{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T03:18:06Z","timestamp":1778901486892,"version":"3.51.4"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Commun."],"published-print":{"date-parts":[[2021,1,1]]},"DOI":"10.1587\/transcom.2020ebp3061","type":"journal-article","created":{"date-parts":[[2020,6,28]],"date-time":"2020-06-28T22:05:18Z","timestamp":1593381918000},"page":"20-26","source":"Crossref","is-referenced-by-count":5,"title":["Optimal Planning of Emergency Communication Network Using Deep Reinforcement Learning"],"prefix":"10.23919","volume":"E104.B","author":[{"given":"Changsheng","family":"YIN","sequence":"first","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruopeng","family":"YANG","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"ZHU","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"ZOU","sequence":"additional","affiliation":[{"name":"National University of Defense Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junda","family":"ZHANG","sequence":"additional","affiliation":[{"name":"Naval Aviation University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] F. Chiti, R. Fantacci, L. Maccari, D. Marabissi, and D. Tarchi, \u201cA broadband wireless communication system for emergency management,\u201d IEEE Wireless Commun., vol.15, no.3, pp.8-14, 2008. 10.1109\/mwc.2008.4547517","DOI":"10.1109\/MWC.2008.4547517"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] M. Abd-El-Barr, \u201cTopological network design: A survey,\u201d J. Netw. Comput. Appl., vol.32, no.3, pp.501-509, 2009. 10.1016\/j.jnca.2008.12.001","DOI":"10.1016\/j.jnca.2008.12.001"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] M. Abd-El-Barr, A. Zakir, S.M. Sait, and A. Almulhem, \u201cReliability and fault tolerance based topological optimization of computer networks \u2014 Part II: Iterative techniques,\u201d IEEE Pacific Rim Conference, pp.736-739, Victoria, BC, Canada, Aug. 2003. 10.1109\/pacrim.2003.1235886","DOI":"10.1109\/PACRIM.2003.1235886"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] L. He and N. Mort, \u201cHybrid genetic algorithms for telecommunications network back-up routing,\u201d BT Technol. J., vol.18, no.4, pp.42-50, 2000. 10.1023\/a:1026702624501","DOI":"10.1023\/A:1026702624501"},{"key":"5","unstructured":"[5] V. Grout, S. Cunningham, and R. Picking, \u201cPractical large-scale network design with variable costs for links and switches,\u201d Int. J. Comput. Sci. Netw. Secur., vol.7, no.7, pp.113-125, 2007."},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] D.N. Le, N.G. Nguyen, N.H. Dinh, N.D. Le, and V.T. Le, \u201cOptimizing gateway placement in wireless mesh networks based on ACO algorithm,\u201d Int. J. Comput. Commun. Eng., vol.2, no.2, pp.143-147, 2013. 10.7763\/ijcce.2013.v2.157","DOI":"10.7763\/IJCCE.2013.V2.157"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] A. Kamar, S.J. Nawaz, M. Patwary, M. Abdel-Maguid, and S.-U.-R. Qureshi, \u201cOptimized algorithm for cellular network planning based on terrain and demand analysis,\u201d Proc. International Conference on Computer Technologies and Development, pp.359-364, 2010. 10.1109\/icctd.2010.5645854","DOI":"10.1109\/ICCTD.2010.5645854"},{"key":"8","unstructured":"[8] Y. Zhou, \u201cResearch on node deployment and topology optimization strategy in FSO-based 5G backhaul networks,\u201d Beijing University of Posts and Telecommunications, 2019."},{"key":"9","unstructured":"[9] W. Wu, \u201cResearch on topology planning for multi-interface multi-channel wireless mesh networks,\u201d Southeast University, 2013."},{"key":"10","unstructured":"[10] Z.H. Zhou, Machine Learning, Tsinghua University Press, Beijing, 2016."},{"key":"11","doi-asserted-by":"publisher","unstructured":"[11] Y. LeCun, Y. Bengio, and G. Hinton, \u201cDeep learning,\u201d Nature, vol.521, no.7553, pp.436-444, 2015. 10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"12","unstructured":"[12] J. Ferret, R. Marinier, M. Geist, and O. Pietquin, \u201cCredit assignment as a proxy for transfer in reinforcement learning,\u201d [EB\/OL]. [2019-7-18]. https:\/\/arxiv.org\/abs\/1907.08027v1"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] M. Jaderberg, W.M. Czarnecki, I. Dunning, L. Marris, G. Lever, A.G. Casta\u00f1eda, C. Beattie, N.C. Rabinowitz, A.S. Morcos, A. Ruderman, N. Sonnerat, T. Green, L. Deason, J.Z. Leibo, D. Silver, D. Hassabis, K. Kavukcuoglu, and T. Graepel, \u201cHuman-level performance in 3D multiplayer games with population-based reinforcement learning,\u201d Science, vol.364, no.6443, pp.859-865, 2019. 10.1126\/science.aau6249","DOI":"10.1126\/science.aau6249"},{"key":"14","unstructured":"[14] R.S. Sutton and A.G. Barto, Reinforcement Learning: An Introduction, Massachusetts Institute of Technology Press, Cambridge, USA, 1998."},{"key":"15","unstructured":"[15] H.H. Van, A. Guez, and D. Silver, \u201cDeep reinforcement learning with double Q learning,\u201d Proc. AAAI Conference on Artificial Intelligence, pp.2094-2100, 2016."},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] 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. Driessche, T. Graepel, and D. Hassabis, \u201cMastering the game of go without human knowledge,\u201d Nature, vol.550, no.7676, pp.354-391, 2017. 