{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T23:44:02Z","timestamp":1782431042119,"version":"3.54.5"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D program of China","doi-asserted-by":"crossref","award":["2020YFC1523004"],"award-info":[{"award-number":["2020YFC1523004"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s10844-024-00907-3","type":"journal-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T09:03:00Z","timestamp":1730970180000},"page":"567-591","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Multi-agent deep reinforcement learning for computation offloading in cooperative edge network"],"prefix":"10.1007","volume":"63","author":[{"given":"Pengju","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yepeng","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"907_CR1","doi-asserted-by":"publisher","unstructured":"Abbas, N., Zhang, Y., & Taherkordi, A., et al. (2017). Mobile edge computing: A survey. IEEE Internet of Things Journal, 5, 450\u2013465. https:\/\/doi.org\/10.1109\/JIOT.2017.2750180","DOI":"10.1109\/JIOT.2017.2750180"},{"key":"907_CR2","doi-asserted-by":"publisher","unstructured":"Alasmari, K.\u00a0R., Green, R.\u00a0C., & Alam, M. (2018). Mobile edge offloading using markov decision processes. In Edge Computing\u2013EDGE 2018: Second International Conference, Held as Part of the Services Conference Federation, SCF 2018, Seattle, WA, USA, June 25-30, 2018, Proceedings 2 (pp. 80\u201390). Springer. https:\/\/doi.org\/10.1007\/978-3-319-94340-4_6","DOI":"10.1007\/978-3-319-94340-4_6"},{"key":"907_CR3","doi-asserted-by":"publisher","unstructured":"Ale, L., King, S. A., & Zhang, N., et al. (2022). D3pg: Dirichlet ddpg for task partitioning and offloading with constrained hybrid action space in mobile-edge computing. IEEE Internet of Things Journal, 9, 19260\u201319272. https:\/\/doi.org\/10.1109\/JIOT.2022.3166110","DOI":"10.1109\/JIOT.2022.3166110"},{"key":"907_CR4","doi-asserted-by":"publisher","unstructured":"Cang, Y., Chen, M., & Pan, Y., et al. (2024). Joint user scheduling and computing resource allocation optimization in asynchronous mobile edge computing networks. IEEE Transactions on Communications, 72, 3378\u20133392. https:\/\/doi.org\/10.1109\/TCOMM.2024.3358237","DOI":"10.1109\/TCOMM.2024.3358237"},{"key":"907_CR5","doi-asserted-by":"publisher","unstructured":"Chen, M., Guo, A., & Song, C. (2023a). Multi-agent deep reinforcement learning for collaborative task offloading in mobile edge computing networks. Digital Signal Processing, (p. 104127). https:\/\/doi.org\/10.1016\/j.dsp.2023.104127","DOI":"10.1016\/j.dsp.2023.104127"},{"key":"907_CR6","doi-asserted-by":"publisher","unstructured":"Chen, Z., Xiong, B., Chen, X., et\u00a0al. (2024a). Joint computation offloading and resource allocation in multi-edge smart communities with personalized federated deep reinforcement learning. IEEE Transactions on Mobile Computing, (pp. 1\u201316). https:\/\/doi.org\/10.1109\/TMC.2024.3396511","DOI":"10.1109\/TMC.2024.3396511"},{"key":"907_CR7","doi-asserted-by":"publisher","unstructured":"Chen, Z., Zhang, J., Min, G., et\u00a0al. (2024c). Traffic-aware lightweight hierarchical offloading towards adaptive slicing-enabled sagin. IEEE Journal on Selected Areas in Communications, (pp. 1\u20131). https:\/\/doi.org\/10.1109\/JSAC.2024.3459020","DOI":"10.1109\/JSAC.2024.3459020"},{"key":"907_CR8","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1109\/JSAC.2018.2815360","volume":"36","author":"M Chen","year":"2018","unstructured":"Chen, M., & Hao, Y. (2018). Task offloading for mobile edge computing in software defined ultra-dense network. IEEE Journal on Selected Areas in Communications, 