{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T04:27:20Z","timestamp":1665721640993},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,6,4]],"date-time":"2010-06-04T00:00:00Z","timestamp":1275609600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2012,1]]},"DOI":"10.1007\/s11227-010-0451-x","type":"journal-article","created":{"date-parts":[[2010,6,3]],"date-time":"2010-06-03T08:12:18Z","timestamp":1275552738000},"page":"526-547","source":"Crossref","is-referenced-by-count":9,"title":["Reinforcement learning technique using agent state occurrence frequency with analysis of knowledge sharing on the agent\u2019s learning process in multiagent environments"],"prefix":"10.1007","volume":"59","author":[{"given":"H. S.","family":"Al-Dayaa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D. B.","family":"Megherbi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,6,4]]},"reference":[{"key":"451_CR1","unstructured":"Al-Dayaa HS, Megherbi DB (2006) A fast reinforcement learning technique via multiple lookahead levels. In: Proceedings of the international conference on machine learning; applications, models, and technologies, Las Vegas, Nevada, USA, June, 2006"},{"key":"451_CR2","unstructured":"Al-Dayaa HS, Megherbi DB (2006) Fast reinforcement learning techniques using the Euclidean distance and agent state occurrence frequency. In: Proceedings of the international conference on machine learning; applications, models, and technologies, Las Vegas, Nevada, USA, June, 2006"},{"key":"451_CR3","unstructured":"American Association for Artificial Intelligence (2010) [online], Machine Learning. Available: http:\/\/www.aaai.org\/AITopics\/html\/machine.html , March 01, 2010 [date accessed]"},{"issue":"1","key":"451_CR4","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1049\/iet-gtd.2009.0168","volume":"4","author":"F Daneshfar","year":"2010","unstructured":"Daneshfar F, Bevrani H (2010) Load-frequency control: a GA-based multi-agent reinforcement learning. IEEE\/IET Gener Trans Distrib 4(1):13\u201326","journal-title":"IEEE\/IET Gener Trans Distrib"},{"key":"451_CR5","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1023\/A:1022694001379","volume":"6","author":"R Mantaras De","year":"1991","unstructured":"De Mantaras R (1991) A distance-based attribute selection measure for decision tree induction. Mach Learn 6:81\u201392","journal-title":"Mach Learn"},{"key":"451_CR6","volume-title":"Autonomous agents and multi-agent systems: explorations in learning, self-organization and adaptive computation","author":"L Jiming","year":"2001","unstructured":"Jiming L (2001) Autonomous agents and multi-agent systems: explorations in learning, self-organization and adaptive computation. World Scientific, Singapore"},{"key":"451_CR7","volume-title":"Advanced engineering mathematics","author":"E Kreyszig","year":"1993","unstructured":"Kreyszig E (1993) Advanced engineering mathematics, 7th edn. Wiley, New York","edition":"7"},{"key":"451_CR8","unstructured":"Liu S, Tian Y (2002) Multi-agent learning methods in an uncertain environment. In: International conference on machine learning and cybernetics, Beijing, 2002"},{"key":"451_CR9","doi-asserted-by":"crossref","unstructured":"Lozano E, Acuna E (2005) Parallel algorithms for distance-based and density-based outliers. In: Fifth IEEE international conference on data mining, 2005, pp 729\u2013732","DOI":"10.1109\/ICDM.2005.116"},{"key":"451_CR10","doi-asserted-by":"crossref","unstructured":"Lozano E, Acuna E (2005) Parallel algorithms for distance-based and density-based outliers. In: Fifth IEEE international conference on data mining 2005, pp 729\u2013732","DOI":"10.1109\/ICDM.2005.116"},{"key":"451_CR11","doi-asserted-by":"crossref","unstructured":"Makar R, Mahadevan S, Ghavamzadeh M (2001) Hierarchical multi-agent reinforcement learning. In: Proceedings of the fifth international conference on autonomous agents, Montreal, Quebec, Canada, 2001, pp 247\u2013253","DOI":"10.1145\/375735.376302"},{"issue":"4","key":"451_CR12","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1109\/TPWRS.2007.908471","volume":"22","author":"SDJ McArthur","year":"2007","unstructured":"McArthur SDJ, Davidson EM, Catterson VM, Dimeas AL, Hatziargyriou ND, Ponci F, Funabashi T (2007) Multi-agent systems for power engineering applications\u2014part II: technologies, standards, and tools for building multi-agent systems. IEEE Trans Power Syst 22(4):1743\u20131752","journal-title":"IEEE Trans Power