10.1038\/nature24270","DOI":"10.1038\/nature24270"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] K. Shao, Y. Zhu, and D. Zhao, \u201cStarCraft micromanagement with reinforcement learning and curriculum transfer learning,\u201d IEEE Trans. Emerg. Topics Comput. Intell., vol.3, no.1, pp.73-84, 2019. 10.1109\/tetci.2018.2823329","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"18","unstructured":"[18] C. Clark and A.J. Storkey, \u201cTraining deep convolutional neural networks to play go,\u201d Proc. 32nd International Conference on International Conference on Machine Learning, vol.37, pp.1766-1774, 2015."},{"key":"19","unstructured":"[19] S.Q. Liu, G. Lever, J. Merel, S. Tunyasuvunakool, N. Heess, and T. Graepel, \u201cEmergent coordination through competition,\u201d [EB\/OL]. [2019-2-21]. https:\/\/arxiv.org\/abs\/1902.07151"},{"key":"20","unstructured":"[20] M. Fortunato, M. Tan, R. Faulkner, et al., \u201cGeneralization of reinforcement learners with working and episodic memory,\u201d Proc. Advances in Neural Information Processing Systems, pp.12448-12457, 2019."},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] D. Silver, A. Huang, C.J. Maddison, A. Guez, L. Sifre, G.V. Driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, S. Dieleman, D. Grewe, J. Nham, N. Kalchbrenner, I. Sutskever, T. Lillicrap, M. Leach, K. Kavukcuoglu, T. Graepel, and D. Hassabis, \u201cMastering the game of Go with deep neural networks and tree search,\u201d Nature, vol.529, no.7587, pp.484-489, 2016. 10.1038\/nature16961","DOI":"10.1038\/nature16961"},{"key":"22","doi-asserted-by":"publisher","unstructured":"[22] X.B. Peng, G. Berseth, K. Yin, and M. Van De Panne, \u201cDeepLoco: Dynamic locomotion skills using hierarchical deep reinforcement learning,\u201d ACM Trans. Graph., vol.36, no.4, pp.1-13, 2017. 10.1145\/3072959.3073602","DOI":"10.1145\/3072959.3073602"},{"key":"23","unstructured":"[23] B. Scherrer, M. Ghavamzadeh, V. Gabillon, et al., \u201cApproximate muddied policy iteration and its application to the game of tetris,\u201d J. Machine Learning Research, vol.16, no.1, pp.1629-1676, 2015."},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] 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, \u201cHuman-level control through deep reinforcement learning,\u201d Nature, vol.518, no.7540, pp.529-533, 2015. 10.1038\/nature14236","DOI":"10.1038\/nature14236"},{"key":"25","unstructured":"[25] V. Mnih, A.P. Badia, M. Mirza, et al., \u201cAsynchronous methods for deep reinforcement learning,\u201d Proc. 33rd International Conference on Machine Learning, vol.48, pp.1928-1937, 2016."},{"key":"26","unstructured":"[26] A. Krizhevsky, I. Sutskever, and G. Hinton, \u201cImagenet classification with deep convolutional neural networks,\u201d Proc. Advances in Neural Information Processing Systems (NIPS), pp.1097-1105, 2012."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] R. Salakhutdinov, A. Mnih, and G. Hinton, \u201cRestricaed Boltzmann machine for collaborative filtering,\u201d Proc. ACM International Conference Proceeding Series, pp.791-798, 2007. 10.1145\/1273496.1273596","DOI":"10.1145\/1273496.1273596"},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] D. Silver and T. Hubert, \u201cA general reinforcement learning algorithm that masters chess, shogi, and Go through self-play,\u201d Science, vol.362, no.6419, pp.1140-1144, 2018. 10.1126\/science.aar6404","DOI":"10.1126\/science.aar6404"},{"key":"29","doi-asserted-by":"publisher","unstructured":"[13] M. Jaderberg, W.M. Czarnecki, I. Dunning, L. Marris, G. Lever, A.G. Casta\u00f1eda, C. Beattie, N.C. Rabinowitz, A.S. Morcos, A. Ruderman, N. Sonnerat, T. Green, L. Deason, J.Z. Leibo, D. Silver, D. Hassabis, K. Kavukcuoglu, and T. Graepel, \u201cHuman-level performance in 3D multiplayer games with population-based reinforcement learning,\u201d Science, vol.364, no.6443, pp.859-865, 2019. 10.1126\/science.aau6249","DOI":"10.1126\/science.aau6249"},{"key":"30","unstructured":"[30] B. Wu, Q. Fu, J. Liang, P. Qu, X. Li, L. Wang, W. Liu, W. Yang, and Y. Liu, \u201cHierarchical macro strategy model for MOBA game AI,\u201d [EB\/OL]. [2018-12-19]. https:\/\/arxiv.org\/abs\/1812.07887v1"},{"key":"31","doi-asserted-by":"publisher","unstructured":"[31] J. Schmidhuber, \u201cDeep learning in neural networks: An overview,\u201d Neural Networks, vol.61, pp.85-117, 2015. 10.1016\/j.neunet.2014.09.003","DOI":"10.1016\/j.neunet.2014.09.003"}],"container-title":["IEICE Transactions on Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transcom\/E104.B\/1\/E104.B_2020EBP3061\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T16:55:11Z","timestamp":1723136111000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transcom\/E104.B\/1\/E104.B_2020EBP3061\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,1]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.1587\/transcom.2020ebp3061","relation":{},"ISSN":["0916-8516","1745-1345"],"issn-type":[{"value":"0916-8516","type":"print"},{"value":"1745-1345","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,1]]}}}