorithms for combinatorial optimization problems. Handbook of applied optimization","author":"Mitchell J. E.","year":"2002","unstructured":"J. E. Mitchell . Branch-and-cut algorithms for combinatorial optimization problems. Handbook of applied optimization , 2002 . J. E. Mitchell. Branch-and-cut algorithms for combinatorial optimization problems. Handbook of applied optimization, 2002."},{"key":"e_1_3_2_2_45_1","volume-title":"Learning heuristics over large graphs via deep reinforcement learning. arXiv preprint arXiv:1903.03332","author":"Mittal A.","year":"2019","unstructured":"A. Mittal , A. Dhawan , S. Manchanda , S. Medya , S. Ranu , and A. Singh . Learning heuristics over large graphs via deep reinforcement learning. arXiv preprint arXiv:1903.03332 , 2019 . A. Mittal, A. Dhawan, S. Manchanda, S. Medya, S. Ranu, and A. Singh. Learning heuristics over large graphs via deep reinforcement learning. arXiv preprint arXiv:1903.03332, 2019."},{"key":"e_1_3_2_2_46_1","volume-title":"Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602","author":"Mnih V.","year":"2013","unstructured":"V. Mnih , K. Kavukcuoglu , D. Silver , A. Graves , I. Antonoglou , D. Wierstra , and M. Riedmiller . Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 , 2013 . V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, and M. Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013."},{"key":"e_1_3_2_2_47_1","volume-title":"Nature","author":"Mnih V.","year":"2015","unstructured":"V. Mnih , K. Kavukcuoglu , D. Silver , A. A. Rusu , J. Veness , M. G. Bellemare , A. Graves , M. Riedmiller , A. K. Fidjeland , G. Ostrovski , S. Petersen , C. Beattie , A. Sadik , I. Antonoglou , H. King , D. Kumaran , D. Wierstra , S. Legg , and D. Hassabis . Human-level control through deep reinforcement learning . Nature , 2015 . V. Mnih, K. Kavukcuoglu, D. Silver, A. A. Rusu, J. Veness, M. G. Bellemare, A. Graves, M. Riedmiller, A. K. Fidjeland, G. Ostrovski, S. Petersen, C. Beattie, A. Sadik, I. Antonoglou, H. King, D. Kumaran, D. Wierstra, S. Legg, and D. Hassabis. Human-level control through deep reinforcement learning. Nature, 2015."},{"key":"e_1_3_2_2_48_1","volume-title":"Planar graphs: Theory and algorithms","author":"Nishizeki T.","year":"1988","unstructured":"T. Nishizeki and N. Chiba . Planar graphs: Theory and algorithms . Elsevier , 1988 . T. Nishizeki and N. Chiba. Planar graphs: Theory and algorithms. Elsevier, 1988."},{"key":"e_1_3_2_2_49_1","unstructured":"NS-3 network simulator. https:\/\/www.nsnam.org\/.  NS-3 network simulator. https:\/\/www.nsnam.org\/."},{"key":"e_1_3_2_2_50_1","series-title":"SIAM review","volume-title":"A branch-and-cut algorithm for the resolution of large-scale symmetric traveling salesman problems","author":"Padberg M.","year":"1991","unstructured":"M. Padberg and G. Rinaldi . A branch-and-cut algorithm for the resolution of large-scale symmetric traveling salesman problems . SIAM review , 1991 . M. Padberg and G. Rinaldi. A branch-and-cut algorithm for the resolution of large-scale symmetric traveling salesman problems. SIAM review, 1991."},{"key":"e_1_3_2_2_51_1","volume-title":"WWW","author":"Peng H.","year":"2018","unstructured":"H. Peng , J. Li , Y. He , Y. Liu , M. Bao , L. Wang , Y. Song , and Q. Yang . Large-scale hierarchical text classification with recursively regularized deep graph-cnn . In WWW , 2018 . H. Peng, J. Li, Y. He, Y. Liu, M. Bao, L. Wang, Y. Song, and Q. Yang. Large-scale hierarchical text classification with recursively regularized deep graph-cnn. In WWW, 2018."},{"key":"e_1_3_2_2_52_1","author":"Scarselli F.","year":"2008","unstructured":"F. Scarselli , M. Gori , A. C. Tsoi , M. Hagenbuchner , and G. Monfardini . The graph neural network model. IEEE Transactions on Neural Networks , 2008 . F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini. The graph neural network model. IEEE Transactions on Neural Networks, 2008.","journal-title":"The graph neural network model. IEEE Transactions on Neural Networks"},{"key":"e_1_3_2_2_53_1","volume-title":"High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438","author":"Schulman J.","year":"2015","unstructured":"J. Schulman , P. Moritz , S. Levine , M. Jordan , and P. Abbeel . High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 , 2015 . J. Schulman, P. Moritz, S. Levine, M. Jordan, and P. Abbeel. High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438, 2015."