{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T10:41:59Z","timestamp":1707993719830},"reference-count":52,"publisher":"Informa UK Limited","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cybernetics and Systems"],"published-print":{"date-parts":[[2004,12,9]]},"DOI":"10.1080\/01969720590887270","type":"journal-article","created":{"date-parts":[[2007,6,25]],"date-time":"2007-06-25T13:33:44Z","timestamp":1182778424000},"page":"1-44","source":"Crossref","is-referenced-by-count":3,"title":["A BIOLOGICALLY INSPIRED HIERARCHICAL REINFORCEMENT LEARNING SYSTEM"],"prefix":"10.1080","volume":"36","author":[{"given":"WEIDONG","family":"ZHOU","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"RICHARD","family":"COGGINS","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"301","reference":[{"key":"CIT0001","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1080\/01969720118947","volume":"32","author":"Balkenius C.","year":"2001","journal-title":"Cybernetics and Systems"},{"key":"CIT0002","first-page":"215","volume-title":"Models of information processing in the basal ganglia","author":"Barto A. G.","year":"1995"},{"key":"CIT0003","doi-asserted-by":"crossref","first-page":"4311","DOI":"10.1523\/JNEUROSCI.20-11-04311.2000","volume":"20","author":"Baxter M. G.","year":"2000","journal-title":"Journal of Neuroscience"},{"key":"CIT0004","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/10.3.295"},{"key":"CIT0005","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1080\/01969720118145","volume":"32","author":"Bozinovski S.","year":"2001","journal-title":"Cybernetics and Systems"},{"key":"CIT0006","volume-title":"Reinforcement learning methods for continuous-time Markov decision problems","author":"Bradtke S. J.","year":"1995"},{"key":"CIT0007","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/10.3.220"},{"key":"CIT0008","volume-title":"The feeling of what happens: Body & emotion in the making of consciousness","author":"Damasio A.","year":"1999"},{"key":"CIT0009","volume-title":"Feudal reinforcement learning","author":"Dayan P.","year":"1993"},{"key":"CIT0010","volume-title":"Contemporary animal learning theory","author":"Dickinson A.","year":"1980"},{"key":"CIT0011","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"Dietterich T. G.","year":"2000","journal-title":"Journal of Artificial Intelligence Research"},{"key":"CIT0012","volume-title":"State abstraction in MAXQ hierarchical reinforcement learning","author":"Dietterich T. G.","year":"2000"},{"key":"CIT0013","first-page":"253","volume-title":"The amygdala: A functional analysis","author":"Everitt B. J.","year":"2000"},{"key":"CIT0014","doi-asserted-by":"publisher","DOI":"10.1016\/S0306-4522(00)00092-0"},{"key":"CIT0015","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1080\/019697201750257766","volume":"32","author":"Gadanho S. C.","year":"2001","journal-title":"Cybernetics and Systems"},{"key":"CIT0016","doi-asserted-by":"publisher","DOI":"10.1016\/S0006-8993(99)01291-3"},{"key":"CIT0017","doi-asserted-by":"crossref","first-page":"5256","DOI":"10.1523\/JNEUROSCI.16-16-05256.1996","volume":"16","author":"Hatfield T.","year":"1996","journal-title":"Journal of Neuroscience"},{"key":"CIT0018","unstructured":"Hengst , B. 2002 . Discovering hierarchy in reinforcement learning with HEXQ . Nineteenth International Conference on Machine Learning , Sydney , Australia , July , pp. 8 \u2013 12 ."},{"key":"CIT0019","first-page":"249","volume-title":"Models of information processing in the basal ganglia","author":"Houk J. C.","year":"1995"},{"key":"CIT0020","unstructured":"Kaelbling , L. P. 1993 . Hierarchical learning in stochastic domains . Proceedings of the Tenth International Conference on Machine Learning , Amherst , MA , USA , 27\u201329 June , pp. 167 \u2013 173 ."},{"key":"CIT0021","first-page":"377","volume":"388","author":"Killcross S.","year":"1997","journal-title":"Nature Neuroscience"},{"key":"CIT0022","doi-asserted-by":"publisher","DOI":"10.1016\/0959-4388(92)90011-9"},{"key":"CIT0023","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.23.1.155"},{"key":"CIT0024","first-page":"293","volume":"8","author":"Lin L.-J.","year":"1992","journal-title":"Machine Learning"},{"key":"CIT0025","unstructured":"Lin , L.J . 1993 . Scaling up reinforcement learning for robot control . Tenth International conference on Machine Learning , Amherst , MA , USA , 27\u201329 June , pp. 182 \u2013 189 ."