{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:06:22Z","timestamp":1743019582134,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031357473"},{"type":"electronic","value":"9783031357480"}],"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\/978-3-031-35748-0_28","type":"book-chapter","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T18:03:19Z","timestamp":1689012199000},"page":"378-391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Policy-Based Reinforcement Learning for\u00a0Assortative Matching in\u00a0Human Behavior Modeling"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1172-1789","authenticated-orcid":false,"given":"Ou","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1325-4275","authenticated-orcid":false,"given":"Qun","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,9]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Ariely, D.: The Upside of Irrationality: The Unexpected Benefits of Defying Logic at Work and at Home. Harper (2010)","key":"28_CR1","DOI":"10.1109\/AERO.2011.5747214"},{"key":"28_CR2","volume-title":"Playing Atari with Deep Reinforcement Learning","author":"V Mnih","year":"2013","unstructured":"Mnih, V., et al.: Playing Atari with Deep Reinforcement Learning. Proc, NIPS Deep Learning Workshop (2013)"},{"key":"28_CR3","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, 529\u2013533 (2015)","journal-title":"Nature"},{"unstructured":"Mnih, V., et al.: Asynchronous Methods for Deep Reinforcement Learning. In: Proc. International Conference on Learning Representations (ICLR) (2016)","key":"28_CR4"},{"unstructured":"Schulman, J., et al.: Proceedings of the 32nd International Conference on Machine Learning. PMLR 37, 1889\u20131897 (2015)","key":"28_CR5"},{"unstructured":"Schulman, J., et al.: Proximal Policy Optimization Algorithms (2017)","key":"28_CR6"},{"unstructured":"Hoffman, M., et al.: Reinforcement Learning with Deep Energy-Based Policies. In: Proc. 34th International Conference on Machine Learning (ICML 2017)","key":"28_CR7"},{"unstructured":"Haarnoja, T., et al.: Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. In: Proc. Conference on Neural Information Processing Systems (NeurIPS 2018)","key":"28_CR8"},{"doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: Attentional Communication Framework for Multi-Agent Reinforcement Learning in Partially Communicable Scenarios. Electronics (2022)","key":"28_CR9","DOI":"10.3390\/electronics11244204"},{"doi-asserted-by":"crossref","unstructured":"Bu\u015foniu, L., et al.: A comprehensive survey of multi-agent reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 38, no. 2, pp. 156\u2013172 (2008)","key":"28_CR10","DOI":"10.1109\/TSMCC.2007.913919"},{"doi-asserted-by":"crossref","unstructured":"Madani, K., et al.: A game theory-reinforcement learning (GT-RL) method to develop optimal operation policies for multi-operator reservoir systems. J. Hydrol. 519, Part A (2014)","key":"28_CR11","DOI":"10.1016\/j.jhydrol.2014.07.061"},{"doi-asserted-by":"publisher","unstructured":"Now\u00e9, A. et al.: Game Theory and Multi-agent Reinforcement Learning. Wiering, M., van Otterlo, M. (eds) Reinforcement Learning. Adaptation, Learning, and Optimization, vol 12. Springer. (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_14","key":"28_CR12","DOI":"10.1007\/978-3-642-27645-3_14"},{"key":"28_CR13","first-page":"282","volume":"4","author":"TS Ferguson","year":"1988","unstructured":"Ferguson, T.S.: Who solved the secretary problem? Statist. Sci. 4, 282\u2013296 (1988)","journal-title":"Statist. Sci."}],"container-title":["Lecture Notes in Computer Science","Digital Human Modeling and Applications in Health, Safety, Ergonomics and Risk Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-35748-0_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T18:12:06Z","timestamp":1689012726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-35748-0_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031357473","9783031357480"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-35748-0_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"9 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Copenhagen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.hci.international\/","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":"CMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7472","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":"1578","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":"396","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":"21% - 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","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":"2","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)"}}]}}