{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:18:49Z","timestamp":1766067529219,"version":"3.37.3"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,4,30]],"date-time":"2022-04-30T00:00:00Z","timestamp":1651276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,30]],"date-time":"2022-04-30T00:00:00Z","timestamp":1651276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012476","name":"Fundamental Research Funds for Central Universities of the Central South University","doi-asserted-by":"publisher","award":["2242021S30009"],"award-info":[{"award-number":["2242021S30009"]}],"id":[{"id":"10.13039\/501100012476","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Consulting Project of Chinese Academy of Engineering","award":["2020-XY-5","2018-XY-07"],"award-info":[{"award-number":["2020-XY-5","2018-XY-07"]}]},{"name":"the Consulting Project of Jiangsu Academy of Chinese Engineering S &T Strategy for Development","award":["JS2021ZT05"],"award-info":[{"award-number":["JS2021ZT05"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s11063-022-10811-y","type":"journal-article","created":{"date-parts":[[2022,4,30]],"date-time":"2022-04-30T07:02:43Z","timestamp":1651302163000},"page":"4341-4373","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["DMADRL: A Distributed Multi-agent Deep Reinforcement Learning Algorithm for Cognitive Offloading in Dynamic MEC Networks"],"prefix":"10.1007","volume":"54","author":[{"given":"Meng","family":"Yi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1184-8117","authenticated-orcid":false,"given":"Peng","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Miao","family":"Du","sequence":"additional","affiliation":[]},{"given":"Ruochen","family":"Ma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,30]]},"reference":[{"issue":"2","key":"10811_CR1","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/COMST.2021.3061981","volume":"23","author":"Y Siriwardhana","year":"2021","unstructured":"Siriwardhana Y, Porambage P, Liyanage M, Ylinattila M (2021) A survey on mobile augmented reality with 5g mobile edge computing: architectures, applications and technical aspects. IEEE Commun Surv Tutor 23(2):1160\u20131192","journal-title":"IEEE Commun Surv Tutor"},{"key":"10811_CR2","doi-asserted-by":"publisher","first-page":"108186","DOI":"10.1016\/j.comnet.2021.108186","volume":"195","author":"M Chen","year":"2021","unstructured":"Chen M, Liu W, Wang T, Liu A, Zeng Z (2021) Edge intelligence computing for mobile augmented reality with deep reinforcement learning approach. Comput Netw 195:108186","journal-title":"Comput Netw"},{"issue":"4","key":"10811_CR3","doi-asserted-by":"publisher","first-page":"4596","DOI":"10.1109\/TVT.2020.2973292","volume":"69","author":"B Xie","year":"2020","unstructured":"Xie B, Zhang Q, Qin J (2020) Joint optimization of cooperative communication and computation in two-way relay MEC systems. IEEE Trans Veh Technol 69(4):4596\u20134600","journal-title":"IEEE Trans Veh Technol"},{"issue":"5","key":"10811_CR4","doi-asserted-by":"publisher","first-page":"2795","DOI":"10.1109\/TNET.2015.2487344","volume":"24","author":"X Chen","year":"2015","unstructured":"Chen X, Jiao L, Li W, Fu X (2015) Efficient multi-user computation offloading for mobile-edge cloud computing. IEEE\/ACM Trans Netw 24(5):2795\u20132808","journal-title":"IEEE\/ACM Trans Netw"},{"issue":"3","key":"10811_CR5","doi-asserted-by":"publisher","first-page":"4049","DOI":"10.1109\/JIOT.2018.2876088","volume":"6","author":"M Asif-Ur-Rahman","year":"2018","unstructured":"Asif-Ur-Rahman M, Afsana F, Mahmud M, Kaiser MS, Ahmed MR, Kaiwartya O, James-Taylor A (2018) Toward a heterogeneous mist, fog, and cloud-based framework for the internet of healthcare things. IEEE Internet Things J 6(3):4049\u20134062","journal-title":"IEEE Internet Things J"},{"key":"10811_CR6","doi-asserted-by":"crossref","unstructured":"Gelsinger PP (2001) Microprocessors for the new millennium: challenges, opportunities, and new frontiers. In: 2001 IEEE international solid-state circuits conference. Digest of Technical Papers. ISSCC (Cat. No. 01CH37177). IEEE, pp 