{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T21:42:42Z","timestamp":1745012562498},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2009,9,25]],"date-time":"2009-09-25T00:00:00Z","timestamp":1253836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Memetic Comp."],"published-print":{"date-parts":[[2009,12]]},"DOI":"10.1007\/s12293-009-0015-x","type":"journal-article","created":{"date-parts":[[2009,9,24]],"date-time":"2009-09-24T18:01:23Z","timestamp":1253815283000},"page":"305-313","source":"Crossref","is-referenced-by-count":11,"title":["Fast reinforcement learning for simple physical robots"],"prefix":"10.1007","volume":"1","author":[{"given":"Pitoyo","family":"Hartono","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sachiko","family":"Kakita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,9,25]]},"reference":[{"key":"15_CR1","unstructured":"Ackley D, Littman M (1992) Interactions between learning and evolution. In: Langton CG, Taylor C, Farmer CD, Rasmussen S (eds). Artificial life II, Addison-Wesley, Reading, MA, pp 487\u2013509"},{"key":"15_CR2","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","volume":"14","author":"J Elman","year":"1990","unstructured":"Elman J (1990) Finding structure in time. Cogn Sci 14: 179\u2013211","journal-title":"Cogn Sci"},{"issue":"2","key":"15_CR3","first-page":"141","volume":"2008","author":"P Hartono","year":"2008","unstructured":"Hartono P, Kakita S (2008) Embedded neural network for swarm learning of physical robots. Proc Int. Conf Artif Neural Netw 2008(2): 141\u2013149","journal-title":"Proc Int. Conf Artif Neural Netw"},{"key":"15_CR4","first-page":"3571","volume":"3","author":"P Hartono","year":"2003","unstructured":"Hartono P, Tabe K, Suzuki K, Hashimoto S (2003) Strategy acquirement by survival robots in outdoor environment. Proc IEEE Int Conf Robot Autom 3: 3571\u20133575","journal-title":"Proc IEEE Int Conf Robot Autom"},{"issue":"3","key":"15_CR5","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/TEVC.2005.850290","volume":"9","author":"S Kamio","year":"2005","unstructured":"Kamio S, Iba H (2005) Adaptation technique for integrating genetic programming and reinforcement learning for real robots. IEEE Trans Evol Comput 9(3): 318\u2013333","journal-title":"IEEE Trans Evol Comput"},{"key":"15_CR6","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/S0921-8890(99)00066-4","volume":"30","author":"C Kube","year":"2000","unstructured":"Kube C, Bonabeau E (2000) Cooperative transport by ants and robots. Robot Autonom Syst 30: 85\u2013101","journal-title":"Robot Autonom Syst"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Morimoto J, Cheng G, Atkeson G, Zeglin G (2004) A simple reinforcement learning algorithm for biped walking. Proceedings of the IEEE international conference on robotics and automation, pp 3030\u20133035","DOI":"10.1109\/ROBOT.2004.1307522"},{"key":"15_CR8","unstructured":"Nakatani M, Suzuki K, Hashimoto S (2003) Subjective-evaluation oriented teaching scheme for a biped humanoid robot. Proceedings of the 2003 IEEE-RAS international conference on humanoid robots"},{"issue":"5","key":"15_CR9","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1109\/TRA.2002.803465","volume":"18","author":"A Nakamura","year":"2002","unstructured":"Nakamura A, Ota J, Arai T (2002) Human-supervised multiple robot system. IEEE Trans Robot Autom 18(5): 728\u2013743","journal-title":"IEEE Trans Robot Autom"},{"key":"15_CR10","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1177\/105971239700500306","volume":"5","author":"S Nolfi","year":"1997","unstructured":"Nolfi S, Parisi D (1997) Learning to adapt to changing environments in evolving neural networks. Adapt Behav 5: 99\u2013105","journal-title":"Adapt Behav"},{"issue":"5","key":"15_CR11","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1109\/TEVC.2005.850262","volume":"9","author":"J Pettersson","year":"2005","unstructured":"Pettersson J, Wahde M (2005) Application of the utility function method for behavioral organization in a locomotion task. IEEE Trans Evol Comput 9(5): 506\u2013521","journal-title":"IEEE Trans Evol Comput"},{"key":"15_CR12","unstructured":"Qiao J, Hou Z, Ruan X (2008) Application of reinforcement learning based on neural network to dynamic obstacle avoidance. Proceedings of the IEEE international conference on information and automation, pp 784\u2013788"},{"key":"15_CR13","first-page":"3404","volume":"4","author":"WD Smart","year":"2002","unstructured":"Smart WD, Kaelbling LP (2002) Effective reinforcement learning for mobile robots. Proc IEEE Int Conf Robot Autom 4: 3404\u20133410","journal-title":"Proc IEEE Int Conf Robot Autom"},{"key":"15_CR14","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"key":"15_CR15","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1073\/pnas.70.4.997","volume":"70","author":"GS Stent","year":"1973","unstructured":"Stent GS (1973) A physiological mechanism for Hebb\u2019s postulate of learning. Proc Natl Acad Sci USA 70: 997\u20131001","journal-title":"Proc Natl Acad Sci USA"},{"issue":"7","key":"15_CR16","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/29.1638","volume":"36","author":"B Widrow","year":"1998","unstructured":"Widrow B, Winter R, Baxter R (1998) Layered neural nets for pattern recognition. IEEE Trans Acoust Speech Signal Process 36(7): 1109\u20131118","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"15_CR17","unstructured":"Yamaguchi T, Masubuchi M, Fujihara K, Yachida M (2006) Realtime reinforcement learning for a real robot in the real environment. Proceedings of the IEEE international conference on intelligent robots and systems, pp 1321\u20131328"}],"container-title":["Memetic Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12293-009-0015-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12293-009-0015-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12293-009-0015-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,2]],"date-time":"2019-06-02T07:45:52Z","timestamp":1559461552000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12293-009-0015-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,9,25]]},"references-count":17,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2009,12]]}},"alternative-id":["15"],"URL":"https:\/\/doi.org\/10.1007\/s12293-009-0015-x","relation":{},"ISSN":["1865-9284","1865-9292"],"issn-type":[{"value":"1865-9284","type":"print"},{"value":"1865-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,9,25]]}}}