{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T11:02:12Z","timestamp":1753441332465,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030757618"},{"type":"electronic","value":"9783030757625"}],"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\/978-3-030-75762-5_2","type":"book-chapter","created":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T09:07:43Z","timestamp":1620464863000},"page":"15-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Collaborative Reinforcement Learning Framework to Model Evolution of Cooperation in Sequential Social Dilemmas"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1912-1721","authenticated-orcid":false,"given":"Ritwik","family":"Chaudhuri","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9796-9429","authenticated-orcid":false,"given":"Kushal","family":"Mukherjee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3289-3950","authenticated-orcid":false,"given":"Ramasuri","family":"Narayanam","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5069-2784","authenticated-orcid":false,"given":"Rohith D.","family":"Vallam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,9]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the Twenty-First International Conference on Machine Learning, ICML 2004, p. 1. ACM, New York (2004)","DOI":"10.1145\/1015330.1015430"},{"issue":"3","key":"2_CR2","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1257\/000282803322157142","volume":"93","author":"J Andreoni","year":"2003","unstructured":"Andreoni, J., Harbaugh, W., Vesterlund, L.: The carrot or the stick: rewards, punishments, and cooperation. Am. Econ. Rev. 93(3), 893\u2013902 (2003)","journal-title":"Am. Econ. Rev."},{"key":"2_CR3","unstructured":"Atkeson, C.G., Schaal, S.: Robot learning from demonstration. In: Proceedings of the Fourteenth International Conference on Machine Learning, ICML 1997, pp. 12\u201320. Morgan Kaufmann Publishers Inc., San Francisco (1997)"},{"issue":"1\u20132","key":"2_CR4","first-page":"1390","volume":"211","author":"R Axelrod","year":"1996","unstructured":"Axelrod, R., Hamilton, W.: The evolution of cooperation. Biosystems 211(1\u20132), 1390\u20131396 (1996)","journal-title":"Biosystems"},{"key":"2_CR5","unstructured":"Bandura, A., Walters, R.H.: Social Learning and Personality Development. Holt Rinehart and Winston, New York (1963). https:\/\/psycnet.apa.org\/record\/1963-35030-000"},{"key":"2_CR6","volume-title":"Social Learning Theory","author":"A Bandura","year":"1977","unstructured":"Bandura, A., Walters, R.H.: Social Learning Theory. Prentice-Hall, Englewood Cliffs (1977)"},{"issue":"4","key":"2_CR7","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1257\/aer.96.4.1029","volume":"96","author":"Y Bereby-Meyer","year":"2006","unstructured":"Bereby-Meyer, Y., Roth, A.E.: The speed of learning in noisy games: partial reinforcement and the sustainability of cooperation. Am. Econ. Rev. 96(4), 1029\u20131042 (2006)","journal-title":"Am. Econ. Rev."},{"key":"2_CR8","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National\/Tenth Conference on Artificial Intelligence\/Innovative Applications of Artificial Intelligence, pp. 746\u2013752 (1998)"},{"key":"2_CR9","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-94-010-2161-6_2","volume-title":"Game Theory as a Theory of a Conflict Resolution","author":"R Engelmore","year":"1978","unstructured":"Engelmore, R.: Prisoner\u2019s dilemma-recollections and observations. In: Rapoport, A. (ed.) Game Theory as a Theory of a Conflict Resolution, pp. 17\u201334. Springer, Dordrecht (1978). https:\/\/doi.org\/10.1007\/978-94-010-2161-6_2"},{"issue":"4","key":"2_CR10","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1257\/aer.90.4.980","volume":"90","author":"E Fehr","year":"2000","unstructured":"Fehr, E., Gachter, S.: Cooperation and punishment in public goods experiments. Am. Econ. Rev. 90(4), 980\u2013994 (2000)","journal-title":"Am. Econ. Rev."