{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:38Z","timestamp":1750220198527,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft (DFG)","doi-asserted-by":"publisher","award":["210487104"],"award-info":[{"award-number":["210487104"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Research Council (ERC)","award":["773196"],"award-info":[{"award-number":["773196"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1145\/3545008.3545025","type":"proceedings-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T01:04:08Z","timestamp":1673744648000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Mean-Field Control for Delayed Information Load Balancing in Large Queuing Systems"],"prefix":"10.1145","author":[{"given":"Anam","family":"Tahir","sequence":"first","affiliation":[{"name":"Self-Organizing Systems Lab, Technische Universit\u00e4t Darmstadt, Germany"}]},{"given":"Kai","family":"Cui","sequence":"additional","affiliation":[{"name":"Self-Organizing Systems Lab, Technische Universit\u00e4t Darmstadt, Germany"}]},{"given":"Heinz","family":"Koeppl","sequence":"additional","affiliation":[{"name":"Self-Organizing Systems Lab, Technische Universit\u00e4t Darmstadt, Germany"}]}],"member":"320","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Machine Learning for Communications. Entropy 23, 7","author":"Aggarwal Vaneet","year":"2021","unstructured":"Vaneet Aggarwal. 2021. Machine Learning for Communications. Entropy 23, 7 (2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-010-9123-8"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2019.1014"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2014.7039639"},{"volume-title":"Mean field games and mean field type control theory. Vol.\u00a0101","author":"Bensoussan Alain","key":"e_1_3_2_1_5_1","unstructured":"Alain Bensoussan, Jens Frehse, Phillip Yam, 2013. Mean field games and mean field type control theory. Vol.\u00a0101. Springer."},{"key":"e_1_3_2_1_6_1","volume-title":"Superhuman AI for multiplayer poker. Science 365, 6456","author":"Brown Noam","year":"2019","unstructured":"Noam Brown and Tuomas Sandholm. 2019. Superhuman AI for multiplayer poker. Science 365, 6456 (2019), 885\u2013890."},{"key":"e_1_3_2_1_7_1","unstructured":"Ren\u00e9 Carmona Mathieu Lauri\u00e8re and Zongjun Tan. 2019. Model-free mean-field reinforcement learning: mean-field MDP and mean-field Q-learning. arXiv preprint arXiv:1910.12802(2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR","author":"Cui Kai","year":"2021","unstructured":"Kai Cui and Heinz Koeppl. 2021. Approximately solving mean field games via entropy-regularized deep reinforcement learning. In International Conference on Artificial Intelligence and Statistics. PMLR, 1909\u20131917."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683749"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-005-6971-z"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1214\/21-AOP1548"},{"key":"e_1_3_2_1_12_1","volume-title":"The journal of physical chemistry 81, 25","author":"Gillespie T","year":"1977","unstructured":"Daniel\u00a0T Gillespie. 1977. The journal of physical chemistry 81, 25 (1977), 2340\u20132361."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1360700"},{"key":"e_1_3_2_1_14_1","unstructured":"Xin Guo Anran Hu Renyuan Xu and Junzi Zhang. 2019. Learning mean-field games. In Advances in Neural Information Processing Systems. 4966\u20134976."},{"volume-title":"Discrete-time Markov control processes: basic optimality criteria. Vol.\u00a030","author":"Hern\u00e1ndez-Lerma On\u00e9simo","key":"e_1_3_2_1_15_1","unstructured":"On\u00e9simo Hern\u00e1ndez-Lerma and Jean\u00a0B Lasserre. 2012. Discrete-time Markov control processes: basic optimality criteria. Vol.\u00a030. Springer Science & Business Media."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.4310\/CIS.2006.v6.n3.a5"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1987.272835"},{"key":"e_1_3_2_1_19_1","volume-title":"Mean field games. Japanese journal of mathematics 2, 1","author":"Lasry Jean-Michel","year":"2007","unstructured":"Jean-Michel Lasry and Pierre-Louis Lions. 2007. Mean field games. Japanese journal of mathematics 2, 1 (2007), 229\u2013260."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-0864-6_3"},{"key":"e_1_3_2_1_21_1","volume-title":"International Conference on Machine Learning. PMLR, 3053\u20133062","author":"Liang Eric","year":"2018","unstructured":"Eric Liang, Richard Liaw, Robert Nishihara, Philipp Moritz, Roy Fox, Ken Goldberg, Joseph Gonzalez, Michael Jordan, and Ion Stoica. 