{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:40:33Z","timestamp":1772725233139,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,5,1]]},"DOI":"10.1587\/transinf.2021dap0010","type":"journal-article","created":{"date-parts":[[2022,4,30]],"date-time":"2022-04-30T22:17:13Z","timestamp":1651357033000},"page":"936-945","source":"Crossref","is-referenced-by-count":9,"title":["Multi-Agent Reinforcement Learning for Cooperative Task Offloading in Distributed Edge Cloud Computing"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Shiyao","family":"DING","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University"}]},{"given":"Donghui","family":"LIN","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] M. Marjani, F. Nasaruddin, A. Gani, A. Karim, I.A.T. Hashem, A. Siddiqa, and I. Yaqoob, \u201cBig IoT data analytics: Architecture, opportunities, and open research challenges,\u201d IEEE Access, vol.5, pp.5247-5261, 2017. 10.1109\/access.2017.2689040","DOI":"10.1109\/ACCESS.2017.2689040"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] X. Tao, K. Ota, M. Dong, H. Qi, and K. Li, \u201cPerformance guaranteed computation offloading for mobile-edge cloud computing,\u201d IEEE Wireless Commun. Lett., vol.6, no.6, pp.774-777, 2017. 10.1109\/lwc.2017.2740927","DOI":"10.1109\/LWC.2017.2740927"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] H. Chang, A. Hari, S. Mukherjee, and T. Lakshman, \u201cBringing the cloud to the edge,\u201d IEEE Conference on Computer Communications Workshops, pp.346-351, 2014. 10.1109\/infcomw.2014.6849256","DOI":"10.1109\/INFCOMW.2014.6849256"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] S. Li and J. Huang, \u201cEnergy efficient resource management and task scheduling for IoT services in edge computing paradigm,\u201d IEEE International Symposium on Parallel and Distributed Processing with Applications, pp.846-851, 2017. 10.1109\/ispa\/iucc.2017.00129","DOI":"10.1109\/ISPA\/IUCC.2017.00129"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] X. Chen, L. Jiao, W. Li, and X. Fu, \u201cEfficient multi-user computation offloading for mobile-edge cloud computing,\u201d IEEE\/ACM Trans. Netw., vol.24, no.5, pp.2795-2808, 2015. 10.1109\/tnet.2015.2487344","DOI":"10.1109\/TNET.2015.2487344"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] X. Liu, J. Yu, J. Wang, and Y. Gao, \u201cResource offloading with edge computing in IoT networks via machine learning,\u201d IEEE Internet Things J., vol.7, no.4, pp.3415-3426, 2020. 10.1109\/jiot.2020.2970110","DOI":"10.1109\/JIOT.2020.2970110"},{"key":"7","doi-asserted-by":"publisher","unstructured":"[7] X. Chen, H. Zhang, C. Wu, S. Mao, Y. Ji, and M. Bennis, \u201cOptimized computation offloading performance in virtual edge computing systems via deep reinforcement learning,\u201d IEEE Internet Things J., vol.6, no.3, pp.4005-4018, 2018. 10.1109\/jiot.2018.2876279","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] H. Nishi, \u201cInformation and communication platform for providing smart community services: System implementation and use case in Saitama city,\u201d IEEE International Conference on Industrial Technology, pp.1375-1380, 2018. 10.1109\/icit.2018.8352380","DOI":"10.1109\/ICIT.2018.8352380"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] S. Donovan, J. Chung, M. Sanders, and R. Clark, \u201cMetroSDX: A resilient edge network for the smart community,\u201d IEEE International Conference on Pervasive Computing and Communications Workshops, pp.575-580, 2017. 10.1109\/percomw.2017.7917626","DOI":"10.1109\/PERCOMW.2017.7917626"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] A.A. Abdellatif, A. Mohamed, C.F. Chiasserini, M. Tlili, and A. Erbad, \u201cEdge computing for smart health: Context-aware approaches, opportunities, and challenges,\u201d IEEE Netw., vol.33, no.3, pp.196-203, 2019. 10.1109\/mnet.2019.1800083","DOI":"10.1109\/MNET.2019.1800083"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] F. Bonomi, R. Milito, J. Zhu, and S. Addepalli, \u201cFog computing and its role in the internet of things,\u201d Proc. First Edition of the MCC Workshop on Mobile Cloud Computing, pp.13-16, 2012. 10.1145\/2342509.2342513","DOI":"10.1145\/2342509.2342513"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, \u201cEdge computing: Vision and challenges,\u201d IEEE Internet Things J., vol.3, no.5, pp.637-646, 2016. 10.1109\/jiot.2016.2579198","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"13","doi-asserted-by":"publisher","unstructured":"[13] Z. Chen and X. Wang, \u201cDecentralized computation offloading for multi-user mobile edge computing: A deep reinforcement learning approach,\u201d EURASIP Journal on Wireless Communications and Networking, pp.1-21, 2020. 