36, 587\u2013597. https:\/\/doi.org\/10.1109\/JSAC.2018.2815360","journal-title":"IEEE Journal on Selected Areas in Communications"},{"key":"907_CR9","doi-asserted-by":"publisher","unstructured":"Chen, Z., Hu, J., & Min, G., et al. (2021). Adaptive and efficient resource allocation in cloud datacenters using actor-critic deep reinforcement learning. IEEE Transactions on Parallel and Distributed Systems, 33, 1911\u20131923. https:\/\/doi.org\/10.1109\/TPDS.2021.3132422","DOI":"10.1109\/TPDS.2021.3132422"},{"key":"907_CR10","doi-asserted-by":"publisher","unstructured":"Chen, Y., Li, Z., & Yang, B., et al. (2020). A stackelberg game approach to multiple resources allocation and pricing in mobile edge computing. Future Generation Computer Systems, 108, 273\u2013287. https:\/\/doi.org\/10.1016\/j.future.2020.02.045","DOI":"10.1016\/j.future.2020.02.045"},{"key":"907_CR11","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1109\/MCOM.001.2200223","volume":"61","author":"Z Chen","year":"2023","unstructured":"Chen, Z., & Yu, Z. (2023). Intelligent offloading in blockchain-based mobile crowdsensing using deep reinforcement learning. IEEE Communications Magazine, 61, 118\u2013123. https:\/\/doi.org\/10.1109\/MCOM.001.2200223","journal-title":"IEEE Communications Magazine"},{"key":"907_CR12","doi-asserted-by":"publisher","unstructured":"Chen, Z., Zhang, J., & Huang, Z., et al. (2024). Computation offloading in blockchain-enabled mcs systems: A scalable deep reinforcement learning approach. Future Generation Computer Systems, 153, 301\u2013311. https:\/\/doi.org\/10.1016\/j.future.2023.12.004","DOI":"10.1016\/j.future.2023.12.004"},{"key":"907_CR13","doi-asserted-by":"publisher","unstructured":"Chen, Z., Zhang, J., & Zheng, X., et al. (2023). Profit-aware cooperative offloading in uav-enabled mec systems using lightweight deep reinforcement learning. IEEE Internet of Things Journal, 11, 21325\u201321336. https:\/\/doi.org\/10.1109\/JIOT.2023.3331722","DOI":"10.1109\/JIOT.2023.3331722"},{"key":"907_CR14","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1146\/annurev-statistics-031219-041220","volume":"7","author":"J Clifton","year":"2020","unstructured":"Clifton, J., & Laber, E. (2020). Q-learning: Theory and applications. Annual Review of Statistics and Its Application, 7, 279\u2013301. https:\/\/doi.org\/10.1146\/annurev-statistics-031219-041220","journal-title":"Annual Review of Statistics and Its Application"},{"key":"907_CR15","doi-asserted-by":"publisher","unstructured":"Ding, Z., Huang, Y., Yuan, H., et\u00a0al. (2020). Introduction to reinforcement learning.  Deep reinforcement learning: fundamentals, research and applications, (pp. 47\u2013123). https:\/\/doi.org\/10.1007\/978-981-15-4095-0_2","DOI":"10.1007\/978-981-15-4095-0_2"},{"key":"907_CR16","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1587\/transinf.2021DAP0010","volume":"105","author":"S Ding","year":"2022","unstructured":"Ding, S., & Lin, D. (2022). Multi-agent reinforcement learning for cooperative task offloading in distributed edge cloud computing. IEICE Transactions on Information and Systems, 105, 936\u2013945. https:\/\/doi.org\/10.1587\/transinf.2021DAP0010","journal-title":"IEICE Transactions on Information and Systems"},{"key":"907_CR17","doi-asserted-by":"publisher","first-page":"3425","DOI":"10.1109\/TMC.2022.3141080","volume":"22","author":"Z Gao","year":"2022","unstructured":"Gao, Z., Yang, L., & Dai, Y. (2022). Large-scale computation offloading using a multi-agent reinforcement learning in heterogeneous multi-access edge computing. IEEE Transactions on Mobile Computing, 22, 