{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:38:04Z","timestamp":1742974684232,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031333767"},{"type":"electronic","value":"9783031333774"}],"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\/978-3-031-33377-4_28","type":"book-chapter","created":{"date-parts":[[2023,5,27]],"date-time":"2023-05-27T09:02:36Z","timestamp":1685178156000},"page":"361-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Regularization of\u00a0the\u00a0Policy Updates for\u00a0Stabilizing Mean Field Games"],"prefix":"10.1007","author":[{"given":"Talal","family":"Algumaei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruben","family":"Solozabal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reda","family":"Alami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hakim","family":"Hacid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Merouane","family":"Debbah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Tak\u00e1\u010d","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,5,28]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","DOI":"10.1038\/nature16961"},{"issue":"7839","key":"28_CR2","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., Antonoglou, I., Hubert, T., Simonyan, K., Sifre, L., Schmitt, S., Guez, A., Lockhart, E., Hassabis, D., Graepel, T., et al.: Mastering atari, go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020)","journal-title":"Nature"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","DOI":"10.1038\/s41586-019-1724-z"},{"key":"28_CR4","unstructured":"Son, K., Kim, D., Kang, W.J., Hostallero, D.E., Yi, Y.: Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5887\u20135896. PMLR (2019)"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Mathieu. Lauriere. Numerical methods for mean field games and mean field type control. Mean Field Games 78 p221 (2021)","DOI":"10.1090\/psapm\/078\/06"},{"issue":"3","key":"28_CR6","doi-asserted-by":"publisher","first-page":"221","DOI":"10.4310\/CIS.2006.v6.n3.a5","volume":"6","author":"M Huang","year":"2006","unstructured":"Huang, M., et al.: Large population stochastic dynamic games: closed-loop mckean-vlasov systems and the nash certainty equivalence principle. Commun. Inf. Syst. 6(3), 221\u2013252 (2006)","journal-title":"Commun. Inf. Syst."},{"key":"28_CR7","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1613\/jair.5449","volume":"59","author":"E Sonu","year":"2017","unstructured":"Sonu, E., Chen, Y., Doshi, P.: Decision-theoretic planning under anonymity in agent populations. J. Artif. Intell. Res. 59, 725\u2013770 (2017)","journal-title":"J. Artif. Intell. Res."},{"key":"28_CR8","unstructured":"Perolat, J., et al.: Scaling up mean field games with online mirror descent. arXiv:2103.00623 (2021)"},{"key":"28_CR9","unstructured":"Lauri\u00e8re, M., et al.: Scalable deep reinforcement learning algorithms for mean field games. arXiv:2203.11973 (2022)"},{"key":"28_CR10","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 (2017)"},{"key":"28_CR11","unstructured":"Lanctot, M., et al.: Openspiel: a framework for reinforcement learning in games. arXiv:1908.09453 (2019)"},{"key":"28_CR12","unstructured":"Subramanian, S.G., Taylor, M.E., Crowley, M., Poupart, P.: Partially observable mean field reinforcement learning. arXiv:2012.15791 (2020)"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Angiuli, A., Fouque, J.-P., Lauri\u00e8re, M.: Unified reinforcement q-learning for mean field game and control problems. Mathematics of Control, Signals, and Systems, pp. 1\u201355 (2022)","DOI":"10.1007\/s00498-021-00310-1"},{"key":"28_CR14","unstructured":"Subramanian, J., Mahajan, A.: Reinforcement learning in stationary mean-field games. