{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:46:50Z","timestamp":1774590410213,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T00:00:00Z","timestamp":1659916800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T00:00:00Z","timestamp":1659916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"CSSC System Engineering Research Institute","award":["SSDKKFJJ-2019-02-03"],"award-info":[{"award-number":["SSDKKFJJ-2019-02-03"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s10489-022-03924-3","type":"journal-article","created":{"date-parts":[[2022,8,8]],"date-time":"2022-08-08T11:02:52Z","timestamp":1659956572000},"page":"9261-9269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Transform networks for cooperative multi-agent deep reinforcement learning"],"prefix":"10.1007","volume":"53","author":[{"given":"Hongbin","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xiaodong","family":"Xie","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3601-9286","authenticated-orcid":false,"given":"Lianke","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,8]]},"reference":[{"issue":"1","key":"3924_CR1","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1109\/TII.2019.2934728","volume":"16","author":"T Liu","year":"2019","unstructured":"Liu T, Liu H, Li YF, Chen Z, Zhang Z, Liu S (2019) Flexible ftir spectral imaging enhancement for industrial robot infrared vision sensing. IEEE Trans Industr Inform 16(1):544\u2013554","journal-title":"IEEE Trans Industr Inform"},{"issue":"1","key":"3924_CR2","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1109\/TMECH.2018.2870056","volume":"24","author":"T Liu","year":"2018","unstructured":"Liu T, Liu H, Li YF, Zhang Z, Liu S (2018) Efficient blind signal reconstruction with wavelet transforms regularization for educational robot infrared vision sensing. IEEE\/ASME Trans Mechatron 24(1):384\u2013394","journal-title":"IEEE\/ASME Trans Mechatron"},{"key":"3924_CR3","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/j.neucom.2020.09.068","volume":"433","author":"H Liu","year":"2021","unstructured":"Liu H, Nie H, Zhang Z, Li YF (2021) Anisotropic angle distribution learning for head pose estimation and attention understanding in human-computer interaction. Neurocomputing 433:310\u2013322","journal-title":"Neurocomputing"},{"key":"3924_CR4","unstructured":"Hoffmann R, Zhang C, Ling X, Zettlemoyer L, Weld DS (2011) Knowledge-based weak supervision for information extraction of overlapping relations. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, pp 541\u2013550"},{"key":"3924_CR5","doi-asserted-by":"crossref","unstructured":"Tan M (1993) Multi-agent reinforcement learning: Independent vs. cooperative agents","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"3924_CR6","doi-asserted-by":"crossref","unstructured":"Liu H, Liu T, Zhang Z, Sangaiah AK, Yang B, Li Y ARHPE (2022) Asymmetric relation-aware representation learning for head pose estimation in industrial human\u2013machine interaction. IEEE Trans Ind Inf","DOI":"10.1109\/TII.2022.3143605"},{"key":"3924_CR7","doi-asserted-by":"crossref","unstructured":"Liu H, Fang S, Zhang Z, Li D, Lin K, Wang J (2021) Mfdnet: Collaborative poses perception and matrix fisher distribution for head pose estimation. IEEE Transactions on Multimedia","DOI":"10.1109\/TMM.2021.3081873"},{"key":"3924_CR8","doi-asserted-by":"crossref","unstructured":"Liu H, Zheng C, Li D, Shen X, Lin K, Wang J, Zhang Z, Zhang Z, Xiong NN (2021) Edmf: Efficient deep matrix factorization with review feature learning for industrial recommender system IEEE Transactions on Industrial Informatics","DOI":"10.1109\/TII.2021.3128240"},{"key":"3924_CR9","doi-asserted-by":"crossref","unstructured":"Li Z, Liu H, Zhang Z, Liu T, Xiong NN (2021) Learning knowledge graph embedding with heterogeneous relation attention networks. IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2021.3055147"},{"key":"3924_CR10","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.neucom.2021.10.050","volume":"468","author":"H Liu","year":"2022","unstructured":"Liu H, Zheng C, Li D, Zhang Z, Ke Lin, Shen X, Xiong NN, Wang J (2022) Multi-perspective social recommendation method with graph representation learning. Neurocomputing 468:469\u2013481","journal-title":"Neurocomputing"},{"key":"3924_CR11","doi-asserted-by":"crossref","unstructured":"Gupta JK, Egorov M, Kochenderfer M (2017) Cooperative multi-agent control using deep reinforcement learning. In: International conference on autonomous agents and multiagent systems. Springer, pp 