{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:26:01Z","timestamp":1743128761050,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819916382"},{"type":"electronic","value":"9789819916399"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-981-99-1639-9_56","type":"book-chapter","created":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T07:02:39Z","timestamp":1681455759000},"page":"671-682","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MAR2MIX: A Novel Model for\u00a0Dynamic Problem in\u00a0Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Gaoyun","family":"Fang","sequence":"first","affiliation":[]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,15]]},"reference":[{"key":"56_CR1","unstructured":"Ackermann, J., Gabler, V., Osa, T., Sugiyama, M.: Reducing overestimation bias in multi-agent domains using double centralized critics. arXiv preprint arXiv:1910.01465 (2019)"},{"issue":"11","key":"56_CR2","doi-asserted-by":"publisher","first-page":"4948","DOI":"10.3390\/app11114948","volume":"11","author":"L Canese","year":"2021","unstructured":"Canese, L., et al.: Multi-agent reinforcement learning: a review of challenges and applications. Appl. Sci. 11(11), 4948 (2021)","journal-title":"Appl. Sci."},{"key":"56_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., et al.: Distributed learning in wireless networks: recent progress and future challenges. IEEE J. Sel. Areas Commun. (2021)","DOI":"10.1109\/JSAC.2021.3118346"},{"issue":"3","key":"56_CR4","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1109\/TITS.2019.2901791","volume":"21","author":"T Chu","year":"2019","unstructured":"Chu, T., Wang, J., Codec\u00e0, L., Li, Z.: Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Trans. Intell. Transp. Syst. 21(3), 1086\u20131095 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"5","key":"56_CR5","doi-asserted-by":"publisher","first-page":"1621","DOI":"10.1109\/TITS.2018.2827460","volume":"20","author":"J Cui","year":"2018","unstructured":"Cui, J., Wei, L., Zhang, J., Xu, Y., Zhong, H.: An efficient message-authentication scheme based on edge computing for vehicular ad hoc networks. IEEE Trans. Intell. Transp. Syst. 20(5), 1621\u20131632 (2018)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"1","key":"56_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-019-09430-0","volume":"34","author":"FL Da Silva","year":"2020","unstructured":"Da Silva, F.L., Warnell, G., Costa, A.H.R., Stone, P.: Agents teaching agents: a survey on inter-agent transfer learning. Auton. Agent. Multi-Agent Syst. 34(1), 1\u201317 (2020)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"issue":"2","key":"56_CR7","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1109\/COMST.2021.3063822","volume":"23","author":"A Feriani","year":"2021","unstructured":"Feriani, A., Hossain, E.: Single and multi-agent deep reinforcement learning for AI-enabled wireless networks: a tutorial. IEEE Commun. Surv. Tutor. 23(2), 1226\u20131252 (2021)","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"56_CR8","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"56_CR9","unstructured":"Gupta, S., Dukkipati, A.: Probabilistic view of multi-agent reinforcement learning: a unified approach (2019)"},{"key":"56_CR10","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"56_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7553","key":"56_CR12","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"56_CR13","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1016\/j.asoc.2018.12.001","volume":"75","author":"J Liang","year":"2019","unstructured":"Liang, J., Chen, J., Zhu, Y., Yu, R.: A novel intrusion detection system for vehicular ad hoc networks (VANETs) based on differences of traffic flow and position. Appl. Soft Comput. 75, 712\u2013727 (2019)","journal-title":"Appl. Soft Comput."},{"key":"56_CR14","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"56_CR15","unstructured":"Liu, B., Liu, Q., Stone, P., Garg, A., Zhu, Y., Anandkumar, A.: Coach-player multi-agent reinforcement learning for dynamic team composition. In: International Conference on Machine Learning, pp. 6860\u20136870. PMLR (2021)"},{"issue":"7","key":"56_CR16","doi-asserted-by":"publisher","first-page":"1603","DOI":"10.1109\/TPDS.2020.3046737","volume":"32","author":"C Liu","year":"2020","unstructured":"Liu, C., Tang, F., Hu, Y., Li, K., Tang, Z., Li, K.: Distributed task migration optimization in MEC by extending multi-agent deep reinforcement learning approach. IEEE Trans. Parallel Distrib. Syst. 32(7), 1603\u20131614 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"56_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, J., Zhu, X., Wei, D., Huang, X., Song, L.: Learning task-specific representation for video anomaly detection with spatial-temporal attention. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2190\u20132194. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746822"},{"key":"56_CR18","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"56_CR19","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"56_CR20","unstructured":"Murphy, K.P.: A survey of POMDP solution techniques. Environment 2(10) (2000)"},{"key":"56_CR21","unstructured":"Rakelly, K., Zhou, A., Finn, C., Levine, S., Quillen, D.: Efficient off-policy meta-reinforcement learning via probabilistic context variables. In: International Conference on Machine Learning, pp. 5331\u20135340. PMLR (2019)"},{"key":"56_CR22","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304. PMLR (2018)"},{"issue":"1","key":"56_CR23","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1109\/TETCI.2018.2823329","volume":"3","author":"K Shao","year":"2018","unstructured":"Shao, K., Zhu, Y., Zhao, D.: Starcraft micromanagement with reinforcement learning and curriculum transfer learning. IEEE Trans. Emerg. Top. Comput. Intell. 3(1), 73\u201384 (2018)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"56_CR24","unstructured":"Son, K., Ahn, S., Reyes, R.D., Shin, J., Yi, Y.: Qtran++: improved value transformation for cooperative multi-agent reinforcement learning. arXiv preprint arXiv:2006.12010 (2020)"},{"key":"56_CR25","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"56_CR26","doi-asserted-by":"crossref","unstructured":"Song, L., Hu, X., Zhang, G., Spachos, P., Plataniotis, K., Wu, H.: Networking systems of AI: on the convergence of computing and communications. IEEE Internet Things J. (2022)","DOI":"10.1109\/JIOT.2022.3172270"},{"key":"56_CR27","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"56_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"56_CR29","doi-asserted-by":"crossref","unstructured":"Xie, Y., Lin, R., Zou, H.: Multi-agent reinforcement learning via directed exploration method. In: 2022 2nd International Conference on Consumer Electronics and Computer Engineering (ICCECE), pp. 512\u2013517. IEEE (2022)","DOI":"10.1109\/ICCECE54139.2022.9712687"},{"key":"56_CR30","unstructured":"Yang, Y., Wang, J.: An overview of multi-agent reinforcement learning from game theoretical perspective. arXiv preprint arXiv:2011.00583 (2020)"},{"issue":"7","key":"56_CR31","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1162\/neco_a_01199","volume":"31","author":"Y Yu","year":"2019","unstructured":"Yu, Y., Si, X., Hu, C., Zhang, J.: A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 31(7), 1235\u20131270 (2019)","journal-title":"Neural Comput."},{"key":"56_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. In: Handbook of Reinforcement Learning and Control, pp. 321\u2013384 (2021)","DOI":"10.1007\/978-3-030-60990-0_12"},{"issue":"8","key":"56_CR33","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","volume":"107","author":"Z Zhou","year":"2019","unstructured":"Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., Zhang, J.: Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proc. IEEE 107(8), 1738\u20131762 (2019)","journal-title":"Proc. IEEE"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-1639-9_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,14]],"date-time":"2023-04-14T07:45:30Z","timestamp":1681458330000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-1639-9_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819916382","9789819916399"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-1639-9_56","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"359","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.65","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}