3425\u20133443. https:\/\/doi.org\/10.1109\/TMC.2022.3141080","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"907_CR18","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MNET.2018.1700139","volume":"32","author":"H Guo","year":"2018","unstructured":"Guo, H., Liu, J., & Qin, H. (2018). Collaborative mobile edge computation offloading for iot over fiber-wireless networks. IEEE Network, 32, 66\u201371. https:\/\/doi.org\/10.1109\/MNET.2018.1700139","journal-title":"IEEE Network"},{"key":"907_CR19","unstructured":"Hernandez-Leal, P., Kartal, B., & Taylor, M. E. (2018). Is multiagent deep reinforcement learning the answer or the question? a brief survey. Learning,21, 22. https:\/\/rbcborealis.com\/research-blogs\/multiagent-reinforcement-learning-answer-or-question-brief-survey\/"},{"key":"907_CR20","doi-asserted-by":"publisher","unstructured":"Jiang, F., Peng, Y., & Wang, K., et al. (2023). Mars: A drl-based multi-task resource scheduling framework for uav with irs-assisted mobile edge computing system. IEEE Transactions on Cloud Computing, 11, 3700\u20133712. https:\/\/doi.org\/10.1109\/TCC.2023.3307582","DOI":"10.1109\/TCC.2023.3307582"},{"key":"907_CR21","doi-asserted-by":"publisher","unstructured":"Li, Y., Yang, C., Deng, M., & et\u00a0al. (2022). A dynamic resource optimization scheme for mec task offloading based on policy gradient. In 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC) (vol.\u00a06, pp. 342\u2013345). IEEE. https:\/\/doi.org\/10.1109\/ITOEC53115.2022.9734566","DOI":"10.1109\/ITOEC53115.2022.9734566"},{"key":"907_CR22","doi-asserted-by":"publisher","unstructured":"Li, X., Da, Xu., L. (2020). A review of internet of things\u2014resource allocation. IEEE Internet of Things Journal, 8, 8657\u20138666. https:\/\/doi.org\/10.1109\/JIOT.2020.3035542","DOI":"10.1109\/JIOT.2020.3035542"},{"key":"907_CR23","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., et\u00a0al. (2016). Ssd: Single shot multibox detector. In  Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14 (pp. 21\u201337). Springer. https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"907_CR24","doi-asserted-by":"publisher","unstructured":"Liu, C., Tang, F., & Hu, Y., et al. (2020). Distributed task migration optimization in mec by extending multi-agent deep reinforcement learning approach. IEEE Transactions on Parallel and Distributed Systems, 32, 1603\u20131614. https:\/\/doi.org\/10.1109\/TPDS.2020.3046737","DOI":"10.1109\/TPDS.2020.3046737"},{"key":"907_CR25","doi-asserted-by":"publisher","unstructured":"Lo Scudo, F., Ritacco, E., Caroprese, L., et al. (2023). Audio-based anomaly detection on edge devices via self-supervision and spectral analysis. Journal of Intelligent Information Systems,61, 765\u2013793. https:\/\/doi.org\/10.1007\/s10844-023-00792-2","DOI":"10.1007\/s10844-023-00792-2"},{"key":"907_CR26","unstructured":"Lowe, R., WU, Y., Tamar, A., et\u00a0al. (2017). Multi-agent actor-critic for mixed cooperative-competitive environments. In Advances in Neural Information Processing Systems (vol.\u00a030). Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/68a9750337a418a86fe06c1991a1d64c-Paper.pdf"},{"key":"907_CR27","doi-asserted-by":"publisher","unstructured":"Mao, Y., You, C., Zhang, J., et al. (2017). A survey on mobile edge computing: The communication perspective. IEEE Communications Surveys & Tutorials,19, 2322\u20132358. https:\/\/doi.org\/10.1109\/COMST.2017.2745201","DOI":"10.1109\/COMST.2017.2745201"},{"key":"907_CR28","doi-asserted-by":"publisher","first-page":"6255511","DOI":"10.1155\/2024\/6255511","volume":"2024","author":"H Mashal","year":"2024","unstructured":"Mashal, H., & Rezvani, M. H. (2024). Multiobjective offloading optimization in fog computing using deep