{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T02:26:28Z","timestamp":1780626388133,"version":"3.54.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030185893","type":"print"},{"value":"9783030185909","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-18590-9_7","type":"book-chapter","created":{"date-parts":[[2019,4,23]],"date-time":"2019-04-23T21:48:41Z","timestamp":1556056121000},"page":"96-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["SparseMAAC: Sparse Attention for Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Wenhao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,4,24]]},"reference":[{"issue":"2","key":"7_CR1","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu, L., Babuska, R., De-Schutter, B.: A comprehensive survey of multi-agent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 38(2), 156\u2013172 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Chen, C., Seff, A., Kornhauser, A., Xiao, J.: Deepdriving: learning affordance for direct perception in autonomous driving. In: IEEE International Conference on Computer Vision, pp. 2722\u20132730 (2015)","DOI":"10.1109\/ICCV.2015.312"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: 32nd AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"7_CR4","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. arXiv preprint arXiv:1801.01290 (2018)"},{"key":"7_CR5","unstructured":"Haarnoja, T., et al.: Soft actor-critic algorithms and applications. arXiv preprint arXiv:1812.05905 (2018)"},{"key":"7_CR6","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. arXiv preprint arXiv:1810.02912 (2018)"},{"key":"7_CR7","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. arXiv preprint arXiv:1805.07733 (2018)"},{"key":"7_CR8","unstructured":"Lillicrap, T., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Littman, M.: Markov games as a framework for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"7_CR10","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, pp. 6379\u20136390 (2017)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"7_CR12","unstructured":"Martins, A., Astudillo, R.: From softmax to sparsemax: a sparse model of attention and multi-label classification. In: International Conference on Machine Learning, pp. 1614\u20131623 (2016)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Matignon, L., Jeanpierre, L., Mouaddib, A.I.: Coordinated multi-robot exploration under communication constraints using decentralized Markov decision processes. In: 26th AAAI Conference on Artificial Intelligence (2012)","DOI":"10.1609\/aaai.v26i1.8380"},{"issue":"7540","key":"7_CR14","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"key":"7_CR15","unstructured":"Mousavi, S., Schukat, M., Howley, E., Borji, A., Mozayani, N.: Learning to predict where to look in interactive environments using deep recurrent Q-learning. arXiv preprint arXiv:1612.05753 (2016)"},{"key":"7_CR16","unstructured":"Niculae, V., Blondel, M.: A regularized framework for sparse and structured neural attention. In: Advances in Neural Information Processing Systems, pp. 3338\u20133348 (2017)"},{"issue":"21","key":"7_CR17","doi-asserted-by":"publisher","first-page":"8145","DOI":"10.1523\/JNEUROSCI.2978-14.2015","volume":"35","author":"Y Niv","year":"2015","unstructured":"Niv, Y., Daniel, R., Geana, A., Gershman, S., Leong, Y., Radulescu, A., Wilson, R.: Reinforcement learning in multidimensional environments relies on attention mechanisms. J. Neurosci. 35(21), 8145\u20138157 (2015)","journal-title":"J. Neurosci."},{"key":"7_CR18","unstructured":"Oh, J., Chockalingam, V., Singh, S., Lee, H.: Control of memory, active perception, and action in minecraft. arXiv preprint arXiv:1605.09128 (2016)"},{"key":"7_CR19","unstructured":"OpenAI: Openai Five (2018). https:\/\/blog.openai.com\/openai-five\/"},{"key":"7_CR20","unstructured":"Peng, P., et al.: Multiagent bidirectionally-coordinated nets for learning to play starcraft combat games. arXiv preprint arXiv:1703.10069 (2017)"},{"key":"7_CR21","volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"M Puterman","year":"2014","unstructured":"Puterman, M.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)"},{"issue":"7","key":"7_CR22","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.artint.2006.02.006","volume":"171","author":"Y Shoham","year":"2007","unstructured":"Shoham, Y., Powers, R., Grenager, T.: If multi-agent learning is the answer, what is the question? Artif. Intell. 171(7), 365\u2013377 (2007)","journal-title":"Artif. Intell."},{"key":"7_CR23","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction (2018)"},{"key":"7_CR24","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057\u20131063 (2000)"},{"key":"7_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"issue":"3\u20134","key":"7_CR26","first-page":"229","volume":"8","author":"R Williams","year":"1992","unstructured":"Williams, R.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"7_CR27","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-18590-9_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T13:20:25Z","timestamp":1709817625000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-18590-9_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030185893","9783030185909"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-18590-9_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"24 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chiang Mai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/dasfaa2019.eng.cmu.ac.th\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"501","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":"92","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":"64","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":"18% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13 demo papers, 6 tutorial 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)"}}]}}