{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T17:48:51Z","timestamp":1793987331537,"version":"4.8.0"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,2]]},"DOI":"10.1109\/infocom48880.2022.9796717","type":"proceedings-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T21:18:49Z","timestamp":1655759929000},"page":"2098-2107","source":"Crossref","is-referenced-by-count":29,"title":["Multi-Agent Distributed Reinforcement Learning for Making Decentralized Offloading Decisions"],"prefix":"10.1109","author":[{"given":"Jing","family":"Tan","sequence":"first","affiliation":[{"name":"Huawei Technology,Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramin","family":"Khalili","sequence":"additional","affiliation":[{"name":"Huawei Technology,Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Holger","family":"Karl","sequence":"additional","affiliation":[{"name":"Hasso Plattner Institute,Berlin,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Artur","family":"Hecker","sequence":"additional","affiliation":[{"name":"Huawei Technology,Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Mixed-strategy learning with continuous action sets","author":"perkins","year":"2015","journal-title":"IEEE Trans on Automatic Control"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1006\/game.1996.0044"},{"key":"ref33","author":"schindler","year":"2011","journal-title":"Pricing Strategies A Marketing Approach"},{"key":"ref32","article-title":"Service-based architecture in 5g: case study and deployment recommendations","year":"2019"},{"key":"ref31","article-title":"Iso 20078:2019 road vehicles-extended vehicle (exve) web services","year":"2019","journal-title":"International Organization for Standardization"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2013.08.004"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/49.872963"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2488608.2488634"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.2307\/2977633"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1086\/695529"},{"key":"ref60","article-title":"Energy-efficient power control for multiple-relay cooperative networks using q-learning","author":"shams","year":"2014","journal-title":"IEEE Trans on Wireless Comm"},{"key":"ref62","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"ICML"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref63","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","author":"lanctot","year":"2017","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Fictitious self-play in extensive-form games","author":"heinrich","year":"2015","journal-title":"ICML"},{"key":"ref64","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"AISTATS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2006.872890"},{"key":"ref29","article-title":"Draco source code","year":"0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_15"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/2430656"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2842798"},{"key":"ref22","article-title":"Decentralized computation offloading game for mobile cloud computing","author":"chen","year":"2014","journal-title":"IEEE Trans on Parallel and Distributed Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485943"},{"key":"ref24","article-title":"A few good agents: multi-agent social learning","author":"oh","year":"2008","journal-title":"AAMAS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0881-6"},{"key":"ref26","article-title":"Best-response multiagent learning in non-stationary environments","author":"weinberg","year":"2004","journal-title":"AAMAS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2006.12.007"},{"key":"ref50","article-title":"Sumo-simulation of urban mobility: an overview","author":"behrisch","year":"2011","journal-title":"SIMUL"},{"key":"ref51","article-title":"Throughput comparison of ieee 802.11 ac and ieee 802.11 n in an indoor environment with interference","author":"shah","year":"2015","journal-title":"ITNAC IEEE"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71924-5_9"},{"key":"ref58","article-title":"Efficient multi-user computation offloading for mobile-edge cloud computing","author":"chen","year":"2015","journal-title":"IEEE\/ACM Trans on Networking"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2015.2388588"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2014.2374606"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3076503"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155404"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2018.2815360"},{"key":"ref52","article-title":"Multiuser joint task offloading and resource optimization in proximate clouds","author":"lyu","year":"2016","journal-title":"IEEE Trans on Vehicular Technology"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218618"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.geb.2005.08.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2016.08.005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09940-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC.2018.8539726"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CloudNet.2014.6968992"},{"key":"ref16","article-title":"An evolutionary game theory-based approach to cooperation in vanets under different network conditions","author":"shivshankar","year":"2014","journal-title":"IEEE Trans on Vehicular Technology"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/NCA.2010.24"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511800481.016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682862"},{"key":"ref4","article-title":"Self-driving cars: A survey","author":"badue","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"ref3","article-title":"A review of motion planning for highway autonomous driving","author":"claussmann","year":"2019","journal-title":"IEEE Trans on Intelligent Transp Systems"},{"key":"ref6","article-title":"European vision for the 6g network ecosystem","author":"bernardos","year":"2021","journal-title":"5G infrastructure association"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOMP.2019.8679433"},{"key":"ref8","article-title":"C-v2x use cases: Methodology, examples and service level requirements","year":"2019","journal-title":"5G Automotive Association"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-2955-6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2014.6856478"},{"key":"ref9","article-title":"C-v2x use cases volume ii: Examples and service level requirements","year":"2020","journal-title":"5G Automotive Association"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6566826"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2017.2737628"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/208"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref42","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2016.7842076"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10804","article-title":"Seqgan: Sequence generative adversarial nets with policy gradient","author":"yu","year":"2017","journal-title":"AAAI"},{"key":"ref43","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"NeurIPS"}],"event":{"name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","location":"London, United Kingdom","start":{"date-parts":[[2022,5,2]]},"end":{"date-parts":[[2022,5,5]]}},"container-title":["IEEE INFOCOM 2022 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9796607\/9796652\/09796717.pdf?arnumber=9796717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T12:55:14Z","timestamp":1700744114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9796717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,2]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/infocom48880.2022.9796717","relation":{},"subject":[],"published":{"date-parts":[[2022,5,2]]}}}