reinforcement learning. Journal of Computer Networks and Communications, 2024, 6255511. https:\/\/doi.org\/10.1155\/2024\/6255511","journal-title":"Journal of Computer Networks and Communications"},{"key":"907_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000086","volume":"16","author":"TM Moerland","year":"2023","unstructured":"Moerland, T. M., Broekens, J., Plaat, A., et al. (2023). Model-based reinforcement learning: A survey. Foundations and Trends\u00ae in Machine Learning, 16, 1\u2013118. https:\/\/doi.org\/10.1561\/2200000086","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"key":"907_CR30","doi-asserted-by":"publisher","unstructured":"Niu, L., Chen, X., & Zhang, N., et al. (2023). Multi-agent meta-reinforcement learning for optimized task scheduling in heterogeneous edge computing systems. IEEE Internet of Things Journal, 10, 10519\u201310531. https:\/\/doi.org\/10.1109\/JIOT.2023.3241222","DOI":"10.1109\/JIOT.2023.3241222"},{"key":"907_CR31","doi-asserted-by":"publisher","unstructured":"Pu, L., Chen, X., & Xu, J., et al. (2016). D2d fogging: An energy-efficient and incentive-aware task offloading framework via network-assisted d2d collaboration. IEEE Journal on Selected Areas in Communications, 34, 3887\u20133901. https:\/\/doi.org\/10.1109\/JSAC.2016.2624118","DOI":"10.1109\/JSAC.2016.2624118"},{"key":"907_CR32","doi-asserted-by":"publisher","unstructured":"Qu, B., Bai, Y., Chu, Y., et al. (2022). Resource allocation for mec system with multi-users resource competition based on deep reinforcement learning approach. Computer Networks,215, 109181. https:\/\/doi.org\/10.1016\/j.comnet.2022.109181","DOI":"10.1016\/j.comnet.2022.109181"},{"key":"907_CR33","doi-asserted-by":"publisher","unstructured":"Ren, J., Yu, G., & He, Y., et al. (2019). Collaborative cloud and edge computing for latency minimization. IEEE Transactions on Vehicular Technology, 68, 5031\u20135044. https:\/\/doi.org\/10.1109\/TVT.2019.2904244","DOI":"10.1109\/TVT.2019.2904244"},{"key":"907_CR34","doi-asserted-by":"publisher","unstructured":"Scott, J., Gass, R., Crowcroft, J., et\u00a0al. (2022). Crawdad cambridge\/haggle (v. 2009-05-29). https:\/\/doi.org\/10.15783\/C70011","DOI":"10.15783\/C70011"},{"key":"907_CR35","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C. E. (1948). A mathematical theory of communication. The Bell System Technical Journal, 27, 379\u2013423. https:\/\/doi.org\/10.1002\/j.1538-7305.1948.tb01338.x","journal-title":"The Bell System Technical Journal"},{"key":"907_CR36","doi-asserted-by":"publisher","unstructured":"Song, F., Deng, M., Xing, H., et\u00a0al. (2024a). Energy-efficient trajectory optimization with wireless charging in uav-assisted mec based on multi-objective reinforcement learning. IEEE Transactions on Mobile Computing (pp. 1\u201318). https:\/\/doi.org\/10.1109\/TMC.2024.3384405","DOI":"10.1109\/TMC.2024.3384405"},{"key":"907_CR37","doi-asserted-by":"publisher","unstructured":"Song, F., Yang, Q., Deng, M., et\u00a0al. (2024b). Aoi and energy tradeoff for aerial-ground collaborative mec: A multi-objective learning approach. IEEE Transactions on Mobile Computing (pp. 1\u201317). https:\/\/doi.org\/10.1109\/TMC.2024.3394568","DOI":"10.1109\/TMC.2024.3394568"},{"key":"907_CR38","doi-asserted-by":"publisher","first-page":"4416","DOI":"10.1109\/TNSM.2023.3267809","volume":"20","author":"A Suzuki","year":"2023","unstructured":"Suzuki, A., Kobayashi, M., & Oki, E. (2023). Multi-agent deep reinforcement learning for cooperative computing offloading and route optimization in multi cloud-edge networks. IEEE Transactions on Network and Service Management, 20, 4416\u20134434. https:\/\/doi.org\/10.1109\/TNSM.2023.3267809","journal-title":"IEEE