22\u201325","DOI":"10.1109\/ISSCC.2001.912412"},{"issue":"3","key":"10811_CR7","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.1109\/COMST.2017.2705720","volume":"19","author":"T Taleb","year":"2017","unstructured":"Taleb T, Samdanis K, Mada B, Flinck H, Dutta S, Sabella D (2017) On multi-access edge computing: a survey of the emerging 5G network edge cloud architecture and orchestration. IEEE Commun Surv Tutor 19(3):1657\u20131681","journal-title":"IEEE Commun Surv Tutor"},{"key":"10811_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.comcom.2021.04.028","volume":"175","author":"M Chen","year":"2021","unstructured":"Chen M, Wang T, Zhang S, Liu A (2021) Deep reinforcement learning for computation offloading in mobile edge computing environment. Comput Commun 175:1\u201312","journal-title":"Comput Commun"},{"key":"10811_CR9","doi-asserted-by":"crossref","unstructured":"Kosta S, Aucinas A, Hui P, Mortier R, Zhang X (2012) Thinkair: dynamic resource allocation and parallel execution in the cloud for mobile code offloading. In: 2012 proceedings IEEE Infocom. IEEE, pp 945\u2013953","DOI":"10.1109\/INFCOM.2012.6195845"},{"key":"10811_CR10","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1016\/j.comcom.2019.12.054","volume":"151","author":"M Chen","year":"2020","unstructured":"Chen M, Wang T, Ota K, Dong M, Zhao M, Liu A (2020) Intelligent resource allocation management for vehicles network: an A3C learning approach. Comput Commun 151:485\u2013494","journal-title":"Comput Commun"},{"key":"10811_CR11","unstructured":"Patel M, Naughton B, Chan C, Sprecher N, Abeta S, Neal A et al (2014) Mobile-edge computing introductory technical white paper. White paper, mobile-edge computing (MEC) industry initiative, pp 1089\u20137801"},{"issue":"7","key":"10811_CR12","doi-asserted-by":"publisher","first-page":"4480","DOI":"10.1109\/TWC.2020.2983890","volume":"19","author":"A Ebrahimzadeh","year":"2020","unstructured":"Ebrahimzadeh A, Maier M (2020) Cooperative computation offloading in FiWi enhanced 4G HetNets using self-organizing MEC. IEEE Trans Wirel Commun 19(7):4480\u20134493","journal-title":"IEEE Trans Wirel Commun"},{"issue":"3","key":"10811_CR13","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1109\/TWC.2020.3033843","volume":"20","author":"L Li","year":"2021","unstructured":"Li L, Cheng Q, Tang X, Bai T, Chen W, Ding Z, Han Z (2021) Resource allocation for NOMA-MEC systems in ultra-dense networks: a learning aided mean-field game approach. IEEE Trans Wirel Commun 20(3):1487\u20131500. https:\/\/doi.org\/10.1109\/TWC.2020.3033843","journal-title":"IEEE Trans Wirel Commun"},{"key":"10811_CR14","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3049356","author":"K Wang","year":"2021","unstructured":"Wang K, Ding Z, So DKC, Karagiannidis GK (2021) Stackelberg game of energy consumption and latency in MEC systems with NOMA. IEEE Trans Commun. https:\/\/doi.org\/10.1109\/TCOMM.2021.3049356","journal-title":"IEEE Trans Commun"},{"issue":"4","key":"10811_CR15","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1109\/JSAC.2020.3018809","volume":"39","author":"B Liu","year":"2021","unstructured":"Liu B, Liu C, Peng M (2021) Resource allocation for energy-efficient MEC in NOMA-enabled massive IoT networks. IEEE J Sel Areas Commun 39(4):1015\u20131027. https:\/\/doi.org\/10.1109\/JSAC.2020.3018809","journal-title":"IEEE J Sel Areas Commun"},{"key":"10811_CR16","volume-title":"Dynamic programming and optimal control","author":"DP Bertsekas","year":"1995","unstructured":"Bertsekas DP (1995) Dynamic programming and optimal control, vol 1. Athena Scientific, Belmont, MA"},{"key":"10811_CR17","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1109\/TC.1977.1674939","volume":"9","author":"PM Narendra","year":"1977","unstructured":"Narendra PM, Fukunaga K (1977) A branch and bound algorithm for feature subset selection. IEEE Trans Comput 9:917\u2013922","journal-title":"IEEE Trans Comput"},{"issue":"1","key":"10811_CR18","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1109\/TVT.2018.2881191","volume":"68","author":"TX Tran","year":"2018","unstructured":"Tran TX, Pompili D (2018) Joint task offloading and resource allocation for multi-server mobile-edge computing networks. IEEE Trans Veh Technol 68(1):856\u2013868","journal-title":"IEEE