{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:53:39Z","timestamp":1783097619102,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["2107078"],"award-info":[{"award-number":["2107078"]}],"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":[[2023,9,10]]},"DOI":"10.1145\/3603269.3604857","type":"proceedings-article","created":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T16:16:29Z","timestamp":1693584989000},"page":"378-393","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":89,"title":["Teal: Learning-Accelerated Optimization of WAN Traffic Engineering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5326-6908","authenticated-orcid":false,"given":"Zhiying","family":"Xu","sequence":"first","affiliation":[{"name":"Harvard University, Cambridge, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2123-4258","authenticated-orcid":false,"given":"Francis Y.","family":"Yan","sequence":"additional","affiliation":[{"name":"Microsoft Research, Redmond, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8118-3026","authenticated-orcid":false,"given":"Rachee","family":"Singh","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9304-216X","authenticated-orcid":false,"given":"Justin T.","family":"Chiu","sequence":"additional","affiliation":[{"name":"Cornell University, NYC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9900-1606","authenticated-orcid":false,"given":"Alexander M.","family":"Rush","sequence":"additional","affiliation":[{"name":"Cornell University, NYC, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2381-0212","authenticated-orcid":false,"given":"Minlan","family":"Yu","sequence":"additional","affiliation":[{"name":"Harvard University, Cambridge, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Parallelism in LP and MIP August 2020. https:\/\/cdn.gurobi.com\/wp-content\/uploads\/2020\/08\/How-to-Exploit-Parallelism-in-Linear-and-Mixed-Integer-Programming.pdf."},{"key":"e_1_3_2_1_2_1","first-page":"175","volume-title":"Proceedings of USENIX NSDI","author":"Abuzaid Firas","year":"2021","unstructured":"Firas Abuzaid, Srikanth Kandula, Behnaz Arzani, Ishai Menache, Matei Zaharia, and Peter Bailis. Contracting Wide-area Network Topologies to Solve Flow Problems Quickly. In Proceedings of USENIX NSDI, pages 175--200, 2021."},{"key":"e_1_3_2_1_3_1","volume-title":"Constrained Optimization and Lagrange Multiplier Methods","author":"Bertsekas Dimitri P.","year":"2014","unstructured":"Dimitri P. Bertsekas. Constrained Optimization and Lagrange Multiplier Methods. Academic press, 2014."},{"key":"e_1_3_2_1_4_1","volume-title":"Michael Schapira. TEAVAR: Striking the Right Utilization-Availability Balance in WAN Traffic Engineering. In Proceedings of ACM SIGCOMM. ACM","author":"Bogle Jeremy","year":"2019","unstructured":"Jeremy Bogle, Nikhil Bhatia, Manya Ghobadi, Ishai Menache, Nikolaj Bj\u00f8rner, Asaf Valadarsky, and Michael Schapira. TEAVAR: Striking the Right Utilization-Availability Balance in WAN Traffic Engineering. In Proceedings of ACM SIGCOMM. ACM, 2019."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"e_1_3_2_1_6_1","volume-title":"The CAIDA AS Relationships Dataset","author":"CAIDA.","year":"2022","unstructured":"CAIDA. The CAIDA AS Relationships Dataset, 2022."},{"key":"e_1_3_2_1_7_1","volume-title":"cuDNN: Efficient Primitives for Deep Learning. arXiv preprint arXiv:1410.0759","author":"Chetlur Sharan","year":"2014","unstructured":"Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. cuDNN: Efficient Primitives for Deep Learning. arXiv preprint arXiv:1410.0759, 2014."},{"key":"e_1_3_2_1_8_1","first-page":"1300","volume-title":"Indra Widjaja. MATE: MPLS Adaptive Traffic Engineering. In Proceedings of IEEE INFOCOM","volume":"3","author":"Elwalid Anwar","year":"2001","unstructured":"Anwar Elwalid, Cheng Jin, Steven Low, and Indra Widjaja. MATE: MPLS Adaptive Traffic Engineering. In Proceedings of IEEE INFOCOM, volume 3, pages 1300--1309 vol.3, 2001."