Transactions on Network and Service Management"},{"key":"907_CR39","doi-asserted-by":"publisher","first-page":"16454","DOI":"10.1109\/TVT.2023.3290954","volume":"72","author":"FD Tilahun","year":"2023","unstructured":"Tilahun, F. D., Abebe, A. T., & Kang, C. G. (2023). Multi-agent reinforcement learning for distributed resource allocation in cell-free massive mimo-enabled mobile edge computing network. IEEE Transactions on Vehicular Technology, 72, 16454\u201316468. https:\/\/doi.org\/10.1109\/TVT.2023.3290954","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"907_CR40","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1109\/TVT.2018.2881191","volume":"68","author":"TX Tran","year":"2018","unstructured":"Tran, T. X., & Pompili, D. (2018). Joint task offloading and resource allocation for multi-server mobile-edge computing networks. IEEE Transactions on Vehicular Technology, 68, 856\u2013868. https:\/\/doi.org\/10.1109\/TVT.2018.2881191","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"907_CR41","doi-asserted-by":"publisher","unstructured":"Wang, X., Wang, S., & Liang, X., et al. (2022). Deep reinforcement learning: A survey. IEEE Transactions on Neural Networks and Learning Systems, 35, 5064\u20135078. https:\/\/doi.org\/10.1109\/TNNLS.2022.3207346","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"907_CR42","doi-asserted-by":"publisher","unstructured":"Xiong, Z., Zhang, Y., & Niyato, D., et al. (2019). Deep reinforcement learning for mobile 5g and beyond: Fundamentals, applications, and challenges. IEEE Vehicular Technology Magazine, 14, 44\u201352. https:\/\/doi.org\/10.1109\/MVT.2019.2903655","DOI":"10.1109\/MVT.2019.2903655"},{"key":"907_CR43","doi-asserted-by":"publisher","first-page":"908056","DOI":"10.3389\/fbioe.2022.908056","volume":"10","author":"J Xu","year":"2022","unstructured":"Xu, J., Xu, Z., & Shi, B. (2022). Deep reinforcement learning based resource allocation strategy in cloud-edge computing system. Frontiers in Bioengineering and Biotechnology, 10, 908056. https:\/\/doi.org\/10.3389\/fbioe.2022.908056","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"key":"907_CR44","doi-asserted-by":"publisher","unstructured":"Yang, Y., Lou, K., & Wang, E., et al. (2023). Multi-agent reinforcement learning based file caching strategy in mobile edge computing. IEEE\/ACM Transactions on Networking, 31, 3159\u20133174. https:\/\/doi.org\/10.1109\/TNET.2023.3278032","DOI":"10.1109\/TNET.2023.3278032"},{"key":"907_CR45","doi-asserted-by":"publisher","unstructured":"Yang, J., Yuan, Q., & Chen, S., et al. (2023). Cooperative task offloading for mobile edge computing based on multi-agent deep reinforcement learning. IEEE Transactions on Network and Service Management, 20, 3205\u20133219. https:\/\/doi.org\/10.1109\/TNSM.2023.3240415","DOI":"10.1109\/TNSM.2023.3240415"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-024-00907-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10844-024-00907-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-024-00907-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T10:45:14Z","timestamp":1743763514000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10844-024-00907-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["907"],"URL":"https:\/\/doi.org\/10.1007\/s10844-024-00907-3","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"23 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 October 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 November 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This paper does not contain any studies involving humans or animals.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}