Trans Veh Technol"},{"issue":"8","key":"10811_CR19","first-page":"3571","volume":"65","author":"TQ Dinh","year":"2017","unstructured":"Dinh TQ, Tang J, La QD, Quek TQ (2017) Offloading in mobile edge computing: task allocation and computational frequency scaling. IEEE Trans Commun 65(8):3571\u20133584","journal-title":"IEEE Trans Commun"},{"issue":"10","key":"10811_CR20","doi-asserted-by":"publisher","first-page":"9278","DOI":"10.1109\/JIOT.2020.2988457","volume":"7","author":"F Jiang","year":"2020","unstructured":"Jiang F, Wang K, Dong L, Pan C, Yang K (2020) Stacked autoencoder-based deep reinforcement learning for online resource scheduling in large-scale MEC networks. IEEE Internet Things J 7(10):9278\u20139290","journal-title":"IEEE Internet Things J"},{"issue":"4","key":"10811_CR21","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.1109\/COMST.2017.2745201","volume":"19","author":"Y Mao","year":"2017","unstructured":"Mao Y, You C, Zhang J, Huang K, Letaief KB (2017) A survey on mobile edge computing: the communication perspective. IEEE Commun Surv Tutor 19(4):2322\u20132358","journal-title":"IEEE Commun Surv Tutor"},{"issue":"3","key":"10811_CR22","doi-asserted-by":"publisher","first-page":"1628","DOI":"10.1109\/COMST.2017.2682318","volume":"19","author":"P Mach","year":"2017","unstructured":"Mach P, Becvar Z (2017) Mobile edge computing: a survey on architecture and computation offloading. IEEE Commun Surv Tutor 19(3):1628\u20131656","journal-title":"IEEE Commun Surv Tutor"},{"key":"10811_CR23","first-page":"87","volume":"26","author":"H Tanaka","year":"2018","unstructured":"Tanaka H, Yoshida M, Mori K, Takahashi N (2018) Multi-access edge computing: a survey. J Inf Process 26:87\u201397","journal-title":"J Inf Process"},{"key":"10811_CR24","unstructured":"Patel M, Naughton B, Chan C, Sprecher N, Abeta S, Neal A, Hu Y, Thornton C, Ramos J, Musiol T et al (2014) White paper, mobile-edge computing (MEC) industry initiative. ETSI White Paper"},{"key":"10811_CR25","unstructured":"ETSI M (2016) Mobile edge computing (MEC); framework and reference architecture. ETSI, DGS MEC 3"},{"issue":"3","key":"10811_CR26","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 J Sel Areas Commun 36(3):587\u2013597","journal-title":"IEEE J Sel Areas Commun"},{"issue":"8","key":"10811_CR27","doi-asserted-by":"publisher","first-page":"7944","DOI":"10.1109\/TVT.2019.2917890","volume":"68","author":"J Zhao","year":"2019","unstructured":"Zhao J, Li Q, Gong Y, Zhang K (2019) Computation offloading and resource allocation for cloud assisted mobile edge computing in vehicular networks. IEEE Trans Veh Technol 68(8):7944\u20137956","journal-title":"IEEE Trans Veh Technol"},{"issue":"6","key":"10811_CR28","doi-asserted-by":"publisher","first-page":"4177","DOI":"10.1109\/TWC.2018.2821664","volume":"17","author":"S Bi","year":"2018","unstructured":"Bi S, Zhang YJ (2018) Computation rate maximization for wireless powered mobile-edge computing with binary computation offloading. IEEE Trans Wirel Commun 17(6):4177\u20134190","journal-title":"IEEE Trans Wirel Commun"},{"issue":"3","key":"10811_CR29","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.1109\/TNET.2020.2983119","volume":"28","author":"PA Apostolopoulos","year":"2020","unstructured":"Apostolopoulos PA, Tsiropoulou EE, Papavassiliou S (2020) Risk-aware data offloading in multi-server multi-access edge computing environment. IEEE\/ACM Trans Netw 28(3):1405\u20131418","journal-title":"IEEE\/ACM Trans Netw"},{"issue":"12","key":"10811_CR30","doi-asserted-by":"publisher","first-page":"7867","DOI":"10.1109\/TCOMM.2020.3020068","volume":"68","author":"F Fang","year":"2020","unstructured":"Fang F, Xu Y, Ding Z, Shen C, Peng M, Karagiannidis GK (2020) Optimal resource allocation for delay minimization in NOMA-MEC networks. IEEE Trans Commun 68(12):7867\u20137881. https:\/\/doi.org\/10.1109\/TCOMM.2020.3020068","journal-title":"IEEE Trans Commun"},{"issue":"12","key":"10811_CR31","doi-asserted-by":"publisher","first-page":"6353","DOI":"10.1109\/TCOMM.2018.2866572","volume":"66","author":"TQ Dinh","year":"2018","unstructured":"Dinh TQ, La QD, Quek TQ, Shin H (2018) Learning for computation