{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:22:39Z","timestamp":1772119359190,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2007,10,3]],"date-time":"2007-10-03T00:00:00Z","timestamp":1191369600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biol Cybern"],"published-print":{"date-parts":[[2007,12]]},"DOI":"10.1007\/s00422-007-0176-y","type":"journal-article","created":{"date-parts":[[2007,10,2]],"date-time":"2007-10-02T05:10:08Z","timestamp":1191301808000},"page":"363-378","source":"Crossref","is-referenced-by-count":9,"title":["Chained learning architectures in a simple closed-loop behavioural context"],"prefix":"10.1007","volume":"97","author":[{"given":"Tomas","family":"Kulvicius","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernd","family":"Porr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florentin","family":"W\u00f6rg\u00f6tter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2007,10,3]]},"reference":[{"key":"176_CR1","unstructured":"Agostini E, Celaya A (2004) Trajectory tracking control of a rotational joint using feature-based categorization learning. In: Proceedings of the IEEE\/RSJ international conference on intelligent robots and systems, IEEE, Sendai, Japan"},{"key":"176_CR2","doi-asserted-by":"crossref","DOI":"10.5962\/bhl.title.5851","volume-title":"An introduction to cybernetics","author":"WR Ashby","year":"1956","unstructured":"Ashby WR (1956). An introduction to cybernetics. Methnen, London"},{"issue":"1","key":"176_CR3","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/35036191","volume":"1","author":"CH Bailey","year":"2000","unstructured":"Bailey CH, Giustetto M, Huang YY, Hawkins RD and Kandel ER (2000). Is heterosynaptic modulation essential for stabilizing Hebbian plasticity and memory. Nat Rev Neurosci 1(1): 11\u201320","journal-title":"Nat Rev Neurosci"},{"key":"176_CR4","first-page":"809","volume-title":"Handbook of brain theory and neural networks.","author":"A Barto","year":"1995","unstructured":"Barto A (1995). Reinforcement learning in motor control. In: Arbib, M (eds) Handbook of brain theory and neural networks., pp 809\u2013812. MIT Press, Cambridge"},{"key":"176_CR5","first-page":"835","volume":"13","author":"AG Barto","year":"1983","unstructured":"Barto AG, Sutton RS and Anderson CW (1983). Neuronlike elements that can solve difficult learning control problems. IEEE Trans Syst Man Cybern 13: 835\u2013846","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"176_CR6","volume-title":"Vehicles: experiments in synthetic psychology","author":"V Braitenberg","year":"1984","unstructured":"Braitenberg V (1984). Vehicles: experiments in synthetic psychology. MIT Press, Cambridge"},{"issue":"5","key":"176_CR7","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1101\/lm.35200","volume":"7","author":"JC Gewirtz","year":"2000","unstructured":"Gewirtz JC and Davis M (2000). Using pavlovian higher-order conditioning paradigms to investigate the neural substrates of emotional learning and memory. Learn Mem 7(5): 257\u2013266","journal-title":"Learn Mem"},{"issue":"7","key":"176_CR8","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1016\/S0893-6080(09)80004-X","volume":"6","author":"H Gomi","year":"1993","unstructured":"Gomi H and Kawato M (1993). Neural network control for a closed-loop system using feedback-error-learning. Neural Netw 6(7): 933\u2013946","journal-title":"Neural Netw"},{"issue":"6968","key":"176_CR9","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1038\/nature02194","volume":"426","author":"Y Humeau","year":"2003","unstructured":"Humeau Y, Shaban H, Bissiere S and Luthi A (2003). Presynaptic induction of heterosynaptic associative plasticity in the mammalian brain. Nature 426(6968): 841\u2013845","journal-title":"Nature"},{"key":"176_CR10","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/S0028-3908(02)00334-9","volume":"44","author":"H Ikeda","year":"2003","unstructured":"Ikeda H, Akiyama G, Fujii Y, Minowa R, Koshikawa N and Cools A (2003). Role of AMPA and NMDA receptors in the nucleus accumbens shell in turning behaviour of rats: interaction with dopamine and receptors. Neuropharmacology 44: 81\u201387","journal-title":"Neuropharmacology"},{"key":"176_CR11","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.lmot.2005.12.001","volume":"37","author":"E