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313488"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0895480199355754"},{"key":"e_1_3_2_1_11_1","first-page":"29","article-title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","author":"Foerster Jakob","year":"2016","unstructured":"Jakob Foerster, Ioannis Alexandros Assael, Nando De Freitas, and Shimon Whiteson. Learning to Communicate with Deep Multi-Agent Reinforcement Learning. Advances in Neural Information Processing Systems, 29, 2016.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_12_1","volume-title":"Shimon Whiteson. Counterfactual Multi-Agent Policy Gradients. In Proceedings of AAAI conference on artificial intelligence","volume":"32","author":"Foerster Jakob","year":"2018","unstructured":"Jakob Foerster, Gregory Farquhar, Triantafyllos Afouras, Nantas Nardelli, and Shimon Whiteson. Counterfactual Multi-Agent Policy Gradients. In Proceedings of AAAI conference on artificial intelligence, volume 32, 2018."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2002.1039866"},{"key":"e_1_3_2_1_14_1","first-page":"1","volume-title":"Shize Zhang. Distributed and Adaptive Traffic Engineering with Deep Reinforcement Learning. In Proceedings of IEEE\/ACM International Symposium on Quality of Service (IWQOS)","author":"Geng Nan","year":"2021","unstructured":"Nan Geng, Mingwei Xu, Yuan Yang, Chenyi Liu, Jiahai Yang, Qi Li, and Shize Zhang. Distributed and Adaptive Traffic Engineering with Deep Reinforcement Learning. In Proceedings of IEEE\/ACM International Symposium on Quality of Service (IWQOS), pages 1--10, 2021."},{"key":"e_1_3_2_1_15_1","first-page":"1263","volume-title":"Dahl. Neural Message Passing for Quantum Chemistry. In International Conference on Machine Learning","author":"Gilmer Justin","year":"2017","unstructured":"Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. Neural Message Passing for Quantum Chemistry. In International Conference on Machine Learning, pages 1263--1272. PMLR, 2017."},{"key":"e_1_3_2_1_16_1","volume-title":"Cloud Tensor Processing Units (TPUs)","author":"Cloud Google","year":"2022","unstructured":"Google Cloud. Cloud Tensor Processing Units (TPUs), 2022."},{"key":"e_1_3_2_1_17_1","volume-title":"Gurobi Optimizer Reference Manual","author":"Optimization Gurobi","year":"2022","unstructured":"Gurobi Optimization, LLC. Gurobi Optimizer Reference Manual, 2022."},{"key":"e_1_3_2_1_18_1","volume-title":"Representation Learning on Graphs: Methods and Applications. arXiv preprint arXiv:1709.05584","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton, Rex Ying, and Jure Leskovec. Representation Learning on Graphs: Methods and Applications. arXiv preprint arXiv:1709.05584, 2017."},{"key":"e_1_3_2_1_19_1","first-page":"23","article-title":"Direct Loss Minimization for Structured Prediction","author":"Hazan Tamir","year":"2010","unstructured":"Tamir Hazan, Joseph Keshet, and David McAllester. Direct Loss Minimization for Structured Prediction. Advances in Neural Information Processing Systems, 23, 2010.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","first-page":"15","article-title":"Stochastic neighbor embedding","author":"Hinton Geoffrey E.","year":"2002","unstructured":"Geoffrey E. Hinton and Sam Roweis. Stochastic neighbor embedding. Advances in Neural Information Processing Systems, 15, 2002.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486012"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of ACM SIGCOMM","author":"Hong Chi-Yao","year":"2018","unstructured":"Chi-Yao Hong, Subhasree Mandal, Mohammad A. Alfares, Min Zhu, Rich Alimi, Kondapa Naidu Bollineni, Chandan Bhagat, Sourabh Jain, Jay Kaimal, Jeffrey Liang, Kirill Mendelev, Steve Padgett, Faro Thomas Rabe, Saikat Ray, Malveeka Tewari, Matt Tierney, Monika Zahn, Jon Zolla, Joon Ong, and Amin Vahdat. B4 and After: Managing Hierarchy, Partitioning, and Asymmetry for Availability and Scale in Google's Software-Defined WAN. In Proceedings of ACM SIGCOMM, 2018."},{"key":"e_1_3_2_1_23_1","unstructured":"IBM. CPLEX Optimizer 2022."},{"key":"e_1_3_2_1_24_1","volume-title":"Nvidia Whitepaper","author":"Learning Inference Based Deep","year":"2015","unstructured":"GPU-Based Deep Learning Inference and Based Deep Learning. A Performance and Power Analysis. Nvidia Whitepaper, Nov, 2015."