},{"key":"CIT0026","doi-asserted-by":"crossref","first-page":"6011","DOI":"10.1523\/JNEUROSCI.17-15-06011.1997","volume":"17","author":"Malkova L.","year":"1997","journal-title":"Journal of Neuroscience"},{"key":"CIT0027","doi-asserted-by":"crossref","unstructured":"Menache , I. , S. Mannor , and N. Shimkin . 2002 . Q-Cut\u2014Dynamic discovery of sub-goals in reinforcement learning . 13th European Conference on Machine Learning , Helsinki , Finland . Berlin , Heidelberg : Springer-Verlag .","DOI":"10.1007\/3-540-36755-1_25"},{"key":"CIT0028","unstructured":"Minsky , M. L. 1954 . Theory of neural-analog reinforcement systems and its application to the brain-model problem. Ph. D. dissertation, Princeton University, Department of Mathematics ."},{"key":"CIT0029","doi-asserted-by":"publisher","DOI":"10.1038\/82959"},{"key":"CIT0030","doi-asserted-by":"crossref","first-page":"2701","DOI":"10.1523\/JNEUROSCI.20-07-02701.2000","volume":"20","author":"Par\u00e9 D.","year":"2000","journal-title":"Journal of Neuroscience"},{"key":"CIT0031","volume-title":"Reinforcement learning with hierarchical machines","author":"Parr R.","year":"1998"},{"key":"CIT0032","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1093\/oso\/9780198505013.003.0002","volume-title":"The amygdala: A functional analysis","author":"Pitkanen A.","year":"2000"},{"key":"CIT0033","doi-asserted-by":"publisher","DOI":"10.1016\/0896-6273(95)90070-5"},{"key":"CIT0034"},{"key":"CIT0035","volume-title":"The brain and emotion","author":"Rolls E. T.","year":"1999"},{"key":"CIT0036","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/10.3.284"},{"key":"CIT0037","first-page":"443","volume":"81","author":"Sadikot A. F.","year":"1990","journal-title":"Experimental Brain Research"},{"key":"CIT0038","doi-asserted-by":"publisher","DOI":"10.1038\/407"},{"key":"CIT0039","doi-asserted-by":"crossref","first-page":"1876","DOI":"10.1523\/JNEUROSCI.19-05-01876.1999","volume":"19","author":"Schoenbaum G.","year":"1999","journal-title":"Journal of Neuroscience"},{"key":"CIT0040","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1152\/jn.1998.80.1.1","volume":"80","author":"Schultz W.","year":"1998","journal-title":"Journal of Neurophysiology"},{"key":"CIT0041","doi-asserted-by":"publisher","DOI":"10.1126\/science.275.5306.1593"},{"key":"CIT0042","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/10.3.272"},{"key":"CIT0043","volume-title":"Balancing multiple sources of reward in reinforcement learning","author":"Shelton C. R.","year":"2001"},{"key":"CIT0044","doi-asserted-by":"publisher","DOI":"10.1037\/h0024127"},{"key":"CIT0045","first-page":"323","volume":"8","author":"Singh S. P.","year":"1992","journal-title":"Machine Learning"},{"key":"CIT0046","first-page":"9","volume":"3","author":"Sutton R. S.","year":"1988","journal-title":"Machine Learning"},{"key":"CIT0047","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.88.2.135"},{"key":"CIT0048","volume-title":"Improved switching among temporally abstract actions","author":"Sutton R. S.","year":"1998"},{"key":"CIT0049","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"CIT0050","first-page":"704","volume":"398","author":"Tremblay L.","year":"1999","journal-title":"Nature Neuroscience"},{"key":"CIT0051","doi-asserted-by":"crossref","first-page":"1864","DOI":"10.1152\/jn.2000.83.4.1864","volume":"83","author":"Tremblay L.","year":"2000","journal-title":"Journal of Neurophysiology"},{"key":"CIT0052","unstructured":"Valesquez , J. D. 1998 . When robots weep: Emotional memories and decision-making .AAAI\u203298. Madison , WI : MIT Press ."}],"container-title":["Cybernetics and Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/01969720590887270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T10:22:46Z","timestamp":1707992566000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.tandfonline.com\/doi\/abs\/10.1080\/01969720590887270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004,12,9]]},"references-count":52,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2004,12,9]]}},"alternative-id":["10.1080\/01969720590887270"],"URL":"https:\/\/doi.org\/10.1080\/01969720590887270","relation":{},"ISSN":["0196-9722","1087-6553"],"issn-type":[{"value":"0196-9722","type":"print"},{"value":"1087-6553","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004,12,9]]}}}