乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T11:55:26Z","timestamp":1726228526051},"publisher-location":"Cham","reference-count":14,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031408779"},{"type":"electronic","value":"9783031408786"}],"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\/978-3-031-40878-6_9","type":"book-chapter","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T13:03:22Z","timestamp":1693832602000},"page":"143-159","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning in\u00a0Cyclic Environmental Changes for\u00a0Agents in\u00a0Non-Communicative Environments: A Theoretical Approach"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-4139-2605","authenticated-orcid":false,"given":"Fumito","family":"Uwano","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0009-0007-0916-5505","authenticated-orcid":false,"given":"Keiki","family":"Takadama","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"9_CR1","unstructured":"Bargiacchi, E., Verstraeten, T., Roijersk, D.M., Now\u00e9, A., van Hasselt, H.: Learning to coordinate with coordination graphs in repeated single-stage multi-agent decision problems. In: The 35th International Conference on Machine Learning, vol. 80, 482\u2013490 (2018)"},{"issue":"7","key":"9_CR2","doi-asserted-by":"publisher","first-page":"7032","DOI":"10.1109\/TIE.2022.3206745","volume":"70","author":"L Chen","year":"2023","unstructured":"Chen, L., et al.: Multiagent path finding using deep reinforcement learning coupled with hot supervision contrastive loss. IEEE Trans. Industr. Electron. 70(7), 7032\u20137040 (2023). https:\/\/doi.org\/10.1109\/TIE.2022.3206745","journal-title":"IEEE Trans. Industr. Electron."},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Ding, S., Aoyama, H., Lin, D.: Combining multiagent reinforcement learning and search method for drone delivery on a non-grid graph. In: Advances in Practical Applications of Agents, Multi-Agent Systems, and Complex Systems Simulation. The PAAMS Collection: 20th International Conference, PAAMS 2022, L\u2019Aquila, Italy, July 13\u201315, 2022, Proceedings, pp. 112\u2013126. Springer-Verlag, Berlin, Heidelberg (2022)","DOI":"10.1007\/978-3-031-18192-4_10"},{"key":"9_CR4","unstructured":"Du, Y., et al.: Learning correlated communication topology in multi-agent reinforcement learning. In: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, pp. 456\u2013464. AAMAS \u201921, International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC (2021)"},{"issue":"2","key":"9_CR5","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1023\/A:1022614421909","volume":"3","author":"JJ Grefenstette","year":"1988","unstructured":"Grefenstette, J.J.: Credit assignment in rule discovery systems based on genetic algorithms. Mach. Learn. 3(2), 225\u2013245 (1988). https:\/\/doi.org\/10.1023\/A:1022614421909","journal-title":"Mach. Learn."},{"issue":"12","key":"9_CR6","doi-asserted-by":"publisher","first-page":"5211","DOI":"10.1109\/TFUZZ.2022.3170646","volume":"30","author":"J Li","year":"2022","unstructured":"Li, J., Shi, H., Hwang, K.S.: Using fuzzy logic to learn abstract policies in large-scale multiagent reinforcement learning. IEEE Trans. Fuzzy Syst. 30(12), 5211\u20135224 (2022). https:\/\/doi.org\/10.1109\/TFUZZ.2022.3170646","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"9_CR7","unstructured":"Raileanu, R., Denton, E., Szlam, A., Fergus, R.: Modeling others using oneself in multi-agent reinforcement learning. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 4257\u20134266. PMLR (10\u201315 Jul 2018). https:\/\/proceedings.mlr.press\/v80\/raileanu18a.html"},{"key":"9_CR8","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: The 35th International Conference on Machine Learning, vol. 80, pp. 4295\u20134304 (2018). http:\/\/proceedings.mlr.press\/v80\/rashid18a.html"},{"key":"9_CR9","unstructured":"Rashid, T., Farquhar, G., Peng, B., Whiteson, S.: Weighted qmix: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS\u201920, Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"9_CR10","unstructured":"Sigaud, O., Buffet, O.: Markov Decision Processes in Artificial Intelligence. Wiley-IEEE Press (2010)"},{"issue":"5","key":"9_CR11","doi-asserted-by":"publisher","first-page":"199","DOI":"10.9746\/jcmsi.12.199","volume":"12","author":"F Uwano","year":"2019","unstructured":"Uwano, F., Takadama, K.: Utilizing observed information for no-communication multi-agent reinforcement learning toward cooperation in dynamic environment. SICE J. Contr. Measure. Syst. Integr. 12(5), 199\u2013208 (2019). https:\/\/doi.org\/10.9746\/jcmsi.12.199","journal-title":"SICE J. Contr. Measure. Syst. Integr."},{"issue":"4","key":"9_CR12","doi-asserted-by":"publisher","first-page":"321","DOI":"10.9746\/jcmsi.11.321","volume":"11","author":"F Uwano","year":"2018","unstructured":"Uwano, F., Tatebe, N., Tajima, Y., Nakata, M., Kovacs, T., Takadama, K.: Multi-agent cooperation based on reinforcement learning with internal reward in maze problem. SICE J. Contr., Measure. Syst. Integr. 11(4), 321\u2013330 (2018). https:\/\/doi.org\/10.9746\/jcmsi.11.321","journal-title":"SICE J. Contr., Measure. Syst. Integr."},{"key":"9_CR13","unstructured":"Uwano, F., Takadama, K.: Directionality reinforcement learning to operate multi-agent system without communication (2021). 10.48550\/ARXIV.2110.05773, arXiv:2110.05773"},{"issue":"12","key":"9_CR14","doi-asserted-by":"publisher","first-page":"5654","DOI":"10.1109\/TNNLS.2021.3100417","volume":"32","author":"Z Zhou","year":"2021","unstructured":"Zhou, Z., Xu, H.: Decentralized adaptive optimal tracking control for massive autonomous vehicle systems with heterogeneous dynamics: A stackelberg game. IEEE Trans. Neural Netw. Learn. Syst. 32(12), 5654\u20135663 (2021). https:\/\/doi.org\/10.1109\/TNNLS.2021.3100417","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Explainable and Transparent AI and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40878-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T13:04:17Z","timestamp":1693832657000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40878-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031408779","9783031408786"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40878-6_9","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":"5 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EXTRAAMAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"London","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"29 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"extraamas2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/extraamas.ehealth.hevs.ch\/","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":"26","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":"15","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":"1","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":"58% - 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":"Between 3 and 5","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":"~1\/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)"}}]}}