{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T18:31:53Z","timestamp":1758393113577,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T00:00:00Z","timestamp":1667001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T00:00:00Z","timestamp":1667001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,29]]},"DOI":"10.1109\/besc57393.2022.9995509","type":"proceedings-article","created":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T18:48:27Z","timestamp":1672253307000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Parameter Tuning Method for Multi-agent Simulation using Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Masanori","family":"Hirano","sequence":"first","affiliation":[{"name":"The University of Tokyo,School of Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiyoshi","family":"Izumi","sequence":"additional","affiliation":[{"name":"The University of Tokyo,School of Engineering,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0263150"},{"article-title":"Emergent Tool Use From Multi-Agent Autocurricula","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR) 2020","author":"Baker","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aad0299"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1469-7688\/2\/5\/303"},{"key":"ref7","article-title":"Measuring and modelling realized volatility: from tick-by-tick to long memory","volume-title":"Ph.D. dissertation","author":"Corsi","year":"2005"},{"issue":"4","key":"ref8","article-title":"Towards Good Social Science","volume":"8","author":"Edmonds","year":"2005","journal-title":"Journal of Artificial Societies and Social Simulation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/460685a"},{"article-title":"Noisy Networks for Exploration","year":"2017","author":"Fortunato","key":"ref10"},{"article-title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","volume-title":"Proceedings of 7th International Conference on Learning Representations, ICLR 2019","author":"Frankle","key":"ref11"},{"key":"ref12","first-page":"2976","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume-title":"Proceedings of 35th International Conference on Machine Learning, ICML 2018","volume":"5","author":"Haarnoja"},{"article-title":"Soft Actor-Critic Algorithms and Applications","year":"2018","author":"Haarnoja","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/jrfm13040075"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IIAI-AAI50415.2020.00103"},{"article-title":"Continuous control with deep reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Lillicrap","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/17290"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1527\/tjsai.ag-e"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3403461"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/isaf.1374"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20937-7_9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.phpro.2014.08.134"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1541\/ieejeiss.133.1779"},{"volume-title":"OpenAI Baselines: ACKTR & A2C","year":"2017","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3389817"},{"volume-title":"On-line Q-learning using connectionist systems","year":"1994","author":"Rummery","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18564\/jasss.2988"},{"issue":"9","key":"ref29","first-page":"1286","article-title":"Estimation of Large-Scale Pedestrian Movement Using Data Assimilation","volume":"J101","author":"Shigenaka","year":"2018","journal-title":"IEICE Transactions on Information and Systems D"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref30"},{"article-title":"Plham: Platform for Large-scale and High-frequency Artificial Market","year":"2016","author":"Torii","key":"ref31"},{"article-title":"PlhamJ","year":"2019","author":"Torii","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s40844-015-0024-z"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10015-017-0368-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1891\/9780826163240.0014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.36.823"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"issue":"3\u20134","key":"ref38","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.11.007"},{"issue":"SAI-039","key":"ref40","first-page":"05","article-title":"Estimation of Large-scale Multi Agent Simulation Results Using Neural Networks [in Japanese]","volume":"2020","author":"Yamashita","year":"2020","journal-title":"Japanese Special Interest Group on Society and Artificial Intelligence (SIG-SAI)"}],"event":{"name":"2022 9th International Conference on Behavioural and Social Computing (BESC)","start":{"date-parts":[[2022,10,29]]},"location":"Matsuyama, Japan","end":{"date-parts":[[2022,10,31]]}},"container-title":["2022 9th International Conference on Behavioural and Social Computing (BESC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9994792\/9994886\/09995509.pdf?arnumber=9995509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:50:23Z","timestamp":1706791823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9995509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,29]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/besc57393.2022.9995509","relation":{},"subject":[],"published":{"date-parts":[[2022,10,29]]}}}