{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:28:39Z","timestamp":1766136519949},"reference-count":13,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2014,7,29]],"date-time":"2014-07-29T00:00:00Z","timestamp":1406592000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Life Robotics"],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1007\/s10015-014-0146-0","type":"journal-article","created":{"date-parts":[[2014,7,28]],"date-time":"2014-07-28T06:08:29Z","timestamp":1406527709000},"page":"109-114","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A reward allocation method for reinforcement learning in stabilizing control tasks"],"prefix":"10.1007","volume":"19","author":[{"given":"Shu","family":"Hosokawa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joji","family":"Kato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazushi","family":"Nakano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,7,29]]},"reference":[{"key":"146_CR1","doi-asserted-by":"crossref","unstructured":"Sutton RS,Barto AG (1998) Reinforcement learning an introduction. MIT Press, Cambridge","DOI":"10.1016\/S1474-6670(17)38315-5"},{"key":"146_CR2","first-page":"524","volume-title":"Readings in machine learning","author":"JJ Grefenstette","year":"1988","unstructured":"Grefenstette JJ (1988) Credit assignment in rule discovery systems based on genetic algorithms. In: Shavlik JW, Dietterich TG (eds) Readings in machine learning. Kaufmann, San Mateo, pp 524\u2013534"},{"issue":"1","key":"146_CR3","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1007\/s10015-008-0579-4","volume":"13","author":"J Ito","year":"2008","unstructured":"Ito J, Nakano K, Sakurama K, Hosokawa S (2008) Adaptive immunity based reinforcement learning. Artif Life Robot 13(1):188\u2013193","journal-title":"Artif Life Robot"},{"key":"146_CR4","unstructured":"Peng J (1993) Efficient dynamic programming-based learning for control. Northeastern University"},{"key":"146_CR5","unstructured":"Tyler S, Oliver J, Sannier A (2006) Verve: a general purpose open source reinforcement learning toolkit. In: ASME conference proceedings, vol 4255X, pp 359\u2013369"},{"issue":"3\u20134","key":"146_CR6","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins CJCH, Dayan P (1992) Technical note: q-learning. Mach Learn 8(3\u20134):279\u2013292","journal-title":"Mach Learn"},{"issue":"4","key":"146_CR7","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1007\/s10015-010-0867-7","volume":"15","author":"S Hosokawa","year":"2010","unstructured":"Hosokawa S, Nakano K, Sakurama K (2010) A consideration of human immunity-based reinforcement learning with continuous states. Artif Life Robot 15(4):560\u2013564","journal-title":"Artif Life Robot"},{"key":"146_CR8","doi-asserted-by":"crossref","unstructured":"Arai S, Sycara K, Payne TR (2000) Experience-based reinforcement learning to acquire effective behavior in a multi-agent domain","DOI":"10.1007\/3-540-44533-1_16"},{"key":"146_CR9","first-page":"580","volume":"9","author":"M Kazuteru","year":"1994","unstructured":"Kazuteru M, Masayuki Y, Shigenobu K (1994) A theory of profit sharing in reinforcement learning. J Jpn Soc Artif Intell 9:580\u2013587 (in japanese)","journal-title":"J Jpn Soc Artif Intell"},{"key":"146_CR10","doi-asserted-by":"crossref","unstructured":"Zheng Y, Luo S, Lv Z (2006) Control double inverted pendulum by reinforcement learning with double cmac network. In: Proceedings of the 18th international conference on pattern recongnition, vol 4 of ICPR06","DOI":"10.1109\/ICPR.2006.416"},{"key":"146_CR11","unstructured":"Atsushi S, Tohgoroh M, Hirohisa S (2003) Profit sharing considering penalty. In: The 17th annual conference of the japanese society for artificial intelligence, pp 3F4-02 (in japanese)"},{"key":"146_CR12","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton RS, Precup D, Singh S (1999) Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif Intell 112:181\u2013211","journal-title":"Artif Intell"},{"key":"146_CR13","unstructured":"Rummery GA, Niranjan M (1994) On line q-learning using connectionist systems. Technical Report CUED\/F-INFENG \/TR 166, Department of Engineering, Cambridge University"}],"container-title":["Artificial Life and Robotics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-014-0146-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10015-014-0146-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-014-0146-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,13]],"date-time":"2019-08-13T03:11:37Z","timestamp":1565665897000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10015-014-0146-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7,29]]},"references-count":13,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,9]]}},"alternative-id":["146"],"URL":"https:\/\/doi.org\/10.1007\/s10015-014-0146-0","relation":{},"ISSN":["1433-5298","1614-7456"],"issn-type":[{"value":"1433-5298","type":"print"},{"value":"1614-7456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7,29]]}}}