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486019"},{"key":"e_1_3_2_1_26_1","first-page":"3050","volume-title":"Aviv Tamar. A Deep Reinforcement Learning Perspective on Internet Congestion Control. In International Conference on Machine Learning","author":"Jay Nathan","year":"2019","unstructured":"Nathan Jay, Noga Rotman, Brighten Godfrey, Michael Schapira, and Aviv Tamar. A Deep Reinforcement Learning Perspective on Internet Congestion Control. In International Conference on Machine Learning, pages 3050--3059. PMLR, 2019."},{"key":"e_1_3_2_1_27_1","first-page":"675","volume-title":"Trevor Darrell. Caffe: Convolutional Architecture for Fast Feature Embedding. In Proceedings of the 22nd ACM international conference on Multimedia","author":"Jia Yangqing","year":"2014","unstructured":"Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. Caffe: Convolutional Architecture for Fast Feature Embedding. In Proceedings of the 22nd ACM international conference on Multimedia, pages 675--678, 2014."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1090191.1080122"},{"key":"e_1_3_2_1_29_1","volume-title":"Kingma and Jimmy Ba. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980, 2014."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.111002"},{"key":"e_1_3_2_1_31_1","first-page":"12","author":"Konda Vijay","year":"1999","unstructured":"Vijay Konda and John Tsitsiklis. Actor-Critic Algorithms. Advances in Neural Information Processing Systems, 12, 1999.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","first-page":"4","volume-title":"K\u00f6ppen. The Curse of Dimensionality. In Proceedings of Online World Conference on Soft Computing in Industrial Applications (WSC)","volume":"1","author":"Mario","year":"2000","unstructured":"Mario K\u00f6ppen. The Curse of Dimensionality. In Proceedings of Online World Conference on Soft Computing in Industrial Applications (WSC), volume 1, pages 4--8, 2000."},{"key":"e_1_3_2_1_33_1","first-page":"325","volume-title":"Himanshu Raj. Decentralized Cloud Wide-Area Network Traffic Engineering with BLASTSHIELD. In Proceedings of USENIX NSDI","author":"Krishnaswamy Umesh","year":"2022","unstructured":"Umesh Krishnaswamy, Rachee Singh, Nikolaj Bj\u00f8rner, and Himanshu Raj. Decentralized Cloud Wide-Area Network Traffic Engineering with BLASTSHIELD. In Proceedings of USENIX NSDI, pages 325--338, Renton, WA, April 2022. USENIX Association."},{"key":"e_1_3_2_1_34_1","first-page":"515","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Krishnaswamy Umesh","year":"2023","unstructured":"Umesh Krishnaswamy, Rachee Singh, Paul Mattes, Paul-Andre C. Bissonnette, Nikolaj Bj\u00f8rner, Zahira Nasrin, Sonal Kothari, Prabhakar Reddy, John Abeln, Srikanth Kandula, et al. OneWAN Is Better than Two: Unifying a Split WAN Architecture. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 515--529, 2023."},{"key":"e_1_3_2_1_35_1","first-page":"1","volume-title":"Cloud Resource Demand Prediction Using Differential Evolution Based Learning","author":"Kumar Jitendra","year":"2019","unstructured":"Jitendra Kumar and Ashutosh Kumar Singh. Cloud Resource Demand Prediction Using Differential Evolution Based Learning. In Proceedings of IEEE International Conference on Smart Computing & Communications (ICSCC), pages 1--5. IEEE, 2019."},{"key":"e_1_3_2_1_36_1","volume-title":"Traffic Prediction with Advanced Graph Neural Networks","author":"Lange Oliver","year":"2020","unstructured":"Oliver Lange and Luis Perez. Traffic Prediction with Advanced Graph Neural Networks, 2020."},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of NeurIPS Workshop on Automated Knowledge Base Construction (AKBC)","author":"Lee Jay Yoon","year":"2017","unstructured":"Jay Yoon Lee, Michael L. Wick, Jean-Baptiste Tristan, and Jaime G. Carbonell. Enforcing Output Constraints via SGD: A Step Towards Neural Lagrangian Relaxation. In Proceedings of NeurIPS Workshop on Automated Knowledge Base Construction (AKBC), 2017."