10.1186\/s13638-020-01801-6","DOI":"10.1186\/s13638-020-01801-6"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] Y. Wen, W. Zhang, and H. Luo, \u201cEnergy-optimal mobile application execution: Taming resource-poor mobile devices with cloud clones,\u201d IEEE International Conference on Computer Communications, pp.2716-2720, 2012. 10.1109\/INFCOM.2012.6195685","DOI":"10.1109\/INFCOM.2012.6195685"},{"key":"15","doi-asserted-by":"publisher","unstructured":"[15] D. L\u00f3pez-P\u00e9rez, X. Chu, A.V. Vasilakos, and H. Claussen, \u201cOn distributed and coordinated resource allocation for interference mitigation in self-organizing LTE networks,\u201d IEEE\/ACM Trans. Netw., vol.21, no.4, pp.1145-1158, 2013. 10.1109\/tnet.2012.2218124","DOI":"10.1109\/TNET.2012.2218124"},{"key":"16","doi-asserted-by":"publisher","unstructured":"[16] M. Xiao, N.B. Shroff, and E.K.P. Chong, \u201cA utility-based power-control scheme in wireless cellular systems,\u201d IEEE\/ACM Trans. Netw., vol.11, no.2, pp.210-221, 2003. 10.1109\/tnet.2003.810314","DOI":"10.1109\/TNET.2003.810314"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] M. Chiang, P. Hande, T. Lan, and C.W. Tan, Power control in wireless cellular networks, Now Foundations and Trends, 2008. 10.1561\/9781601981370","DOI":"10.1561\/9781601981370"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] F.A. Oliehoek and C. Amato, A concise introduction to decentralized POMDPs, Springer Briefs in Intelligent Systems, Springer, 2016. 10.1007\/978-3-319-28929-8","DOI":"10.1007\/978-3-319-28929-8"},{"key":"19","doi-asserted-by":"publisher","unstructured":"[19] A. Tampuu, T. Matiisen, D. Kodelja, I. Kuzovkin, K. Korjus, J. Aru, J. Aru, R. Vicente, \u201cMultiagent cooperation and competition with deep reinforcement learning,\u201d PloS One, vol.12, no.4, e0172395, 2017. 10.1371\/journal.pone.0172395","DOI":"10.1371\/journal.pone.0172395"},{"key":"20","unstructured":"[20] M. Hausknecht and P. Stone, \u201cDeep recurrent Q-learning for partially observable MDPs,\u201d AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents, pp.29-37, 2015."},{"key":"21","doi-asserted-by":"publisher","unstructured":"[21] X. Liu, J. Yu, Z. Feng, and Y. Gao, \u201cMulti-agent reinforcement learning for resource allocation in IoT networks with edge computing,\u201d China Communications, vol.17, no.9, pp.220-236, 2020. 10.23919\/jcc.2020.09.017","DOI":"10.23919\/JCC.2020.09.017"},{"key":"22","unstructured":"[22] P. Sunehag, G. Lever, A. Gruslys, W.M. Czarnecki, V. Zambaldi, M. Jaderberg, M. Lanctot, N. Sonnerat, J.Z. Leibo, K. Tuyls, and T. Graepel, \u201cValue-decomposition networks for cooperative multiagent learning based on team reward,\u201d The 17th International Conference on Autonomous Agents and Multiagent Systems, no.3, pp.2085-2087, 2017."},{"key":"23","unstructured":"[23] T. Rashid, M. Samvelyan, C. Schroeder, G. Farquhar, J. Foerster, and S. Whiteson, \u201cQmix: Monotonic value function factorisation for deep multi-agent reinforcement learning,\u201d International Conference on Machine Learning, pp.4295-4304, 2018."},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] C.J.C.H Watkins and P. Dayan, \u201cQ-learning,\u201d Machine Learning, vol.8, no.3-4, pp.279-292, 1992. 10.1007\/BF00992698","DOI":"10.1007\/BF00992698"},{"key":"25","doi-asserted-by":"publisher","unstructured":"[25] 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":"26","unstructured":"[26] C. Reiss, J. Wilkes, and J.L. Hellerstein, \u201cGoogle cluster-usage traces: Format + schema. Technical report,\u201d Google Inc., Mountain View, CA, USA, 2011."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] F. Jiang, W. Liu, J. Wang, and X. Liu, \u201cQ-learning based task offloading and resource allocation scheme for internet of vehicles,\u201d IEEE\/CIC International Conference on Communications in China, pp.460-465, 2020. 10.1109\/iccc49849.2020.9238925","DOI":"10.1109\/ICCC49849.2020.9238925"},{"key":"28","doi-asserted-by":"crossref","unstructured":"[28] S. Barbarossa, S. Sardellitti, and P.D. Lorenzo, \u201cJoint allocation of computation and communication resources in multiuser mobile cloud computing,\u201d IEEE 14th Workshop Signal Process. Adv. Wireless Commun., pp.26-30, 2013. 10.1109\/spawc.2013.6612005","DOI":"10.1109\/SPAWC.2013.6612005"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/5\/E105.D_2021DAP0010\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,7]],"date-time":"2022-05-07T04:39:30Z","timestamp":1651898370000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/5\/E105.D_2021DAP0010\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,1]]},"references-count":28,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2021dap0010","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,1]]},"article-number":"2021DAP0010"}}