{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:03:08Z","timestamp":1743105788073,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030693213"},{"type":"electronic","value":"9783030693220"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69322-0_9","type":"book-chapter","created":{"date-parts":[[2021,2,14]],"date-time":"2021-02-14T08:44:56Z","timestamp":1613292296000},"page":"133-149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Policy Advisory Module for Exploration Hindrance Problem in Multi-agent Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Jiahao","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9271-4507","authenticated-orcid":false,"given":"Toshiharu","family":"Sugawara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,14]]},"reference":[{"issue":"4","key":"9_CR1","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of Markov decision processes. Math. Oper. Res. 27(4), 819\u2013840 (2002). https:\/\/doi.org\/10.1287\/moor.27.4.819.297","journal-title":"Math. Oper. Res."},{"key":"9_CR2","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1007\/978-3-030-03098-8_30","volume-title":"PRIMA 2018: Principles and Practice of Multi-Agent Systems","author":"EAO Diallo","year":"2018","unstructured":"Diallo, E.A.O., Sugawara, T.: Learning strategic group formation for coordinated behavior in adversarial multi-agent with double DQN. In: Miller, T., Oren, N., Sakurai, Y., Noda, I., Savarimuthu, B.T.R., Cao Son, T. (eds.) PRIMA 2018. LNCS (LNAI), vol. 11224, pp. 458\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-03098-8_30"},{"key":"9_CR3","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. CoRR abs\/1709.06560 (2017). http:\/\/arxiv.org\/abs\/1709.06560"},{"key":"9_CR4","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.amc.2017.10.018","volume":"320","author":"K Huang","year":"2018","unstructured":"Huang, K., Chen, X., Yu, Z., Yang, C., Gui, W.: Heterogeneous cooperative belief for social dilemma in multi-agent system. Appl. Math. Comput. 320, 572\u2013579 (2018)","journal-title":"Appl. Math. Comput."},{"key":"9_CR5","unstructured":"Kim, D., et al.: Learning to schedule communication in multi-agent reinforcement learning. arXiv preprint arXiv:1902.01554 (2019)"},{"key":"9_CR6","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"9_CR7","unstructured":"Leibo, J.Z., Zambaldi, V.F., Lanctot, M., Marecki, J., Graepel, T.: Multi-agent reinforcement learning in sequential social dilemmas. CoRR abs\/1702.03037 (2017). http:\/\/arxiv.org\/abs\/1702.03037"},{"key":"9_CR8","unstructured":"Lowe, R., Wu, Y.I., 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":"9_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1007\/978-3-030-33792-6_40","volume-title":"PRIMA 2019: Principles and Practice of Multi-Agent Systems","author":"Y Miyashita","year":"2019","unstructured":"Miyashita, Y., Sugawara, T.: Coordination in collaborative work by deep reinforcement learning with various state descriptions. In: Baldoni, M., Dastani, M., Liao, B., Sakurai, Y., Zalila Wenkstern, R. (eds.) PRIMA 2019. LNCS (LNAI), vol. 11873, pp. 550\u2013558. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-33792-6_40"},{"key":"9_CR10","unstructured":"Pynadath, D.V., Tambe, M.: The communicative multiagent team decision problem: analyzing teamwork theories and models. CoRR abs\/1106.4569 (2011). http:\/\/arxiv.org\/abs\/1106.4569"},{"key":"9_CR11","doi-asserted-by":"publisher","DOI":"10.3998\/mpub.20269","volume-title":"Prisoner\u2019s Dilemma: A Study in Conflict and Cooperation","author":"A Rapoport","year":"1965","unstructured":"Rapoport, A., Chammah, A.M., Orwant, C.J.: Prisoner\u2019s Dilemma: A Study in Conflict and Cooperation, vol. 165. University of Michigan Press, Ann Arbor (1965)"},{"key":"9_CR12","unstructured":"Stimpson, J.L., Goodrich, M.A.: Learning to cooperate in a social dilemma: a satisficing approach to bargaining. In: Proceedings of the 20th International Conference on Machine Learning (ICML 2003), pp. 728\u2013735 (2003)"},{"issue":"12","key":"9_CR13","doi-asserted-by":"publisher","first-page":"3083","DOI":"10.1109\/TNNLS.2015.2403394","volume":"26","author":"C Yu","year":"2015","unstructured":"Yu, C., Zhang, M., Ren, F., Tan, G.: Emotional multiagent reinforcement learning in spatial social dilemmas. IEEE Trans. Neural Netw. Learn. Syst. 26(12), 3083\u20133096 (2015)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","PRIMA 2020: Principles and Practice of Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69322-0_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,14]],"date-time":"2021-02-14T08:52:32Z","timestamp":1613292752000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69322-0_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030693213","9783030693220"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69322-0_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"14 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRIMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Principles and Practice of Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nagoya","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"prima2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/uchiya.web.nitech.ac.jp\/prima2020\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"50","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":"19","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":"38% - 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":"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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}