},{"key":"e_1_3_2_1_38_1","first-page":"527","volume-title":"Proceedings of ACM SIGCOMM","author":"Liu Hongqiang Harry","year":"2014","unstructured":"Hongqiang Harry Liu, Srikanth Kandula, Ratul Mahajan, Ming Zhang, and David Gelernter. Traffic Engineering with Forward Fault Correction. In Fabi\u00e1n E. Bustamante, Y. Charlie Hu, Arvind Krishnamurthy, and Sylvia Ratnasamy, editors, Proceedings of ACM SIGCOMM, pages 527--538. ACM, 2014."},{"key":"e_1_3_2_1_39_1","first-page":"430","volume-title":"Hua Shao. Automated Traffic Engineering in SDWAN: Beyond Reinforcement Learning. In IEEE INFOCOM WKSHPS Workshops","author":"Liu Libin","year":"2020","unstructured":"Libin Liu, Li Chen, Hong Xu, and Hua Shao. Automated Traffic Engineering in SDWAN: Beyond Reinforcement Learning. In IEEE INFOCOM WKSHPS Workshops, pages 430--435, 2020."},{"key":"e_1_3_2_1_40_1","first-page":"1","volume-title":"Prasanna Balaprakash. Dynamic Graph Neural Network for Traffic Forecasting in Wide Area Networks. In Proceedings of IEEE International Conference on Big Data (Big Data)","author":"Mallick Tanwi","year":"2020","unstructured":"Tanwi Mallick, Mariam Kiran, Bashir Mohammed, and Prasanna Balaprakash. Dynamic Graph Neural Network for Traffic Forecasting in Wide Area Networks. In Proceedings of IEEE International Conference on Big Data (Big Data), pages 1--10. IEEE, 2020."},{"key":"e_1_3_2_1_41_1","first-page":"197","volume-title":"Mohammad Alizadeh. Neural Adaptive Video Streaming with Pensieve. In Proceedings of ACM SIGCOMM","author":"Mao Hongzi","year":"2017","unstructured":"Hongzi Mao, Ravi Netravali, and Mohammad Alizadeh. Neural Adaptive Video Streaming with Pensieve. In Proceedings of ACM SIGCOMM, pages 197--210, 2017."},{"key":"e_1_3_2_1_42_1","first-page":"14424","volume-title":"Christian Claudel. Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction. In Proceedings of IEEE\/CVF CVPR","author":"Mohamed Abduallah","year":"2020","unstructured":"Abduallah Mohamed, Kun Qian, Mohamed Elhoseiny, and Christian Claudel. Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction. In Proceedings of IEEE\/CVF CVPR, pages 14424--14432, 2020."},{"key":"e_1_3_2_1_43_1","first-page":"1","volume-title":"DeepRoute on Chameleon: Experimenting with Large-Scale Reinforcement Learning and SDN on Chameleon Testbed","author":"Mohammed Bashir","year":"2019","unstructured":"Bashir Mohammed, Mariam Kiran, and Nandini Krishnaswamy. DeepRoute on Chameleon: Experimenting with Large-Scale Reinforcement Learning and SDN on Chameleon Testbed. In Proceedings of IEEE International Conference on Network Protocols (ICNP), pages 1--2, 2019."},{"key":"e_1_3_2_1_44_1","volume-title":"Solving Mixed Integer Programs Using Neural Networks. arXiv preprint arXiv:2012.13349","author":"Nair Vinod","year":"2020","unstructured":"Vinod Nair, Sergey Bartunov, Felix Gimeno, Ingrid von Glehn, Pawel Lichocki, Ivan Lobov, Brendan O'Donoghue, Nicolas Sonnerat, Christian Tjandraatmadja, Pengming Wang, et al. Solving Mixed Integer Programs Using Neural Networks. arXiv preprint arXiv:2012.13349, 2020."},{"key":"e_1_3_2_1_45_1","first-page":"138","volume-title":"Srikanth Kandula. Minding the Gap Between Fast Heuristics and Their Optimal Counterparts. In Proceedings of the 21st ACM Workshop on Hot Topics in Networks","author":"Namyar Pooria","year":"2022","unstructured":"Pooria Namyar, Behnaz Arzani, Ryan Beckett, Santiago Segarra, Himanshu Raj, and Srikanth Kandula. Minding the Gap Between Fast Heuristics and Their Optimal Counterparts. In Proceedings of the 21st ACM Workshop on Hot Topics in Networks, pages 138--144, 2022."},{"key":"e_1_3_2_1_46_1","first-page":"521","volume-title":"Matei Zaharia. Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP. In Proceedings of ACM SOSP","author":"Narayanan Deepak","year":"2021","unstructured":"Deepak Narayanan, Fiodar Kazhamiaka, Firas Abuzaid, Peter Kraft, Akshay Agrawal, Srikanth Kandula, Stephen Boyd, and Matei Zaharia. Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP. In Proceedings of ACM SOSP, pages 521--537, 2021."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/5992.814654"},{"key":"e_1_3_2_1_48_1","first-page":"8024","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems, pages 8024--8035, 2019."