{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:04:58Z","timestamp":1740099898390,"version":"3.37.3"},"reference-count":14,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4202049"],"award-info":[{"award-number":["4202049"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2018YFB1800805"],"award-info":[{"award-number":["2018YFB1800805"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1109\/globecom42002.2020.9322446","type":"proceedings-article","created":{"date-parts":[[2021,1,26]],"date-time":"2021-01-26T00:51:27Z","timestamp":1611622287000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Value Decomposition based Multi-Task Multi-Agent Deep Reinforcement Learning in Vehicular Networks"],"prefix":"10.1109","author":[{"given":"Shilin","family":"Xu","sequence":"first","affiliation":[]},{"given":"Caili","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Rose Qingyang","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Qian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017","journal-title":"arXiv preprint arXiv 1706 05296"},{"key":"ref11","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","first-page":"5392","article-title":"Hybrid reward architecture for reinforcement learning","author":"seijen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Multi-agent deep reinforcement learning enabled computation resource allocation in a vehicular cloud network","author":"xu","year":"2020","journal-title":"arXiv preprint arXiv 2008 06439"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps45667.2019.9024659"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"10190","DOI":"10.1109\/TVT.2018.2867191","article-title":"Mobility-aware edge caching and computing in vehicle networks: A deep reinforcement learning","volume":"67","author":"hu","year":"2018","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref3","article-title":"Explaining deep adaptive programs via reward decomposition","author":"erwig","year":"2018","journal-title":"Proceedings of the IJCAI Workshop on Explainable Artificial Intelligence"},{"key":"ref6","article-title":"Diff-dac: Distributed actor-critic for multitask deep reinforcement learning","author":"macua","year":"2017","journal-title":"arXiv preprint arXiv 1710 10363"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"3086","DOI":"10.1109\/TVT.2019.2893898","article-title":"Twin-timescale artificial intelligence aided mobility-aware edge caching and computing in vehicular networks","volume":"68","author":"hu","year":"2019","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref7","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"4005","DOI":"10.1109\/JIOT.2018.2876279","article-title":"Optimized computation offloading performance in virtual edge computing systems via deep reinforcement learning","volume":"6","author":"chen","year":"2018","journal-title":"IEEE Internet of Things Journal"},{"key":"ref1","article-title":"Deep deterministic policy gradient for urban traffic light control","author":"casas","year":"2017","journal-title":"arXiv preprint arXiv 1703 09042"},{"key":"ref9","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","author":"omidshafiei","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"}],"event":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","start":{"date-parts":[[2020,12,7]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2020,12,11]]}},"container-title":["GLOBECOM 2020 - 2020 IEEE Global Communications Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9322055\/9321973\/09322446.pdf?arnumber=9322446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:57:07Z","timestamp":1656345427000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9322446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/globecom42002.2020.9322446","relation":{},"subject":[],"published":{"date-parts":[[2020,12]]}}}