{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:34:56Z","timestamp":1743136496178,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030926373"},{"type":"electronic","value":"9783030926380"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-92638-0_22","type":"book-chapter","created":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T13:02:45Z","timestamp":1641042165000},"page":"370-384","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention-Aware Actor for\u00a0Cooperative Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Chenran","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dianxi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaowen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqianwen","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaowu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,1]]},"reference":[{"key":"22_CR1","unstructured":"Ba, J., Mnih, V., Kavukcuoglu, K.: Multiple object recognition with visual attention. arXiv preprint arXiv:1412.7755 (2014)"},{"key":"22_CR2","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"issue":"12","key":"22_CR3","doi-asserted-by":"publisher","first-page":"5706","DOI":"10.1109\/TIP.2015.2487833","volume":"24","author":"A Borji","year":"2015","unstructured":"Borji, A., Cheng, M.M., Jiang, H., Li, J.: Salient object detection: a benchmark. IEEE Trans. Image Process. 24(12), 5706\u20135722 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"22_CR4","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. arXiv preprint arXiv:1810.02912 (2018)"},{"key":"22_CR5","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 2961\u20132970. PMLR (2019)"},{"key":"22_CR6","unstructured":"Jaques, N., et al.: Social influence as intrinsic motivation for multi-agent deep reinforcement learning. In: International Conference on Machine Learning, pp. 3040\u20133049. PMLR (2019)"},{"key":"22_CR7","unstructured":"Jiang, J., Dun, C., Huang, T., Lu, Z.: Graph convolutional reinforcement learning. arXiv preprint arXiv:1810.09202 (2018)"},{"key":"22_CR8","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. arXiv preprint arXiv:1805.07733 (2018)"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Judd, T., Ehinger, K., Durand, F., Torralba, A.: Learning to predict where humans look. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 2106\u20132113. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"22_CR10","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. arXiv preprint arXiv:1703.03130 (2017)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, W., Hu, Y., Hao, J., Chen, X., Gao, Y.: Multi-agent game abstraction via graph attention neural network. arXiv preprint arXiv:1911.10715 (2019)","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, W., Hu, Y., Hao, J., Chen, X., Gao, Y.: Multi-agent game abstraction via graph attention neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7211\u20137218 (2020)","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"22_CR13","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. arXiv preprint arXiv:1706.02275 (2017)"},{"key":"22_CR14","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, pp. 2204\u20132212 (2014)"},{"key":"22_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek, F.A., Amato, C.: A Concise Introduction to Decentralized POMDPs. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-28929-8"},{"key":"22_CR16","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)"},{"key":"22_CR17","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)"},{"key":"22_CR18","unstructured":"Sukhbaatar, S., Szlam, A., Fergus, R.: Learning multiagent communication with backpropagation. arXiv preprint arXiv:1605.07736 (2016)"},{"key":"22_CR19","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296 (2017)"},{"key":"22_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"issue":"27","key":"22_CR21","doi-asserted-by":"publisher","first-page":"8715","DOI":"10.1523\/JNEUROSCI.0962-09.2009","volume":"29","author":"V Wyart","year":"2009","unstructured":"Wyart, V., Tallon-Baudry, C.: How ongoing fluctuations in human visual cortex predict perceptual awareness: baseline shift versus decision bias. J. Neurosci. 29(27), 8715\u20138725 (2009)","journal-title":"J. Neurosci."},{"key":"22_CR22","unstructured":"Yang, Y., et al.: Qatten: a general framework for cooperative multiagent reinforcement learning. arXiv preprint arXiv:2002.03939 (2020)"},{"key":"22_CR23","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5571\u20135580. PMLR (2018)"}],"container-title":["Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","Collaborative Computing: Networking, Applications and Worksharing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92638-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T13:11:22Z","timestamp":1641042682000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92638-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030926373","9783030926380"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92638-0_22","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"type":"print","value":"1867-8211"},{"type":"electronic","value":"1867-822X"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"1 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CollaborateCom","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Collaborative Computing: Networking, Applications and Worksharing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2021","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":"colcom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/collaboratecom.eai-conferences.org\/2021\/","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":"Confy +","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"206","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":"62","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":"7","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":"30% - 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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}