},{"key":"e_1_3_2_1_49_1","first-page":"1557","volume-title":"Aviv Tamar. DOTE: Rethinking (Predictive) Wan Traffic Engineering. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Perry Yarin","year":"2023","unstructured":"Yarin Perry, Felipe Vieira Frujeri, Chaim Hoch, Srikanth Kandula, Ishai Menache, Michael Schapira, and Aviv Tamar. DOTE: Rethinking (Predictive) Wan Traffic Engineering. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23), pages 1557--1581, 2023."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00033"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098853"},{"key":"e_1_3_2_1_52_1","first-page":"201","volume-title":"Paramvir Bahl. Cost-Effective Cloud Edge Traffic Engineering With Cascara. In Proceedings of USENIX NSDI","author":"Singh Rachee","year":"2021","unstructured":"Rachee Singh, Sharad Agarwal, Matt Calder, and Paramvir Bahl. Cost-Effective Cloud Edge Traffic Engineering With Cascara. In Proceedings of USENIX NSDI, pages 201--216, 2021."},{"key":"e_1_3_2_1_53_1","first-page":"547","volume-title":"Phillipa Gill. RADWAN: Rate Adaptive Wide Area Network. In Proceedings of ACM SIGCOMM","author":"Singh Rachee","year":"2018","unstructured":"Rachee Singh, Manya Ghobadi, Klaus-Tycho Foerster, Mark Filer, and Phillipa Gill. RADWAN: Rate Adaptive Wide Area Network. In Proceedings of ACM SIGCOMM, page 547--560, New York, NY, USA, 2018. Association for Computing Machinery."},{"key":"e_1_3_2_1_54_1","first-page":"2169","volume-title":"International Conference on Machine Learning","author":"Song Yang","year":"2016","unstructured":"Yang Song, Alexander Schwing, Raquel Urtasun, et al. Training Deep Neural Networks via Direct Loss Minimization. In International Conference on Machine Learning, pages 2169--2177. PMLR, 2016."},{"key":"e_1_3_2_1_55_1","first-page":"12","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","author":"Sutton Richard S.","year":"1999","unstructured":"Richard S. Sutton, David McAllester, Satinder Singh, and Yishay Mansour. Policy Gradient Methods for Reinforcement Learning with Function Approximation. Advances in Neural Information Processing Systems, 12, 1999.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_56_1","volume-title":"An End-to-End Open Source Machine Learning Platform","year":"2022","unstructured":"Tensorflow. An End-to-End Open Source Machine Learning Platform, 2022."},{"key":"e_1_3_2_1_57_1","volume-title":"Open Neural Network Exchange","author":"Foundation The Linux","year":"2022","unstructured":"The Linux Foundation. Open Neural Network Exchange, 2022."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"e_1_3_2_1_59_1","volume-title":"NIPS Deep Reinforcement Learning Symposium","author":"Valadarsky Asaf","year":"2017","unstructured":"Asaf Valadarsky, Michael Schapira, Dafna Shahaf, and Aviv Tamar. Learning to route with deep RL. In NIPS Deep Reinforcement Learning Symposium, 2017."},{"issue":"7782","key":"e_1_3_2_1_60_1","first-page":"350","article-title":"Grandmaster Level","volume":"575","author":"Vinyals Oriol","year":"2019","unstructured":"Oriol Vinyals, Igor Babuschkin, Wojciech M. Czarnecki, Micha\u00ebl Mathieu, Andrew Dudzik, Junyoung Chung, David H. Choi, Richard Powell, Timo Ewalds, Petko Georgiev, et al. Grandmaster Level in StarCraft II Using Multi-Agent Reinforcement Learning. Nature, 575(7782):350--354, 2019.","journal-title":"StarCraft II Using Multi-Agent Reinforcement Learning. Nature"},{"key":"e_1_3_2_1_61_1","first-page":"99","volume-title":"Albert Greenberg. COPE: Traffic Engineering in Dynamic Networks. In Proceedings of the 2006 conference on Applications, technologies, architectures, and protocols for computer communications","author":"Wang Hao","year":"2006","unstructured":"Hao Wang, Haiyong Xie, Lili Qiu, Yang Richard Yang, Yin Zhang, and Albert Greenberg. COPE: Traffic Engineering in Dynamic Networks. In Proceedings of the 2006 conference on Applications, technologies, architectures, and protocols for computer communications, pages 99--110, 2006."