Jara","year":"2006","unstructured":"Jara E, Vila J and Maldonado A (2006). Second-order conditioning of human causal learning. Learn Motiv 37: 230\u2013246","journal-title":"Learn Motiv"},{"issue":"6","key":"176_CR12","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1016\/S0301-0082(03)00085-6","volume":"69","author":"T Jay","year":"2003","unstructured":"Jay T (2003). Dopamine: a potential substrate for synaptic plasticity and memory mechanisms. Prog Neurobiol 69(6): 375\u2013390","journal-title":"Prog Neurobiol"},{"key":"176_CR13","doi-asserted-by":"crossref","unstructured":"Jodogne S, Scalzo F, Piater JH (2005) Task-driven learning of spatial combinations of visual features. In: Proceedings of the IEEE workshop on learning in computer vision and pattern recognition, IEEE, San Diego (CA, USA)","DOI":"10.1109\/CVPR.2005.539"},{"key":"176_CR14","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1111\/j.1749-6632.1999.tb09262.x","volume":"877","author":"AE Kelley","year":"1999","unstructured":"Kelley AE (1999). Functional specificity of ventral striatal compartments in appetitive behaviors. Ann NY Acad Sci 877: 71\u201390","journal-title":"Ann NY Acad Sci"},{"issue":"2","key":"176_CR15","doi-asserted-by":"crossref","first-page":"85","DOI":"10.3758\/BF03333113","volume":"16","author":"AH Klopf","year":"1988","unstructured":"Klopf AH (1988). A neuronal model of classical conditioning. Psychobiology 16(2): 85\u2013123","journal-title":"Psychobiology"},{"key":"176_CR16","doi-asserted-by":"crossref","unstructured":"Kolodziejski C, W\u00f6rg\u00f6tter F, Porr B (2007) Mathematical properties of neuronal TD-rules and differential Hebbian learning: A comparison. Biol Cybern (submitted)","DOI":"10.1007\/s00422-007-0209-6"},{"key":"176_CR17","doi-asserted-by":"crossref","unstructured":"Kosco B (1986) Differential Hebbian learning. In: Denker JS (ed) Neural networks for computing: AIP Conference Proceedings, vol. 151. American Institute of Physics, New York","DOI":"10.1063\/1.36225"},{"key":"176_CR18","doi-asserted-by":"crossref","unstructured":"Land MF (2001) Does steering a car involve perception of the velocity flow field. In: Zeil JMZJ (ed) Motion vision\u2014computational, neural, and ecological constraints, pp. 227\u2013235","DOI":"10.1007\/978-3-642-56550-2_13"},{"key":"176_CR19","unstructured":"Manoonpong P, Geng T, Kulvicius T, Porr B, W\u00f6rg\u00f6tter F (2007) Adaptive, fast walking in a biped robot under neuronal control and learning. PLoS Comput Biol 3(7):e134 doi: 10.1371\/journal.pcbi.0030,134"},{"key":"176_CR20","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5237.001.0001","volume-title":"Parallel distributed processing, vol 1","author":"JL McClelland","year":"1987","unstructured":"McClelland JL, Rumelhart DE and Hinton GE (1987). Parallel distributed processing, vol 1. MIT Press, Cambridge"},{"key":"176_CR21","volume-title":"Feedback mechanisms in animal behaviour","author":"DJ McFarland","year":"1971","unstructured":"McFarland DJ (1971). Feedback mechanisms in animal behaviour. Academic, London"},{"issue":"9","key":"176_CR22","doi-asserted-by":"crossref","first-page":"3387","DOI":"10.1073\/pnas.0511281103","volume":"103","author":"JL McKinstry","year":"2006","unstructured":"McKinstry JL, Edelman GM and Krichmar JL (2006). A cerebellar model for predictive motor control tested in a brain-based device. Proc Natl Acad Sci USA 103(9): 3387\u20133392","journal-title":"Proc Natl Acad Sci USA"},{"key":"176_CR23","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1038\/377725a0","volume":"377","author":"PR Montague","year":"1995","unstructured":"Montague PR, Dayan P, Person C and Sejnowski TJ (1995). Bee foraging in uncertain environments using predictive Hebbian learning. Nature 377: 725\u2013728","journal-title":"Nature"},{"key":"176_CR24","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1016\/j.neunet.2004.05.003","volume":"17","author":"J Nakanishi","year":"2004","unstructured":"Nakanishi J and Schaal S (2004). Feedback error learning and nonlinear adaptive control. Neural Netw 17: 1453\u20131465","journal-title":"Neural Netw"},{"issue":"1","key":"176_CR25","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1177\/1059-712302-010001-01","volume":"10","author":"Y