{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:02:26Z","timestamp":1743148946477,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":16,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819923557"},{"type":"electronic","value":"9789819923564"}],"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\/978-981-99-2356-4_39","type":"book-chapter","created":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T13:03:30Z","timestamp":1683896610000},"page":"492-501","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-agent Adversarial Reinforcement Learning Algorithm Based on Reward Query Attention Mechanism"],"prefix":"10.1007","author":[{"given":"Liwei","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dingquan","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,13]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., et al.: Mastering the game of go without human knowledge. Nature\u00a0550(7676), 354\u2013359 (2017)","DOI":"10.1038\/nature24270"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature\u00a0518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Kim, S., Kim, B.J., Park, B.B.: Environment-adaptive multiple access for distributed V2X network: A reinforcement learning framework.\u00a0In: 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), pp. 1\u20137. IEEE ( 2021)","DOI":"10.1109\/VTC2021-Spring51267.2021.9448824"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Burgue\u00f1o, J., Adeogun, R., Bruun, R L., et al.: Distributed deep reinforcement learning resource allocation scheme for industry 4.0 device-to-device scenarios. In:\u00a02021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), pp.\u00a01\u20137.\u00a0IEEE (2021)","DOI":"10.1109\/VTC2021-Fall52928.2021.9625582"},{"issue":"11","key":"39_CR5","doi-asserted-by":"publisher","first-page":"3698","DOI":"10.4249\/scholarpedia.3698","volume":"5","author":"J Peters","year":"2010","unstructured":"Peters, J., Bagnell, J.A.: Policy gradient methods. Scholarpedia 5(11), 3698 (2010)","journal-title":"Scholarpedia"},{"issue":"3","key":"39_CR6","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"39_CR7","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.\u00a0\u00a0321\u2013384 (2021)","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G, Afouras, T., et al.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32(1) (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ma, H., Wang, Y.: Avd-net: Attention value decomposition network for deep multi-agent reinforcement learning. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7810\u20137816. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413114"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Tampuu, A., Matiisen, T., Kodelja, D., et al.: Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE 12(4), e0172395 (2017)","DOI":"10.1371\/journal.pone.0172395"},{"key":"39_CR11","unstructured":"Sunehag, P., Lever, G., Gruslys, A., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296, (2017)"},{"key":"39_CR12","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., et al.: Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning. In: International conference on machine learning, pp. 4295\u20134304. PMLR (2018)"},{"key":"39_CR13","doi-asserted-by":"publisher","unstructured":"Oliehoek, F.A., Amato, C.A.: concise introduction to decentralized POMDPs. Springer, (2016).\u00a0\u00a0https:\/\/doi.org\/10.1007\/978-3-319-28929-8","DOI":"10.1007\/978-3-319-28929-8"},{"key":"39_CR14","unstructured":"Ioffe, S., Szegedy. C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning,\u00a0pp. 448\u2013456.\u00a0PMLR (2015)"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Niu, Z., Zhong, G., Yu, H.: A review on the attention mechanism of deep learning. Neurocomputing 452, 48\u201362 (2021)","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"39_CR16","unstructured":"Samvelyan, M., Rashid, T., De Witt, C.S., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043, (2019)"}],"container-title":["Communications in Computer and Information Science","Computer Supported Cooperative Work and Social Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-2356-4_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,12]],"date-time":"2023-05-12T13:04:40Z","timestamp":1683896680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-2356-4_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819923557","9789819923564"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-2356-4_39","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":"13 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ChineseCSCW","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF Conference on Computer Supported Cooperative Work  and Social Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Datong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"23 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"chinesecscw2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.scholat.com\/ccscw\/2022","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","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":"60","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":"30","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":"28% - 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":"3","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":"4","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)"}}]}}