offloading in mobile edge computing. IEEE Trans Commun 66(12):6353\u20136367","journal-title":"IEEE Trans Commun"},{"key":"10811_CR32","doi-asserted-by":"crossref","unstructured":"Wang F, Wang F, Liu J, Shea R, Sun L (2020) Intelligent video caching at network edge: A multi-agent deep reinforcement learning approach. In: IEEE INFOCOM 2020-IEEE conference on computer communications. IEEE, pp 2499\u20132508","DOI":"10.1109\/INFOCOM41043.2020.9155373"},{"issue":"3","key":"10811_CR33","doi-asserted-by":"publisher","first-page":"3476","DOI":"10.1109\/TNSM.2021.3049381","volume":"18","author":"MS Munir","year":"2021","unstructured":"Munir MS, Abedin SF, Tran NH, Han Z, Huh E-N, Hong CS (2021) Risk-aware energy scheduling for edge computing with microgrid: a multi-agent deep reinforcement learning approach. IEEE Trans Netw Serv Manag 18(3):3476\u20133497","journal-title":"IEEE Trans Netw Serv Manag"},{"issue":"12","key":"10811_CR34","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MCOM.2016.1600492CM","volume":"54","author":"X Sun","year":"2016","unstructured":"Sun X, Ansari N (2016) EdgeIoT: mobile edge computing for the internet of things. IEEE Commun Mag 54(12):22\u201329","journal-title":"IEEE Commun Mag"},{"issue":"8","key":"10811_CR35","doi-asserted-by":"publisher","first-page":"7432","DOI":"10.1109\/TVT.2017.2672701","volume":"66","author":"C Wang","year":"2017","unstructured":"Wang C, Yu FR, Liang C, Chen Q, Tang L (2017) Joint computation offloading and interference management in wireless cellular networks with mobile edge computing. IEEE Trans Veh Technol 66(8):7432\u20137445","journal-title":"IEEE Trans Veh Technol"},{"issue":"6","key":"10811_CR36","doi-asserted-by":"publisher","first-page":"2651","DOI":"10.1109\/TNET.2018.2873002","volume":"26","author":"F Guo","year":"2018","unstructured":"Guo F, Zhang H, Ji H, Li X, Leung VC (2018) An efficient computation offloading management scheme in the densely deployed small cell networks with mobile edge computing. IEEE\/ACM Trans Netw 26(6):2651\u20132664","journal-title":"IEEE\/ACM Trans Netw"},{"issue":"11","key":"10811_CR37","doi-asserted-by":"publisher","first-page":"2457","DOI":"10.1109\/JSAC.2017.2760459","volume":"35","author":"J Du","year":"2017","unstructured":"Du J, Gelenbe E, Jiang C, Zhang H, Ren Y (2017) Contract design for traffic offloading and resource allocation in heterogeneous ultra-dense networks. IEEE J Sel Areas Commun 35(11):2457\u20132467","journal-title":"IEEE J Sel Areas Commun"},{"issue":"8","key":"10811_CR38","doi-asserted-by":"publisher","first-page":"4924","DOI":"10.1109\/TWC.2017.2703901","volume":"16","author":"C Wang","year":"2017","unstructured":"Wang C, Liang C, Yu FR, Chen Q, Tang L (2017) Computation offloading and resource allocation in wireless cellular networks with mobile edge computing. IEEE Trans Wirel Commun 16(8):4924\u20134938","journal-title":"IEEE Trans Wirel Commun"},{"issue":"4","key":"10811_CR39","doi-asserted-by":"publisher","first-page":"2375","DOI":"10.1109\/TWC.2018.2794345","volume":"17","author":"X Hu","year":"2018","unstructured":"Hu X, Wong K, Yang K (2018) Wireless powered cooperation-assisted mobile edge computing. IEEE Trans Wirel Commun 17(4):2375\u20132388. https:\/\/doi.org\/10.1109\/TWC.2018.2794345","journal-title":"IEEE Trans Wirel Commun"},{"key":"10811_CR40","doi-asserted-by":"publisher","first-page":"107660","DOI":"10.1016\/j.knosys.2021.107660","volume":"235","author":"M Chen","year":"2022","unstructured":"Chen M, Liu W, Wang T, Zhang S, Liu A (2022) A game-based deep reinforcement learning approach for energy-efficient computation in MEC systems. Knowl-Based Syst 235:107660","journal-title":"Knowl-Based Syst"},{"issue":"2","key":"10811_CR41","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1109\/TCCN.2019.2942924","volume":"6","author":"P Mukherjee","year":"2019","unstructured":"Mukherjee P, De S (2019) A system state aware switched-multichannel protocol for energy harvesting CRNS. IEEE Trans Cognit Commun Netw 6(2):669\u2013682","journal-title":"IEEE Trans Cognit Commun Netw"},{"issue":"2","key":"10811_CR42","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1109\/TNSE.2021.3117565","volume":"9","author":"M