},{"key":"2_CR11","doi-asserted-by":"publisher","first-page":"026117","DOI":"10.1103\/PhysRevE.78.026117","volume":"78","author":"F Fu","year":"2008","unstructured":"Fu, F., Hauert, C., Nowa, M.A., Wang, L.: Reputation-based partner choice promotes cooperation in social networks. Phys. Rev. E 78, 026117 (2008)","journal-title":"Phys. Rev. E"},{"issue":"2","key":"2_CR12","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.obhdp.2005.08.005","volume":"101","author":"A Gunnthorsdottir","year":"2006","unstructured":"Gunnthorsdottir, A., Rapoport, A.: Embedding social dilemmas in intergroup competition reduces free-riding. Organ. Beha. Hum. Decis. Processes 101(2), 184\u2013199 (2006)","journal-title":"Organ. Beha. Hum. Decis. Processes"},{"key":"2_CR13","unstructured":"Hu, J., Wellman, M.P.: Multiagent reinforcement learning: theoretical framework and an algorithm. In: Proceedings of the Fifteenth International Conference on Machine Learning, ICML 1998, pp. 242\u2013250. Morgan Kaufmann Publishers Inc., San Francisco (1998)"},{"issue":"2","key":"2_CR14","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.obhdp.2012.11.003","volume":"120","author":"PAV Lange","year":"2013","unstructured":"Lange, P.A.V., Joireman, J., Parks, C.D., Dijk, E.V.: The psychology of social dilemmas: a review. Organ. Behav. Hum. Decis. Processes 120(2), 125\u2013141 (2013)","journal-title":"Organ. Behav. Hum. Decis. Processes"},{"key":"2_CR15","volume-title":"The Handbook of Experimental Economics","author":"J Ledyard","year":"1995","unstructured":"Ledyard, J.: A survey of experimental research. In: Kagel, J.H., Roth, A.E. (eds.) The Handbook of Experimental Economics. Princeton University Press, Princeton (1995)"},{"key":"2_CR16","unstructured":"Leibo, J.Z., Zambaldi, V., Lanctot, M., Marecki, J., Graepel, T.: Multi-agent reinforcement learning in sequential social dilemmas. In: Proceedings of the 16th Conference on Autonomous Agents and Multiagent Systems, pp. 464\u2013473 (2017)"},{"key":"2_CR17","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. In: NIPS Deep Learning Workshop 2013 (2013)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Nowak, M.A., Signmund, K.: Evolution of indirect reciprocity. In: Proceedings of the National Academy of Sciences, pp. 1291\u20131298 (2005)","DOI":"10.1038\/nature04131"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Rand, D.G., Arbesman, S., Christakis, N.A.: Dynamic social networks promote cooperation in experiments with humans. In: Proceedings of the National Academy of Sciences, pp. 19193\u201319198 (2011)","DOI":"10.1073\/pnas.1108243108"},{"issue":"1\u20132","key":"2_CR20","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/0303-2647(95)01551-5","volume":"37","author":"TW Sandholm","year":"1996","unstructured":"Sandholm, T.W., Crites, R.H.: Multiagent reinforcement learning in the iterated prisoner\u2019s dilemma. Biosystems 37(1\u20132), 147\u2013166 (1996)","journal-title":"Biosystems"},{"key":"2_CR21","doi-asserted-by":"publisher","first-page":"9929","DOI":"10.1073\/pnas.1206694109","volume":"109","author":"M van Veelen","year":"2012","unstructured":"van Veelen, M., Garcia, J., Rand, D.G., Nowak, M.A.: Direct reciprocity in structured populations. Proc. Natl. Acad. Sci. 109, 9929\u20139934 (2012)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"2_CR22","unstructured":"Wunder, M., Littman, M., Babes, M.: Classes of multiagent q-learning dynamics with greedy exploration. In: Proceedings of the 27th International Conference on Machine Learning, ICML 2010 (2010)"},{"key":"2_CR23","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: Proceedings of the 35th International Conference on Machine Learning, pp. 5571\u20135580 (2018)"},{"issue":"5","key":"2_CR24","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1109\/TCYB.2016.2543238","volume":"47","author":"L Zhou","year":"2017","unstructured":"Zhou, L., Yang, P., Chen, C., Gao, Y.: Multiagent reinforcement learning with sparse interactions by negotiation and knowledge transfer. IEEE Trans. Cybern. 47(5), 1238\u20131250 (2017)","journal-title":"IEEE Trans. Cybern."}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-75762-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T17:11:30Z","timestamp":1710349890000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-75762-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030757618","9783030757625"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-75762-5_2","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":"9 May 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 May 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 May 2021","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":"pakdd2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2021.org\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"673","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":"157","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":"0","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":"23% - 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":"7","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)"}}]}}