{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T08:19:23Z","timestamp":1697530763314},"reference-count":14,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2006,6,19]],"date-time":"2006-06-19T00:00:00Z","timestamp":1150675200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems & Computers in Japan"],"published-print":{"date-parts":[[2006,8]]},"abstract":"Abstract<\/jats:title>One method of designing a multiagent system is called multiagent reinforcement learning. In multiagent reinforcement learning, an agent also observes the other agents as part of the environment. As a result, as the number of agents increases, the state space increases exponentially (curse of dimensionality), and the learning speed decreases dramatically. The amount of memory required for learning also becomes enormous. Modular Q\u2010learning, which was proposed as a technique for solving this problem, has the disadvantage that the learning performance decreases due to the incompleteness of perception. In the current research, the authors propose the HMQL technique for improving the learning performance of Modular Q\u2010learning by using a method of partially increasing the dimensionality of the state space. \u00a9 2006 Wiley Periodicals, Inc. Syst Comp Jpn, 37(9): 22\u201331, 2006; Published online in Wiley InterScience (www.interscience.wiley.com<\/jats:ext-link>). DOI 10.1002\/scj.20526<\/jats:p>","DOI":"10.1002\/scj.20526","type":"journal-article","created":{"date-parts":[[2006,6,19]],"date-time":"2006-06-19T18:04:35Z","timestamp":1150740275000},"page":"22-31","source":"Crossref","is-referenced-by-count":4,"title":["Multiagent reinforcement learning with the partly high\u2010dimensional state space"],"prefix":"10.1002","volume":"37","author":[{"given":"Kazuyuki","family":"Fujita","sequence":"first","affiliation":[]},{"given":"Hiroshi","family":"Matsuo","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2006,6,19]]},"reference":[{"key":"e_1_2_1_2_2","volume-title":"Reinforcement learning: An introduction","author":"Sutton RS","year":"1998"},{"key":"e_1_2_1_3_2","first-page":"476","article-title":"Multiagent reinforcement learning\u2014Uniting planning, theory, and various techniques for implementation","volume":"16","author":"Arai S","year":"2001","journal-title":"J Japan Soc Artif Intell"},{"key":"e_1_2_1_4_2","first-page":"1017","article-title":"Improving elevator performance using reinforcement learning","volume":"8","author":"Crites RH","year":"1996","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_1_5_2","unstructured":"WolpertDH SillJ TumerK.Reinforcement learning in distributed domains: Beyond team games. Proc 17th National Conference on Artificial Intelligence p819\u2013824 Seattle WA 2001."},{"key":"e_1_2_1_6_2","first-page":"518","article-title":"Perspective of multiagent social simulation","volume":"46","author":"Kurumatani K","year":"2002","journal-title":"ISCIE J Syst Control Inf"},{"key":"e_1_2_1_7_2","doi-asserted-by":"publisher","DOI":"10.7210\/jrsj.20.281"},{"key":"e_1_2_1_8_2","unstructured":"EdazawaK TakahashiY AsadaM.Behavior acquisition in a multi\u2010agent environment using multiple learning modules. 20th Annual Conference of the Robotics Society of Japan 3H33 2002."},{"key":"e_1_2_1_9_2","first-page":"51","article-title":"State generalization with support vector machines in reinforcement learning","author":"Goto R","year":"2002","journal-title":"4th Asia\u2010Pacific Conference on Simulated Evolution and Learning"},{"key":"e_1_2_1_10_2","doi-asserted-by":"publisher","DOI":"10.7210\/jrsj.21.164"},{"key":"e_1_2_1_11_2","doi-asserted-by":"crossref","unstructured":"GultekinI ArslanA.Modular\u2010fuzzy cooperation algorithm for multi\u2010agent systems. Advances in Information Systems: 2nd International Conference p255\u2013263 2002.","DOI":"10.1007\/3-540-36077-8_26"},{"key":"e_1_2_1_12_2","first-page":"285","article-title":"Speeding up multiagent reinforcement learning by coarse\u2010graining of perception: The hunter game","volume":"84","author":"Ito A","year":"2001","journal-title":"Trans IEICE"},{"key":"e_1_2_1_13_2","unstructured":"OnoN FukumotoK.Multi\u2010agent reinforcement learning: A modular approach. Proc 2nd International Conference on Multi\u2010agent Systems (ICMAS\u201096) p252\u2013258 AAAI Press."},{"key":"e_1_2_1_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3184-5_3"},{"key":"e_1_2_1_15_2","first-page":"821","article-title":"Reinforcement learning using a policy estimate of the other agent in a two\u2010agent stochastic game","volume":"86","author":"Nagayuki Y","year":"2003","journal-title":"Trans IEICE"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.20526","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.20526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T07:47:40Z","timestamp":1697528860000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.20526"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,6,19]]},"references-count":14,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2006,8]]}},"alternative-id":["10.1002\/scj.20526"],"URL":"https:\/\/doi.org\/10.1002\/scj.20526","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"value":"0882-1666","type":"print"},{"value":"1520-684X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,6,19]]}}}