Syst"},{"issue":"4","key":"451_CR13","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1109\/TPWRS.2007.908472","volume":"22","author":"SDJ McArthur","year":"2007","unstructured":"McArthur SDJ, Davidson EM, Catterson VM, Dimeas AL, Hatziargyriou ND, Ponci F, Funabashi T (2007) Multi-agent systems for power engineering applications\u2014part I: concepts, approaches, and technical challenges. IEEE Trans Power Syst 22(4):1753\u20131759","journal-title":"IEEE Trans Power Syst"},{"key":"451_CR14","unstructured":"Megherbi DB, Al-Dayaa HS (2007) A Lyapunov-stability-based system hardware architecture for a real-time multiple-look-ahead-levels reinforcement learning. In: Proceedings of the 2006 international conference on machine learning; models, technologies & applications, Nevada, USA, 2007"},{"key":"451_CR15","doi-asserted-by":"crossref","unstructured":"Megherbi DB, Teirelbar A, Boulenouar AJ (2001) A time-varying-environment machine learning technique for autonomous agent shortest path planning. In: Proceedings of the SPIE international conference on defense sensing. Unmanned Ground vehicle Technology, Orlando, Florida, USA, April, 2001, pp 419\u2013428","DOI":"10.1117\/12.440003"},{"key":"451_CR16","volume-title":"Machine learning","author":"TM Mitchell","year":"1997","unstructured":"Mitchell TM (1997) Machine learning. McGraw-Hill, New York"},{"key":"451_CR17","volume-title":"A mathematical introduction to robotic manipulation","author":"RM Murray","year":"1994","unstructured":"Murray RM, Li Z, Sastry SS (1994) A mathematical introduction to robotic manipulation. CRC Press LLC, Boca Raton"},{"key":"451_CR18","doi-asserted-by":"crossref","unstructured":"Rudek R, Koszalka L, Pozniak-Koszalka I (2005) Introduction to multi-agent modified Q-learning routing for computer networks. In: IEEE advanced industrial conference on telecommunications, 2005","DOI":"10.1109\/AICT.2005.53"},{"key":"451_CR19","unstructured":"Sutton RS (1990) Integrated architectures for learning, planning, and reaction based on approximating dynamic programming. In: Proceedings of the seventh int conf on machine learning, 1990, pp 216\u2013224"},{"key":"451_CR20","doi-asserted-by":"crossref","unstructured":"Sutton RS (1991) Dyna an integrated architecture for learning, planning, and reacting. In: Working notes of 1991 AAAI spring symposium, 1991, pp 151\u2013155","DOI":"10.1145\/122344.122377"},{"key":"451_CR21","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"issue":"3","key":"451_CR22","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1109\/TRO.2004.839224","volume":"21","author":"P Tabuada","year":"2005","unstructured":"Tabuada P, Pappas GJ, Lima P (2005) Motion feasibility of multi-agent formations. IEEE Trans Robot 21(3):387\u2013392","journal-title":"IEEE Trans Robot"},{"issue":"4","key":"451_CR23","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/TRO.2006.878948","volume":"22","author":"L Vig","year":"2006","unstructured":"Vig L, Adams JA (2006) Multi-robot coalition formation. IEEE Trans Robot 22(4):637\u2013649","journal-title":"IEEE Trans Robot"},{"key":"451_CR24","first-page":"279","volume":"8","author":"C Watkins","year":"1992","unstructured":"Watkins C, Dayan P (1992) Q-Learning. Mach Learn 8:279\u2013292","journal-title":"Mach Learn"},{"key":"451_CR25","volume-title":"Multiagent systems: a modern approach to distributed artificial intelligence","author":"G Weiss","year":"1999","unstructured":"Weiss G (1999) Multiagent systems: a modern approach to distributed artificial intelligence. MIT Press, Cambridge"},{"key":"451_CR26","doi-asserted-by":"crossref","unstructured":"Yamamura T, Umano M, Seta K (2006) Reinforcement learning of agent with a staged view in distance and direction for the pursuit problem. In: IEEE international conference on fuzzy systems, Vancouver, BC, Canada, July 2006","DOI":"10.1109\/FUZZY.2006.1681706"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-010-0451-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-010-0451-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-010-0451-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T06:24:01Z","timestamp":1559370241000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-010-0451-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,6,4]]},"references-count":26,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,1]]}},"alternative-id":["451"],"URL":"https:\/\/doi.org\/10.1007\/s11227-010-0451-x","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,6,4]]}}}