{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:26:09Z","timestamp":1725992769330},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030014209"},{"type":"electronic","value":"9783030014216"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","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":[[2018]]},"DOI":"10.1007\/978-3-030-01421-6_24","type":"book-chapter","created":{"date-parts":[[2018,9,25]],"date-time":"2018-09-25T16:50:11Z","timestamp":1537894211000},"page":"240-249","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Action Markets in Deep Multi-Agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Kyrill","family":"Schmid","sequence":"first","affiliation":[]},{"given":"Lenz","family":"Belzner","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Gabor","sequence":"additional","affiliation":[]},{"given":"Thomy","family":"Phan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,9,26]]},"reference":[{"key":"24_CR1","unstructured":"Foerster, J., Assael, Y.M., de Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2137\u20132145 (2016)"},{"key":"24_CR2","unstructured":"Foerster, J.N., Chen, R.Y., Al-Shedivat, M., Whiteson, S., Abbeel, P., Mordatch, I.: Learning with opponent-learning awareness. arXiv preprint arXiv:1709.04326 (2017)"},{"key":"24_CR3","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","volume-title":"Autonomous Agents and Multiagent Systems","author":"Jayesh K. Gupta","year":"2017","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multiagent control using deep reinforcement learning. In: Proceedings of the Adaptive and Learning Agents Workshop (AAMAS 2017) (2017)"},{"key":"24_CR4","unstructured":"Hernandez-Leal, P., Kaisers, M., Baarslag, T., de Cote, E.M.: A survey of learning in multiagent environments: Dealing with non-stationarity. arXiv preprint arXiv:1707.09183 (2017)"},{"key":"24_CR5","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"24_CR6","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-642-27645-3_2","volume-title":"Reinforcement Learning","author":"S Lange","year":"2012","unstructured":"Lange, S., Gabel, T., Riedmiller, M.: Batch reinforcement learning. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning, pp. 45\u201373. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_2"},{"issue":"1","key":"24_CR7","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3233\/KES-2010-0206","volume":"15","author":"Guillaume J. Laurent","year":"2011","unstructured":"Laurent, G.J., Matignon, L., Fort-Piat, L., et al.: The world of independent learners is not Markovian. Int. J. Knowl. Based Intell. Eng. Syst. 15(1), 55\u201364 (2011)","journal-title":"International Journal of Knowledge-based and Intelligent Engineering Systems"},{"key":"24_CR8","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. International Foundation for Autonomous Agents and Multiagent Systems (2017)"},{"key":"24_CR9","unstructured":"Lerer, A., Peysakhovich, A.: Maintaining cooperation in complex social dilemmas using deep reinforcement learning. arXiv preprint arXiv:1707.01068 (2017)"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning, vol. 157, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"24_CR11","unstructured":"Malialis, K., Devlin, S., Kudenko, D.: Resource abstraction for reinforcement learning in multiagent congestion problems. In: Proceedings of the 2016 International Conference on Autonomous Agents and Multiagent Systems, pp. 503\u2013511. International Foundation for Autonomous Agents and Multiagent Systems (2016)"},{"issue":"7540","key":"24_CR12","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"Volodymyr Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"24_CR13","volume-title":"A Course in Game Theory","author":"MJ Osborne","year":"1994","unstructured":"Osborne, M.J., Rubinstein, A.: A Course in Game Theory. MIT Press, Cambridge (1994)"},{"issue":"3","key":"24_CR14","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: the state of the art. Auton. Agents Multi Agent Syst. 11(3), 387\u2013434 (2005)","journal-title":"Auton. Agents Multi Agent Syst."},{"key":"24_CR15","unstructured":"Perolat, J., Leibo, J.Z., Zambaldi, V., Beattie, C., Tuyls, K., Graepel, T.: A multi-agent reinforcement learning model of common-pool resource appropriation. arXiv preprint arXiv:1707.06600 (2017)"},{"key":"24_CR16","unstructured":"Peysakhovich, A., Lerer, A.: Prosocial learning agents solve generalized stag hunts better than selfish ones. arXiv preprint arXiv:1709.02865 (2017)"},{"key":"24_CR17","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"24_CR18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811654","volume-title":"Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations","author":"Y Shoham","year":"2008","unstructured":"Shoham, Y., Leyton-Brown, K.: Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations. Cambridge University Press, Cambridge (2008)"},{"issue":"7676","key":"24_CR19","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"David Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of Go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"issue":"4","key":"24_CR20","doi-asserted-by":"publisher","first-page":"e0172395","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"Ardi Tampuu","year":"2017","unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. PloS One 12(4), e0172395 (2017)","journal-title":"PLOS ONE"},{"key":"24_CR21","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/B978-1-55860-307-3.50049-6","volume-title":"Machine Learning Proceedings 1993","author":"Ming Tan","year":"1993","unstructured":"Tan, M.: Multi-agent reinforcement learning: independent vs. cooperative agents. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 330\u2013337 (1993)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2018"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01421-6_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,24]],"date-time":"2019-10-24T17:31:55Z","timestamp":1571938315000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-01421-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030014209","9783030014216"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01421-6_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rhodes","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"360","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"139","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"28","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"39% - 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"}},{"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"}},{"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"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"In addition there are 41 full poster papers and 11 short poster papers included in the proceedings","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}