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, pp. 251\u2013259 (2019)"},{"key":"28_CR15","doi-asserted-by":"crossref","unstructured":"Mishra, R.K., Vasal, D., Vishwanath, S.: Model-free reinforcement learning for non-stationary mean field games. In: 2020 59th IEEE Conference on Decision and Control (CDC), pp. 1032\u20131037. IEEE (2020)","DOI":"10.1109\/CDC42340.2020.9304340"},{"key":"28_CR16","unstructured":"Cui, K., Koeppl, H.: Approximately solving mean field games via entropy-regularized deep reinforcement learning. In: International Conference on Artificial Intelligence and Statistics, pp. 1909\u20131917. PMLR (2021)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Cardaliaguet, P., Hadikhanloo, S.: Learning in mean field games: the fictitious play. ESAIM: Control, Optimisation and Calculus of Variations, 23 (2017)","DOI":"10.1051\/cocv\/2016004"},{"key":"28_CR18","unstructured":"Perrin, S., P\u00e9rolat, J., Lauri\u00e8re, M., Geist, M., Elie, R., Pietquin, O.: Fictitious play for mean field games: Continuous time analysis and applications. Advances in Neural Information Processing Systems, 33 (2020)"},{"key":"28_CR19","unstructured":"Heinrich, J., Silver, D.: Deep reinforcement learning from self-play in imperfect-information games. arXiv:1603.01121 (2016)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Cacace, S., Camilli, F., Goffi, A.: A policy iteration method for mean field games. ESAIM: Control, Optimisation and Calculus of Variations, 27, p. 85 (2021)","DOI":"10.1051\/cocv\/2021081"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Shalev-Shwartz, S., et al.: Online learning and online convex optimization. Found. Trends Mach. Learn. 4(2), 107\u2013194 (2012)","DOI":"10.1561\/2200000018"},{"key":"28_CR22","first-page":"4235","volume":"33","author":"N Vieillard","year":"2020","unstructured":"Vieillard, N., Pietquin, O., Geist, M.: Munchausen reinforcement learning. Adv. Neural. Inf. Process. Syst. 33, 4235\u20134246 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"28_CR23","unstructured":"Zaman, M.A.U., et al.: Oracle-free reinforcement learning in mean-field games along a single sample path. In: International Conference on Artificial Intelligence and Statistics, pp. 10178\u201310206. PMLR (2023)"},{"key":"28_CR24","unstructured":"Xie, Q., Yang, Z., Wang, Z., Minca, A.: Learning while playing in mean-field games: Convergence and optimality. In: International Conference on Machine Learning, pp. 11436\u201311447. PMLR (2021)"},{"key":"28_CR25","unstructured":"Fu, Z., Yang, Z., Chen, Y., Wang, Z.: Actor-critic provably finds nash equilibria of linear-quadratic mean-field games. arXiv:1910.07498 (2019)"},{"key":"28_CR26","unstructured":"Angiuli, A., Fouque, J.-P., Lauriere, M.: Reinforcement learning for mean field games, with applications to economics. arXiv:2106.13755 (2021)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Aneeq uz Zaman, M., Zhang, K., Miehling, E., Basar, T.: Reinforcement learning in non-stationary discrete-time linear-quadratic mean-field games. In: 2020 59th IEEE Conference on Decision and Control (CDC), pp. 2278\u20132284. IEEE (2020)","DOI":"10.1109\/CDC42340.2020.9304279"},{"key":"28_CR28","unstructured":"Yu, C., Velu, A., Vinitsky, E., Wang, Y., Bayen, A., Wu, Y.: The surprising effectiveness of ppo in cooperative, multi-agent games. arXiv:2103.01955 (2021)"},{"issue":"6218","key":"28_CR29","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1126\/science.1259433","volume":"347","author":"M Bowling","year":"2015","unstructured":"Bowling, M., Burch, N., Johanson, M., Tammelin, O.: Heads-up limit hold\u2019em poker is solved. Science 347(6218), 145\u2013149 (2015)","journal-title":"Science"},{"key":"28_CR30","unstructured":"Lanctot, M., Waugh, K., Zinkevich, M., Bowling, M.: Monte carlo sampling for regret minimization in extensive games. Advances in neural information processing systems, 22 (2009)"}],"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\/978-3-031-33377-4_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T12:04:59Z","timestamp":1686917099000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33377-4_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031333767","9783031333774"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33377-4_28","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":"28 May 2023","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":"Osaka","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 May 2023","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":"pakdd2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2023.org\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"813","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":"143","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":"18% - 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":"3.5","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":"10","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)"}}]}}