66\u201383","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"3924_CR12","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1613\/jair.2447","volume":"32","author":"FA Oliehoek","year":"2008","unstructured":"Oliehoek FA, Spaan MTJ, Vlassis N (2008) Optimal and approximate q-value functions for decentralized pomdps. J Artif Intell Res 32:289\u2013353","journal-title":"J Artif Intell Res"},{"key":"3924_CR13","unstructured":"Lowe R, Wu YI, Tamar A, Harb J, Abbeel P, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. arXiv:1706.02275"},{"key":"3924_CR14","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":"3924_CR15","unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ , Tuyls K et al (2017) Value-decomposition networks for cooperative multi-agent learning. arXiv:1706.05296"},{"key":"3924_CR16","unstructured":"Rashid T, Samvelyan M, Schroeder C, Farquhar G, Foerster J, Whiteson S (2018) Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning. In: International conference on machine learning. PMLR, pp 4295\u20134304"},{"key":"3924_CR17","unstructured":"Son K, Kim D, Kang WJ, Hostallero DE, Yi Y (2019) Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International conference on machine learning. PMLR, pp 5887\u20135896"},{"key":"3924_CR18","unstructured":"Samvelyan M, Rashid T, De Witt CS, Farquhar G, Nardelli N, Rudner TGJ, Hung Chia-Man, Torr PHS , Foerster J, Whiteson S (2019) The starcraft multi-agent challeng. arXiv:1902.04043"},{"key":"3924_CR19","doi-asserted-by":"crossref","unstructured":"Zhao S, Grishman R (2005) Extracting relations with integrated information using kernel methods. In: Proceedings of the 43rd annual meeting of the association for computational linguistics (acl\u201905), pp 419\u2013426","DOI":"10.3115\/1219840.1219892"},{"key":"3924_CR20","doi-asserted-by":"crossref","unstructured":"Wen C, Yao Xu, Wang Y, Tan X (2020) Smix (\u03bb): Enhancing centralized value functions for cooperative multi-agent reinforcement learning. In: Proceedings of the AAAI Conference on artificial intelligence, vol 34, pp 7301\u20137308","DOI":"10.1609\/aaai.v34i05.6223"},{"key":"3924_CR21","unstructured":"Mahajan A, Rashid T, Samvelyan M, Whiteson S (2019) Maven: Multi-agent variational exploration. Advances in Neural Information Processing Systems 32"},{"key":"3924_CR22","unstructured":"Wang J, Ren Z, Liu T, Yu Y, Zhang c (2020) Qplex: Duplex dueling multi-agent q-learning. arXiv:2008.01062"},{"key":"3924_CR23","unstructured":"Du Y, Han L, Fang M, Lui J, Dai T, Tao D (2019) liir: Learning individual intrinsic reward in multi-agent reinforcement learning"},{"key":"3924_CR24","unstructured":"Wang W, Yang T, Liu Y, Hao J, Hao X, Hu Y, Chen Y, Fan C, Gao Y (2019) Action semantics network: Considering the effects of actions in multiagent systems. arXiv:1907.11461"},{"key":"3924_CR25","unstructured":"Vinyals O, Ewalds T, Bartunov S, Georgiev P, Vezhnevets AS, Yeo M, Makhzani A, K\u00fcttler H, Agapiou J , Schrittwieser J et al (2017) Starcraft ii: A new challenge for reinforcement learning. arXiv:1708.04782"},{"key":"3924_CR26","doi-asserted-by":"crossref","unstructured":"Oliehoek FA, Amato C (2015) A concise introduction to decentralized pomdps","DOI":"10.1007\/978-3-319-28929-8"},{"key":"3924_CR27","doi-asserted-by":"crossref","unstructured":"Littman ML (1994) Markov games as a framework for multi-agent reinforcement learning. In: Machine learning proceedings 1994. Elsevier, pp 157\u2013163","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"3924_CR28","doi-asserted-by":"crossref","unstructured":"Wiering MA, Van Otterlo M (2012) Reinforcement learning. Adaptation, learning, and optimization, 12(3)","DOI":"10.1007\/978-3-642-27645-3_1"},{"key":"3924_CR29","unstructured":"Szepesv\u00e1ri C (2009) Synthesis lectures on artificial intelligence and machine learning. Synthesis lectures on artificial intelligence and machine learning"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03924-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03924-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03924-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T09:23:33Z","timestamp":1682846613000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03924-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,8]]},"references-count":29,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["3924"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03924-3","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,8]]},"assertion":[{"value":"22 June 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 August 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}