Niv","year":"2002","unstructured":"Niv Y, Joel D, Meilijson I and Ruppin E (2002). Evolution of reinforcement learning in uncertain environments: a simple explanation for complex foraging behaviors. Adapt Behav 10(1): 5\u201324","journal-title":"Adapt Behav"},{"key":"176_CR26","first-page":"161","volume-title":"Early visual learning.","author":"D Pomerleau","year":"1996","unstructured":"Pomerleau D (1996). Neural network vision for robot driving. In: Nayar, S and Poggio, T (eds) Early visual learning., pp 161\u2013181. Oxford University Press, New York"},{"key":"176_CR27","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1162\/08997660360581921","volume":"15","author":"B Porr","year":"2003","unstructured":"Porr B and W\u00f6rg\u00f6tter F (2003a). Isotropic sequence order learning. Neural Comp 15: 831\u2013864","journal-title":"Neural Comp"},{"issue":"1811","key":"176_CR28","doi-asserted-by":"crossref","first-page":"2225","DOI":"10.1098\/rsta.2003.1273","volume":"361","author":"B Porr","year":"2003","unstructured":"Porr B and W\u00f6rg\u00f6tter F (2003b). Isotropic sequence order learning in a closed loop behavioural system. R Soc Phil Trans Math Phys Eng Sci 361(1811): 2225\u20132244","journal-title":"R Soc Phil Trans Math Phys Eng Sci"},{"issue":"6","key":"176_CR29","doi-asserted-by":"crossref","first-page":"1380","DOI":"10.1162\/neco.2006.18.6.1380","volume":"18","author":"B Porr","year":"2006","unstructured":"Porr B and W\u00f6rg\u00f6tter F (2006). Strongly improved stability and faster convergence of temporal sequence learning by utilising input correlations only. Neural Comp 18(6): 1380\u20131412","journal-title":"Neural Comp"},{"key":"176_CR30","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1162\/08997660360581930","volume":"15","author":"B Porr","year":"2003","unstructured":"Porr B, Ferber C and Worgotter F (2003). Iso-learning approximates a solution to the inverse controller problem in an unsupervised behavioural paradigm. Neural Comp 15: 865\u2013884","journal-title":"Neural Comp"},{"key":"176_CR31","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1162\/08997660360581930","volume":"15","author":"B Porr","year":"2003","unstructured":"Porr B, W\u00f6rg\u00f6tter F and Ferber C (2003). ISO-learning approximates a solution to the inverse-controller problem in an unsupervised behavioral paradigm. Neural Comp 15: 865\u2013884","journal-title":"Neural Comp"},{"key":"176_CR32","volume-title":"Pavlovian second-order conditioning: studies in associative learning","author":"RA Rescorla","year":"1980","unstructured":"Rescorla RA (1980). Pavlovian second-order conditioning: studies in associative learning. Erlbaum, Hillsdale"},{"issue":"4","key":"176_CR33","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1162\/089976601300014376","volume":"13","author":"W Schultz","year":"2001","unstructured":"Schultz W and Suri RE (2001). Temporal difference model reproduces anticipatory neural activity. Neural Comp 13(4): 841\u2013862","journal-title":"Neural Comp"},{"key":"176_CR34","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1007\/s002210050467","volume":"121","author":"RE Suri","year":"1998","unstructured":"Suri RE and Schultz W (1998). Learning of sequential movements by neural network model with dopamine-like reinforcement signal. Exp Brain Res 121: 350\u2013354","journal-title":"Exp Brain Res"},{"key":"176_CR35","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1037\/0033-295X.88.2.135","volume":"88","author":"R Sutton","year":"1981","unstructured":"Sutton R and Barto A (1981). Towards a modern theory of adaptive networks: expectation and prediction. Psychol Rev 88: 135\u2013170","journal-title":"Psychol Rev"},{"key":"176_CR36","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton RS (1988). Learning to predict by the methods of temporal differences. Mach Learn 3: 9\u201344","journal-title":"Mach Learn"},{"key":"176_CR37","volume-title":"Learning and computational neuroscience: foundation of adaptive networks.","author":"RS Sutton","year":"1990","unstructured":"Sutton RS and Barto AG (1990). Time-derivative models of Pavlovian reinforcement. In: Gabriel, M and Moore, J (eds) Learning and computational neuroscience: foundation of adaptive networks., pp. MIT Press, Cambridge"},{"key":"176_CR38","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS and Barto AG (1998). Reinforcement learning: an introduction. MIT Press, Cambridge"},{"issue":"3","key":"176_CR39","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1113\/jphysiol.2002.033803","volume":"546","author":"M Tsukamoto","year":"2003","unstructured":"Tsukamoto M, Yasui T, Yamada MK, Nishiyama N, Matsuki N and Ikegaya Y (2003). Mossy fibre synaptic NMDA receptors trigger non-Hebbian long-term potentiation at entorhino-CA3 synapses in the rat. J Physiol 546(3): 665\u2013675","journal-title":"J Physiol"},{"key":"176_CR40","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1207\/s15516709cog2704_1","volume":"27","author":"P Verschure","year":"2003","unstructured":"Verschure P and Althaus P (2003). A real-world rational agent: unifying old and new AI. Cogn Sci 27: 561\u2013590","journal-title":"Cogn Sci"},{"key":"176_CR41","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1088\/0954-898X_2_2_004","volume":"2","author":"P Verschure","year":"1991","unstructured":"Verschure P and Coolen A (1991). Adaptive fields: distributed representations of classically conditioned associations. Network 2: 189\u2013206","journal-title":"Network"},{"key":"176_CR42","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1038\/scientificamerican0550-42","volume":"182","author":"WG Walter","year":"1950","unstructured":"Walter WG (1950). An imitation of life. Sci Am 182: 42\u201345","journal-title":"Sci Am"},{"key":"176_CR43","unstructured":"Watkins CJCH (1989) Learning from delayed rewards. PhD Thesis, University of Cambridge, Cambridge, England"},{"key":"176_CR44","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins CJCH and Dayan P (1992). Technical note: Q-Learning. Mach Learn 8: 279\u2013292","journal-title":"Mach Learn"},{"key":"176_CR45","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1038\/417359a","volume":"417","author":"B Webb","year":"2002","unstructured":"Webb B (2002). Robots in invertebrate neuroscience. Nature 417: 359\u2013363","journal-title":"Nature"},{"key":"176_CR46","doi-asserted-by":"crossref","DOI":"10.1037\/13140-000","volume-title":"Cybernetics\u2014or control and communication in the animal and the machine, 2nd edn","author":"N Wiener","year":"1961","unstructured":"Wiener N (1961). Cybernetics\u2014or control and communication in the animal and the machine, 2nd edn. The MIT Press, Cambridge"},{"key":"176_CR47","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/S0019-9958(77)90354-0","volume":"34","author":"IH Witten","year":"1977","unstructured":"Witten IH (1977). An adaptive optimal controller for discrete-time Markov environments. Inf Control 34: 86\u2013295","journal-title":"Inf Control"},{"key":"176_CR48","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1162\/0899766053011555","volume":"17","author":"F W\u00f6rg\u00f6tter","year":"2005","unstructured":"W\u00f6rg\u00f6tter F and Porr B (2005). Temporal sequence learning for prediction and control - a review of different models and their relation to biological mechanisms. Neural Comp 17: 245\u2013319","journal-title":"Neural Comp"},{"issue":"Suppl 3","key":"176_CR49","first-page":"50","volume":"271","author":"R Wyss","year":"2004","unstructured":"Wyss R, K\u00f6nig P and Verschure PFMJ (2004). Involving the motor system in decision making. Proc Biol Sci 271(Suppl 3): 50\u201352","journal-title":"Proc Biol Sci"}],"container-title":["Biological Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-007-0176-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00422-007-0176-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-007-0176-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,14]],"date-time":"2023-05-14T05:05:50Z","timestamp":1684040750000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00422-007-0176-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,10,3]]},"references-count":49,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2007,12]]}},"alternative-id":["176"],"URL":"https:\/\/doi.org\/10.1007\/s00422-007-0176-y","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.1091397.545839","asserted-by":"object"}]},"ISSN":["0340-1200","1432-0770"],"issn-type":[{"value":"0340-1200","type":"print"},{"value":"1432-0770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2007,10,3]]}}}