},{"key":"e_1_3_2_1_62_1","first-page":"355","volume-title":"Modeling Complexity in Economic and Social Systems","author":"David","year":"2002","unstructured":"David H. Wolpert and Kagan Tumer. Optimal Payoff Functions for Members of Collectives. In Modeling Complexity in Economic and Social Systems, pages 355--369. World Scientific, 2002."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/65.826369"},{"key":"e_1_3_2_1_65_1","volume-title":"Chi Harold Liu, and Dejun Yang. Experience-Driven Networking: A Deep Reinforcement Learning Based Approach. CoRR, abs\/1801.05757","author":"Xu Zhiyuan","year":"2018","unstructured":"Zhiyuan Xu, Jian Tang, Jingsong Meng, Weiyi Zhang, Yanzhi Wang, Chi Harold Liu, and Dejun Yang. Experience-Driven Networking: A Deep Reinforcement Learning Based Approach. CoRR, abs\/1801.05757, 2018."},{"key":"e_1_3_2_1_66_1","first-page":"495","volume-title":"Keith Winstein. Learning in Situ: A Randomized Experiment in Video Streaming. In Proceedings of USENIX NSDI","author":"Yan Francis Y.","year":"2020","unstructured":"Francis Y. Yan, Hudson Ayers, Chenzhi Zhu, Sadjad Fouladi, James Hong, Keyi Zhang, Philip Levis, and Keith Winstein. Learning in Situ: A Randomized Experiment in Video Streaming. In Proceedings of USENIX NSDI, pages 495--511, Santa Clara, CA, February 2020. USENIX Association."},{"key":"e_1_3_2_1_67_1","first-page":"731","volume-title":"Keith Winstein. Pantheon: the Training Ground for Internet Congestion-Control Research. In Proceedings of USENIX ATC","author":"Yan Francis Y.","year":"2018","unstructured":"Francis Y. Yan, Jestin Ma, Greg D. Hill, Deepti Raghavan, Riad S. Wahby, Philip Levis, and Keith Winstein. Pantheon: the Training Ground for Internet Congestion-Control Research. In Proceedings of USENIX ATC, pages 731--743, Boston, MA, July 2018. USENIX Association."},{"key":"e_1_3_2_1_68_1","first-page":"432","volume-title":"Reliability and Programmability for Global Internet Peering. In Proceedings of ACM SIGCOMM","author":"Yap Kok-Kiong","year":"2017","unstructured":"Kok-Kiong Yap, Murtaza Motiwala, Jeremy Rahe, Steve Padgett, Matthew Holliman, Gary Baldus, Marcus Hines, Taeeun Kim, Ashok Narayanan, Ankur Jain, et al. Taking the Edge off with Espresso: Scale, Reliability and Programmability for Global Internet Peering. In Proceedings of ACM SIGCOMM, pages 432--445, 2017."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000371"},{"key":"e_1_3_2_1_70_1","first-page":"560","volume-title":"Ying Zhang. ARROW: Restoration-Aware Traffic Engineering. In Proceedings of ACM SIGCOMM","author":"Zhong Zhizhen","year":"2021","unstructured":"Zhizhen Zhong, Manya Ghobadi, Alaa Khaddaj, Jonathan Leach, Yiting Xia, and Ying Zhang. ARROW: Restoration-Aware Traffic Engineering. In Proceedings of ACM SIGCOMM, page 560--579, New York, NY, USA, 2021. Association for Computing Machinery."},{"key":"e_1_3_2_1_71_1","first-page":"258","volume-title":"Xin Jin. Network Planning with Deep Reinforcement Learning. In Proceedings of ACM SIGCOMM","author":"Zhu Hang","year":"2021","unstructured":"Hang Zhu, Varun Gupta, Satyajeet Singh Ahuja, Yuandong Tian, Ying Zhang, and Xin Jin. Network Planning with Deep Reinforcement Learning. In Proceedings of ACM SIGCOMM, pages 258--271, 2021."}],"event":{"name":"ACM SIGCOMM '23: ACM SIGCOMM 2023 Conference","location":"New York NY USA","acronym":"ACM SIGCOMM '23","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2023 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603269.3604857","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603269.3604857","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603269.3604857","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:42Z","timestamp":1750178802000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603269.3604857"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":71,"alternative-id":["10.1145\/3603269.3604857","10.1145\/3603269"],"URL":"https:\/\/doi.org\/10.1145\/3603269.3604857","relation":{},"subject":[],"published":{"date-parts":[[2023,9]]},"assertion":[{"value":"2023-09-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}