{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:34:26Z","timestamp":1742942066327,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030918842"},{"type":"electronic","value":"9783030918859"}],"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\/978-3-030-91885-9_30","type":"book-chapter","created":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T13:03:12Z","timestamp":1638450192000},"page":"401-416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Convergence of the Reinforcement Learning Mechanism Applied to the Channel Detection Sequence Problem"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6390-1250","authenticated-orcid":false,"given":"Andr\u00e9","family":"Mendes","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,1]]},"reference":[{"key":"30_CR1","unstructured":"McHenry, M.A.: NSF Spectrum Occupancy Measurements Project (2005)"},{"key":"30_CR2","unstructured":"FCC: FCC-03-322 - NOTICE OF PROPOSED RULE MAKING AND ORDER. Technical report, Federal Communications Commission, 30 December 2003"},{"key":"30_CR3","unstructured":"Cheng, H.T., Zhuang, W.: Simple channel sensing order in cognitive radio networks. IEEE J. Sel. Areas Commun. (2011)"},{"key":"30_CR4","unstructured":"Chow, Y.S., Robbins, H., Siegmund, D.: Great Expectations: The Theory of Optimal Stopping. Houghton Mifflin Company, Boston (1971)"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Mendes, A.C., Augusto, C.H.P., Da Silva, M.W., Guedes, R.M., De Rezende, J.F.: Channel sensing order for cognitive radio networks using reinforcement learning. In: IEEE LCN (2011)","DOI":"10.1109\/LCN.2011.6115516"},{"key":"30_CR6","unstructured":"Claus, C., Boutilier, C.: The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems. National Conference on Artificial Intelligence (1998)"},{"key":"30_CR7","unstructured":"Tan, M.: Multi-agent Reinforcement Learning: Independent vs. Cooperative Agents. In: Readings in Agents (1997)"},{"key":"30_CR8","unstructured":"Lauer, M., Riedmiller, M.: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: ICML (2000)"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Kapetanakis, S., Kudenko, D.: Improving on the reinforcement learning of coordination in cooperative multi-agent systems. In: AAMAS (2002)","DOI":"10.1007\/3-540-44826-8_2"},{"key":"30_CR10","unstructured":"Lauer, M., Riedmiller, M.: Reinforcement learning for stochastic cooperative multiagent systems. In: AAMAS (2004)"},{"key":"30_CR11","unstructured":"Bowling, M.: Convergence and No-Regret in Multiagent Learning. In: Advances in Neural Information Processing Systems 17. MIT Press, Cambridge (2005)"},{"key":"30_CR12","unstructured":"Jafari, A., Greenwald, A., Gondek, D., Ercal, G.: On no-regret learning, fictitious play and nash equilibrium. In: Proceedings of the 18th International Conference on Machine Learning (2001)"},{"key":"30_CR13","unstructured":"Zapechelnyuk, A.: Limit behavior of no-regret dynamics. Technical report, School of Economics, Kyiv, Ucraine (2009)"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Leslie, D., Collins, E.: Generalised weakened fctitious play. Games Econ. Behav. 56(2) (2006)","DOI":"10.1016\/j.geb.2005.08.005"},{"key":"30_CR15","unstructured":"Brown, G.: Some notes on computation of games solutions. Research memoranda rm-125-pr, RAND Corporation, Santa Monica, California (1949)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Verbeeck, K., Now\u00e9, A., Parent, J., Tuyls, K.: Exploring selfish reinforcement learning in repeated games with stochastic rewards. In: JAAMAS (2006)","DOI":"10.1007\/s10458-006-9007-0"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MP, Cambridge (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"30_CR18","first-page":"279","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Yau, K.A., Komisarczuk, P., Teal, P.D.: Applications of reinforcement learning to cognitive radio networks. In: IEEE International Conference in Communications (ICC) (July 2010)","DOI":"10.1109\/ICCW.2010.5503970"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Yau, K.A., Komisarczuk, P., Teal, P.D.: Enhancing network performance in distributed cognitive radio networks using single-agent and multi-agent reinforcement learning. In: IEEE Conference on Local Computer Networks (October 2010)","DOI":"10.1109\/LCN.2010.5735689"},{"key":"30_CR21","unstructured":"Vu, H.L., Sakurai, T.: Collision probability in saturated IEEE 802.11 networks. In: Australian Telecommunication Networks and Applications Conference (2006)"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Hasselt, H.: Double q-learning. In: NIPS (2010)","DOI":"10.1145\/1833513.1839556"}],"container-title":["Communications in Computer and Information Science","Optimization, Learning Algorithms and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-91885-9_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:10:10Z","timestamp":1699884610000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-91885-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030918842","9783030918859"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-91885-9_30","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"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":"OL2A","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Optimization, Learning Algorithms and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bragan\u00e7a","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ol2a2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ol2a.ipb.pt\/EN_index.html","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"134","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":"39","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":"13","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":"29% - 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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","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)"}}]}}