2018. RLlib: Abstractions for distributed reinforcement learning. In International Conference on Machine Learning. PMLR, 3053\u20133062."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1287\/stsy.2019.0045"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"e_1_3_2_1_24_1","first-page":"143","article-title":"Conditional strong law of large number","volume":"20","author":"Majerek Dariusz","year":"2005","unstructured":"Dariusz Majerek, Wioletta Nowak, and Wieslaw Zieba. 2005. Conditional strong law of large number. Int. J. Pure Appl. Math 20, 2 (2005), 143\u2013156.","journal-title":"Int. J. Pure Appl. Math"},{"key":"e_1_3_2_1_25_1","volume-title":"How useful is old information?IEEE Transactions on Parallel and Distributed Systems 11, 1","author":"Mitzenmacher Michael","year":"2000","unstructured":"Michael Mitzenmacher. 2000. How useful is old information?IEEE Transactions on Parallel and Distributed Systems 11, 1 (2000), 6\u201320."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.963420"},{"key":"e_1_3_2_1_27_1","volume-title":"Human-level control through deep reinforcement learning. nature 518, 7540","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei\u00a0A Rusu, Joel Veness, Marc\u00a0G Bellemare, Alex Graves, Martin Riedmiller, Andreas\u00a0K Fidjeland, Georg Ostrovski, 2015. Human-level control through deep reinforcement learning. nature 518, 7540 (2015), 529\u2013533."},{"key":"e_1_3_2_1_28_1","unstructured":"Washim\u00a0Uddin Mondal Mridul Agarwal Vaneet Aggarwal and Satish\u00a0V Ukkusuri. 2021. On the approximation of cooperative heterogeneous multi-agent reinforcement learning (marl) using mean field control (mfc). arXiv preprint arXiv:2109.04024(2021)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1287\/stsy.2018.0016"},{"volume-title":"A concise introduction to decentralized POMDPs","author":"Oliehoek A","key":"e_1_3_2_1_30_1","unstructured":"Frans\u00a0A Oliehoek and Christopher Amato. 2016. A concise introduction to decentralized POMDPs. Springer."},{"volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"Puterman L","key":"e_1_3_2_1_31_1","unstructured":"Martin\u00a0L Puterman. 2014. Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1137\/17M1112583"},{"key":"e_1_3_2_1_33_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347(2017)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11134-016-9497-7"},{"key":"e_1_3_2_1_35_1","volume-title":"A survey of Markov decision models for control of networks of queues. Queueing systems 13, 1","author":"Stidham Shaler","year":"1993","unstructured":"Shaler Stidham and Richard Weber. 1993. A survey of Markov decision models for control of networks of queues. Queueing systems 13, 1 (1993), 291\u2013314."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.5555\/3306127.3331700"},{"volume-title":"Reinforcement learning: An introduction","author":"Sutton S","key":"e_1_3_2_1_37_1","unstructured":"Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3322205.3311075"},{"key":"e_1_3_2_1_39_1","unstructured":"Mark van\u00a0der Boor Sem\u00a0C Borst Johan\u00a0SH van Leeuwaarden and Debankur Mukherjee. 2018. Scalable load balancing in networked systems: A survey of recent advances. arXiv preprint arXiv:1806.05444(2018)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/2777647.2777653"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.2307\/3213271"},{"key":"e_1_3_2_1_42_1","volume-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of Reinforcement Learning and Control","author":"Zhang Kaiqing","year":"2021","unstructured":"Kaiqing Zhang, Zhuoran Yang, and Tamer Ba\u015far. 2021. Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of Reinforcement Learning and Control (2021), 321\u2013384."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2020.102146"}],"event":{"name":"ICPP '22: 51st International Conference on Parallel Processing","acronym":"ICPP '22","location":"Bordeaux France"},"container-title":["Proceedings of the 51st International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545025","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3545008.3545025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:43Z","timestamp":1750186963000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":43,"alternative-id":["10.1145\/3545008.3545025","10.1145\/3545008"],"URL":"https:\/\/doi.org\/10.1145\/3545008.3545025","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"2023-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}