{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T02:14:23Z","timestamp":1722392063758},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,11,1]],"date-time":"2012-11-01T00:00:00Z","timestamp":1351728000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2013,7]]},"DOI":"10.1007\/s10489-012-0392-6","type":"journal-article","created":{"date-parts":[[2012,10,31]],"date-time":"2012-10-31T03:20:27Z","timestamp":1351653627000},"page":"28-40","source":"Crossref","is-referenced-by-count":8,"title":["Multi-criteria expertness based cooperative Q-learning"],"prefix":"10.1007","volume":"39","author":[{"given":"Esmat","family":"Pakizeh","sequence":"first","affiliation":[]},{"given":"Maziar","family":"Palhang","sequence":"additional","affiliation":[]},{"given":"Mir Mohsen","family":"Pedram","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,11,1]]},"reference":[{"issue":"3","key":"392_CR1","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L Panait","year":"2005","unstructured":"Panait L, Luke S (2005) Cooperative multi-agent learning: the state of the art. J Auton Agents Multi-Agent Syst 11(3):387\u2013434","journal-title":"J Auton Agents Multi-Agent Syst"},{"key":"392_CR2","doi-asserted-by":"crossref","first-page":"401","DOI":"10.7551\/mitpress\/3232.003.0023","volume-title":"Genetic and cultural evolution of cooperation","author":"E Smith","year":"2003","unstructured":"Smith E (2003) Human cooperation: perspectives from behavioral ecology. In: Hammerstein P (ed) Genetic and cultural evolution of cooperation. MIT Press, Cambridge, pp\u00a0401\u2013427"},{"key":"392_CR3","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/3-540-44826-8_3","volume":"2636","author":"L Nunes","year":"2003","unstructured":"Nunes L, Oliveira E (2003) Cooperative learning using advice-exchange. J Adapt Agents Multi-Agent Syst 2636:33\u201348","journal-title":"J Adapt Agents Multi-Agent Syst"},{"key":"392_CR4","volume-title":"Reinforcement learning: an introduction to adaptive computation and machine learning","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction to adaptive computation and machine learning. MIT Press, Cambridge"},{"key":"392_CR5","first-page":"2261","volume-title":"Proceedings of the 2000 IEEE\/RSJ international conference on intelligent robots and systems","author":"M Nili Ahmadabadi","year":"2000","unstructured":"Nili Ahmadabadi M, Asadpour M, Khodaabakhsh Seyyed H, Nakano E (2000) Expertness measuring in cooperative learning. In: Proceedings of the 2000 IEEE\/RSJ international conference on intelligent robots and systems, pp\u00a02261\u20132267"},{"issue":"1","key":"392_CR6","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1109\/3477.979961","volume":"32","author":"M Nili Ahmadabadi","year":"2002","unstructured":"Nili Ahmadabadi M, Asadpour M (2002) Expertness based cooperative Q-learning. IEEE Trans Syst Man Cybern, Part B, Cybern 32(1):66\u201376","journal-title":"IEEE Trans Syst Man Cybern, Part B, Cybern"},{"issue":"2","key":"392_CR7","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s10489-006-9652-7","volume":"25","author":"N Dragoni","year":"2006","unstructured":"Dragoni N, Gaspari M, Guidi D (2006) An infrastructure to support cooperation of knowledge-level agents on the semantic grid. J Appl Intell 25(2):159\u2013180","journal-title":"J Appl Intell"},{"issue":"1","key":"392_CR8","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1023\/A:1008251315338","volume":"9","author":"M Kinney","year":"1998","unstructured":"Kinney M, Tsatsoulis C (1998) Learning communication strategies in multi-agent systems. J Appl Intell 9(1):71\u201391","journal-title":"J Appl Intell"},{"key":"392_CR9","unstructured":"Watkins CJCH (1989) Learning with delayed rewards. PhD Dissertation, Cambridge University, Psychology Department, England"},{"key":"392_CR10","unstructured":"Whitehead S, Ballard D (1991) A study of cooperative mechanisms for faster reinforcement learning. Technical Report 365, Computer Science Dept, University of Rochester"},{"key":"392_CR11","first-page":"487","volume-title":"Proceedings of tenth international conference on machine learning","author":"M Tan","year":"1993","unstructured":"Tan M (1993) Multi-agent reinforcement learning: independent vs cooperative agents. In: Proceedings of tenth international