},{"key":"e_1_3_2_2_54_1","volume-title":"Nature","author":"Silver D.","year":"2017","unstructured":"D. Silver , J. Schrittwieser , K. Simonyan , I. Antonoglou , A. Huang , A. Guez , T. Hubert , L. Baker , M. Lai , A. Bolton , Y. Chen , T. Lillicrap , F. Hui , L. Sifre , G. v. d. Driessche , T. Graepel , and D. Hassabis . Mastering the game of go without human knowledge . Nature , 2017 . D. Silver, J. Schrittwieser, K. Simonyan, I. Antonoglou, A. Huang, A. Guez, T. Hubert, L. Baker, M. Lai, A. Bolton, Y. Chen, T. Lillicrap, F. Hui, L. Sifre, G. v. d. Driessche, T. Graepel, and D. Hassabis. Mastering the game of go without human knowledge. Nature, 2017."},{"key":"e_1_3_2_2_55_1","unstructured":"OpenAI Spinning Up. https:\/\/spinningup.openai.com\/en\/latest\/.  OpenAI Spinning Up. https:\/\/spinningup.openai.com\/en\/latest\/."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOCN.11.000547"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2017.8227766"},{"key":"e_1_3_2_2_58_1","volume-title":"International Conference on Machine Learning","author":"Tang Y.","year":"2020","unstructured":"Y. Tang , S. Agrawal , and Y. Faenza . Reinforcement learning for integer programming: Learning to cut . In International Conference on Machine Learning , 2020 . Y. Tang, S. Agrawal, and Y. Faenza. Reinforcement learning for integer programming: Learning to cut. In International Conference on Machine Learning, 2020."},{"key":"e_1_3_2_2_59_1","volume-title":"Elf opengo: An analysis and open reimplementation of alphazero. arXiv preprint arXiv:1902.04522","author":"Tian Y.","year":"2019","unstructured":"Y. Tian , J. Ma , Q. Gong , S. Sengupta , Z. Chen , J. Pinkerton , and C. L. Zitnick . Elf opengo: An analysis and open reimplementation of alphazero. arXiv preprint arXiv:1902.04522 , 2019 . Y. Tian, J. Ma, Q. Gong, S. Sengupta, Z. Chen, J. Pinkerton, and C. L. Zitnick. Elf opengo: An analysis and open reimplementation of alphazero. arXiv preprint arXiv:1902.04522, 2019."},{"key":"e_1_3_2_2_60_1","author":"Tornatore M.","year":"2007","unstructured":"M. Tornatore , G. Maier , and A. Pattavina . Wdm network design by ilp models based on flow aggregation. IEEE\/ACM Transactions on Networking , 2007 . M. Tornatore, G. Maier, and A. Pattavina. Wdm network design by ilp models based on flow aggregation. IEEE\/ACM Transactions on Networking, 2007.","journal-title":"IEEE\/ACM Transactions on Networking"},{"key":"e_1_3_2_2_61_1","volume-title":"Mlgo: a machine learning guided compiler optimizations framework. arXiv preprint arXiv:2101.04808","author":"Trofin M.","year":"2021","unstructured":"M. Trofin , Y. Qian , E. Brevdo , Z. Lin , K. Choromanski , and D. Li . Mlgo: a machine learning guided compiler optimizations framework. arXiv preprint arXiv:2101.04808 , 2021 . M. Trofin, Y. Qian, E. Brevdo, Z. Lin, K. Choromanski, and D. Li. Mlgo: a machine learning guided compiler optimizations framework. arXiv preprint arXiv:2101.04808, 2021."},{"key":"e_1_3_2_2_62_1","volume-title":"NIPS Deep Reinforcement Learning Symposium","author":"Valadarsky A.","year":"2017","unstructured":"A. Valadarsky , M. Schapira , D. Shahaf , and A. Tamar . Learning to route with deep rl . In NIPS Deep Reinforcement Learning Symposium , 2017 . A. Valadarsky, M. Schapira, D. Shahaf, and A. Tamar. Learning to route with deep rl. In NIPS Deep Reinforcement Learning Symposium, 2017."},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2010.02.018"},{"key":"e_1_3_2_2_64_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Veli\u010dkovi\u0107 P.","year":"2017","unstructured":"P. Veli\u010dkovi\u0107 , G. Cucurull , A. Casanova , A. Romero , P. Lio , and Y. Bengio . Graph attention networks. arXiv preprint arXiv:1710.10903 , 2017 . P. Veli\u010dkovi\u0107, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2002.1003824"},{"key":"e_1_3_2_2_66_1","author":"Verd\u00fa S.","year":"1999","unstructured":"S. Verd\u00fa and S. Shamai . Spectral efficiency of cdma with random spreading. IEEE Transactions on Information Theory , 1999 . S. Verd\u00fa and S. Shamai. Spectral efficiency of cdma with random spreading. IEEE Transactions on Information Theory, 1999.","journal-title":"Spectral efficiency of cdma with random spreading. IEEE Transactions on Information Theory"},{"key":"e_1_3_2_2_67_1","volume-title":"USENIX OSDI","author":"Wang J.","year":"2021","unstructured":"J. Wang , D. Ding , H. Wang , C. Christensen , Z. Wang , H. Chen , and J. Li . Polyjuice: High-performance transactions via learned concurrency control . In USENIX OSDI , 2021 . J. Wang, D. Ding, H. Wang, C. Christensen, Z. Wang, H. Chen, and J. Li. Polyjuice: High-performance transactions via learned concurrency control. In USENIX OSDI, 2021."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2012.2212180"},{"key":"e_1_3_2_2_69_1","volume-title":"ICLR","author":"Wu Y.","year":"2016","unstructured":"Y. Wu and Y. Tian . Training agent for first-person shooter game with actor-critic curriculum learning . In ICLR , 2016 . Y. Wu and Y. Tian. Training agent for first-person shooter game with actor-critic curriculum learning. In ICLR, 2016."