Chen","year":"2021","unstructured":"Chen M, Liu A, Liu W, Ota K, Dong M, Xiong N (2021) RDRL a recurrent deep reinforcement learning scheme for dynamic spectrum access in reconfigurable wireless networks. IEEE Trans Netw Sci Eng 9(2):364\u2013376","journal-title":"IEEE Trans Netw Sci Eng"},{"issue":"4","key":"10811_CR43","doi-asserted-by":"publisher","first-page":"3133","DOI":"10.1109\/COMST.2019.2916583","volume":"21","author":"NC Luong","year":"2019","unstructured":"Luong NC, Hoang DT, Gong S, Niyato D, Wang P, Liang Y-C, Kim DI (2019) Applications of deep reinforcement learning in communications and networking: a survey. IEEE Commun Surv Tutor 21(4):3133\u20133174","journal-title":"IEEE Commun Surv Tutor"},{"issue":"1","key":"10811_CR44","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/TCCN.2020.3027695","volume":"7","author":"L Wang","year":"2020","unstructured":"Wang L, Wang K, Pan C, Xu W, Aslam N, Hanzo L (2020) Multi-agent deep reinforcement learning based trajectory planning for multi-UAV assisted mobile edge computing. IEEE Trans Cogn Commun Netw 7(1):73\u201384","journal-title":"IEEE Trans Cogn Commun Netw"},{"key":"10811_CR45","first-page":"1","volume":"30","author":"R Lowe","year":"2017","unstructured":"Lowe R, Wu YI, Tamar A, Harb J, Pieter Abbeel O, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. Adv Neural Inf Process Syst 30:1\u201312","journal-title":"Adv Neural Inf Process Syst"},{"key":"10811_CR46","unstructured":"Bultitude YJ, Rautiainen T (2007) IST-4-027756 WINNER II D1. 1.2 V1. 2 WINNER II channel models. EBITG, TUI, UOULU, CU\/CRC, NOKIA, Technical Report"},{"issue":"2","key":"10811_CR47","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/COMST.2014.2368999","volume":"17","author":"X Lu","year":"2014","unstructured":"Lu X, Wang P, Niyato D, Kim DI, Han Z (2014) Wireless networks with RF energy harvesting: a contemporary survey. IEEE Commun Surv Tutor 17(2):757\u2013789","journal-title":"IEEE Commun Surv Tutor"},{"key":"10811_CR48","unstructured":"Omidshafiei S, Pazis J, Amato C, How JP, Vian J (2017) Deep decentralized multi-task multi-agent reinforcement learning under partial observability. In: International conference on machine learning. PMLR, pp 2681\u20132690"},{"issue":"7540","key":"10811_CR49","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"10811_CR50","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI conference on artificial intelligence, vol 30","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"10811_CR51","unstructured":"Foerster J, Nardelli N, Farquhar G, Afouras T, Torr PH, Kohli P, Whiteson S (2017) Stabilising experience replay for deep multi-agent reinforcement learning. In: International conference on machine learning. PMLR, pp 1146\u20131155"},{"key":"10811_CR52","doi-asserted-by":"crossref","unstructured":"Foerster J, Farquhar G, Afouras T, Nardelli N, Whiteson S (2018) Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"10811_CR53","unstructured":"Sutton RS, McAllester DA, Singh SP, Mansour Y et al (1999) Policy gradient methods for reinforcement learning with function approximation. In: NIPs, vol 99. Citeseer, pp 1057\u20131063"},{"issue":"5","key":"10811_CR54","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/MNET.001.1900561","volume":"34","author":"S Gong","year":"2020","unstructured":"Gong S, Xie Y, Xu J, Niyato D, Liang Y-C (2020) Deep reinforcement learning for backscatter-aided data offloading in mobile edge computing. IEEE Netw 34(5):106\u2013113","journal-title":"IEEE Netw"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10811-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-022-10811-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-022-10811-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T07:26:23Z","timestamp":1665732383000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-022-10811-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,30]]},"references-count":54,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["10811"],"URL":"https:\/\/doi.org\/10.1007\/s11063-022-10811-y","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2022,4,30]]},"assertion":[{"value":"31 March 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}