conference on machine learning, Amherst, America, pp\u00a0487\u2013494"},{"issue":"6","key":"392_CR12","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1109\/70.338535","volume":"10","author":"y Kuniyoshi","year":"1994","unstructured":"Kuniyoshi y (1994) Learning by watching: extracting reuseable task knowledge from visual observation of human performance. IEEE Trans Robot Autom 10(6):799\u2013822","journal-title":"IEEE Trans Robot Autom"},{"key":"392_CR13","first-page":"251","volume":"22","author":"R Maclin","year":"1996","unstructured":"Maclin R, Shavlik JW (1996) Creating advice-taking reinforcement learners. J Mach Learn 22:251\u2013282","journal-title":"J Mach Learn"},{"key":"392_CR14","volume-title":"AAAI 2010","author":"K Judah","year":"2010","unstructured":"Judah K, Roy S, Fern A, Dietterich T (2010) Reinforcement learning via practice and critique advice. In: AAAI 2010"},{"key":"392_CR15","unstructured":"Garland A, Alterman R (1995) Preparation of multi-agent knowledge for reuse. Technical Report, Waltham: AAAI fall symposium on adaptation of knowledge for reuse, November 10\u201312, Menlo Park, Canada"},{"key":"392_CR16","first-page":"33","volume-title":"Proceedings of adaptation, co evolution and learning in multi-agent systems: papers from the 1996 AAAI spring symposium","author":"A Garland","year":"1996","unstructured":"Garland A, Alterman R (1996) Multi-agent learning through collective memory. In: Proceedings of adaptation, co evolution and learning in multi-agent systems: papers from the 1996 AAAI spring symposium, Menlo Park, CA, pp\u00a033\u201338"},{"key":"392_CR17","first-page":"317","volume-title":"Proceeding of 22nd inter conf of the north American fuzzy information processing society","author":"MR Akbarzadeh","year":"2003","unstructured":"Akbarzadeh MR, Rezaei H, Naghibi MB (2003) A fuzzy adaptive algorithm for expertness based cooperative learning, application to herding problem. In: Proceeding of 22nd inter conf of the north American fuzzy information processing society, pp\u00a0317\u2013322"},{"key":"392_CR18","series-title":"LNAI","first-page":"60","volume-title":"Comparison and analysis of expertness measure in knowledge sharing among robots","author":"P Ritthipravat","year":"2006","unstructured":"Ritthipravat P, Maneewarn T, Wyatt J, Laowattana D (2006) Comparison and analysis of expertness measure in knowledge sharing among robots, LNAI, vol\u00a04031. Springer, Berlin, pp\u00a060\u201369"},{"key":"392_CR19","first-page":"224","volume-title":"Proceedings of international conference on computational intelligence and security workshops","author":"Y Yang","year":"2007","unstructured":"Yang Y, Tian Y, Mei H (2007) Cooperative Q learning based on blackboard architecture. In: Proceedings of international conference on computational intelligence and security workshops, pp\u00a0224\u2013227"},{"key":"392_CR20","volume-title":"2009 IEEE international conference on mechatronics and automation","author":"M Yang","year":"2009","unstructured":"Yang M, Tian Y, Liu X (2009) Cooperative Q-learning based on maturity of the policy. In: 2009 IEEE international conference on mechatronics and automation, August 9\u201312, Changchun, China"},{"key":"392_CR21","unstructured":"Bianchi RAC, Costa AHR (2004) The use of heuristics to speedup reinforcement learning. Boletim Interno, No. BT\/PCS 0409, Escola Polit\u00e9cnica da USP, S\u00e3o Paulo, Brazil, pp\u00a0125\u2013144"},{"key":"392_CR22","unstructured":"Kadle\u010dek D (2008) Motivation driven reinforcement learning and automatic creation of behavior hierarchies. PhD Dissertation, Faculty of Electrical Engineering, Czech Technical University in Prague"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-012-0392-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10489-012-0392-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-012-0392-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T22:44:47Z","timestamp":1714517087000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10489-012-0392-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,1]]},"references-count":22,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,7]]}},"alternative-id":["392"],"URL":"https:\/\/doi.org\/10.1007\/s10489-012-0392-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,11,1]]}}}