},{"key":"e_1_3_2_2_70_1","author":"Wu Z.","year":"2020","unstructured":"Z. Wu , S. Pan , F. Chen , G. Long , C. Zhang , and S. Y. Philip . A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems , 2020 . Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and S. Y. Philip. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 2020.","journal-title":"A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_2_71_1","volume-title":"How powerful are graph neural networks? arXiv preprint arXiv:1810.00826","author":"Xu K.","year":"2018","unstructured":"K. Xu , W. Hu , J. Leskovec , and S. Jegelka . How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 , 2018 . K. Xu, W. Hu, J. Leskovec, and S. Jegelka. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826, 2018."},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389770"},{"key":"e_1_3_2_2_73_1","volume-title":"USENIX OSDI","author":"Yao J.","year":"2021","unstructured":"J. Yao , R. Tao , R. Gu , J. Nieh , S. Jana , and G. Ryan . Distai: Data-driven automated invariant learning for distributed protocols . In USENIX OSDI , 2021 . J. Yao, R. Tao, R. Gu, J. Nieh, S. Jana, and G. Ryan. Distai: Data-driven automated invariant learning for distributed protocols. In USENIX OSDI, 2021."},{"key":"e_1_3_2_2_74_1","volume-title":"Advances in Neural Information Processing Systems","author":"You J.","year":"2018","unstructured":"J. You , B. Liu , Z. Ying , V. Pande , and J. Leskovec . Graph convolutional policy network for goal-directed molecular graph generation . In Advances in Neural Information Processing Systems , 2018 . J. You, B. Liu, Z. Ying, V. Pande, and J. Leskovec. Graph convolutional policy network for goal-directed molecular graph generation. In Advances in Neural Information Processing Systems, 2018."},{"key":"e_1_3_2_2_75_1","volume-title":"Resource management at the network edge: A deep reinforcement learning approach","author":"Zeng D.","year":"2019","unstructured":"D. Zeng , L. Gu , S. Pan , J. Cai , and S. Guo . Resource management at the network edge: A deep reinforcement learning approach . IEEE Network , 2019 . D. Zeng, L. Gu, S. Pan, J. Cai, and S. Guo. Resource management at the network edge: A deep reinforcement learning approach. IEEE Network, 2019."},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"e_1_3_2_2_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"},{"key":"e_1_3_2_2_78_1","volume-title":"Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434","author":"Zhou J.","year":"2018","unstructured":"J. Zhou , G. Cui , Z. Zhang , C. Yang , Z. Liu , and M. Sun . Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434 , 2018 . J. Zhou, G. Cui, Z. Zhang, C. Yang, Z. Liu, and M. Sun. Graph neural networks: A review of methods and applications. arXiv preprint arXiv:1812.08434, 2018."},{"key":"e_1_3_2_2_79_1","volume-title":"USENIX NSDI","author":"Zhuo D.","year":"2017","unstructured":"D. Zhuo , M. Ghobadi , R. Mahajan , A. Phanishayee , X. K. Zou , H. Guan , A. Krishnamurthy , and T. Anderson . RAIL: A case for redundant arrays of inexpensive links in data center networks . In USENIX NSDI , 2017 . D. Zhuo, M. Ghobadi, R. Mahajan, A. Phanishayee, X. K. Zou, H. Guan, A. Krishnamurthy, and T. Anderson. RAIL: A case for redundant arrays of inexpensive links in data center networks. In USENIX NSDI, 2017."},{"key":"e_1_3_2_2_80_1","volume-title":"Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578","author":"Zoph B.","year":"2016","unstructured":"B. Zoph and Q. V. Le . Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 , 2016 . B. Zoph and Q. V. Le. Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578, 2016."}],"event":{"name":"SIGCOMM '21: ACM SIGCOMM 2021 Conference","location":"Virtual Event USA","acronym":"SIGCOMM '21","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 2021 ACM SIGCOMM 2021 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3452296.3472902","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3452296.3472902","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3452296.3472902","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:13Z","timestamp":1750197673000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3452296.3472902"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,9]]},"references-count":80,"alternative-id":["10.1145\/3452296.3472902","10.1145\/3452296"],"URL":"https:\/\/doi.org\/10.1145\/3452296.3472902","relation":{},"subject":[],"published":{"date-parts":[[2021,8,9]]},"assertion":[{"value":"2021-08-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}