{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T23:47:26Z","timestamp":1771544846429,"version":"3.50.1"},"reference-count":87,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2014,5,7]],"date-time":"2014-05-07T00:00:00Z","timestamp":1399420800000},"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":["J Comput Neurosci"],"published-print":{"date-parts":[[2014,10]]},"DOI":"10.1007\/s10827-014-0500-1","type":"journal-article","created":{"date-parts":[[2014,5,6]],"date-time":"2014-05-06T02:03:39Z","timestamp":1399341819000},"page":"259-280","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Learning and control of exploration primitives"],"prefix":"10.1007","volume":"37","author":[{"given":"Goren","family":"Gordon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehud","family":"Fonio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ehud","family":"Ahissar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,5,7]]},"reference":[{"issue":"3","key":"500_CR1","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1162\/089976698300017683","volume":"10","author":"E Ahissar","year":"1998","unstructured":"Ahissar, E. (1998). Temporal-code to rate-code conversion by neuronal phase-locked loops. Neural Computer, 10(3), 597\u2013650.","journal-title":"Neural Computer"},{"issue":"1","key":"500_CR2","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1093\/cercor\/13.1.53","volume":"13","author":"E Ahissar","year":"2003","unstructured":"Ahissar, E., & Kleinfeld, D. (2003). Closed-loop neuronal computations: focus on vibrissa somatosensation in rat. Cereb Cortex, 13(1), 53\u201362.","journal-title":"Cereb Cortex"},{"key":"500_CR86","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1007\/s00422-008-0214-4","volume":"98","author":"E Ahissar","year":"2008","unstructured":"Ahissar, E., & Knutsen, P.M. (2008). Object localization with whiskers. Biol Cybern, 98, 449\u2013458.","journal-title":"Biol Cybern"},{"key":"500_CR3","unstructured":"Ahissar, E., & Oram, T. (2013). Thalamic relay or cortico-thalamic processing? Old question, New Answers. Cerebral Cortex: bht296."},{"key":"500_CR4","doi-asserted-by":"crossref","unstructured":"Baldassarre, G. (2011). What are intrinsic motivations? a biological perspective. IEEE International conference developmental learning (ICDL), (Vol. 2, pp. 1\u20138).","DOI":"10.1109\/DEVLRN.2011.6037367"},{"key":"500_CR87","doi-asserted-by":"crossref","first-page":"3298","DOI":"10.1152\/jn.00198.2004","volume":"92","author":"A Bahar","year":"2004","unstructured":"Bahar, A., Dudai, Y., Ahissar, E. (2004). Neural signature of taste familiarity in the gustatory cortex of the freely behaving rat. J Neurophysiol, 92, 3298\u20133308.","journal-title":"J Neurophysiol"},{"issue":"4","key":"500_CR5","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2044-8295.1958.tb00667.x","volume":"49","author":"SA Barnett","year":"1958","unstructured":"Barnett, S.A. (1958). Exploratory behaviour. Br J Psychol, 49(4), 289\u2013310.","journal-title":"Br J Psychol"},{"issue":"1\u20132","key":"500_CR6","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1022140919877","volume":"13","author":"AG Barto","year":"2003","unstructured":"Barto, A.G., & Mahadevan, S. (2003). Recent advances in hierarchical reinforcement learning. Discrete Event Dynamical System, 13(1\u20132), 41\u201377.","journal-title":"Discrete Event Dynamical System"},{"key":"500_CR7","unstructured":"Barto, A.G., Singh, S., Chentanez, N. (2004). Intrinsically motivated learning of hierarchical collections of skills. In International conference on developmental learning (ICDL)."},{"issue":"4","key":"500_CR8","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1016\/j.neuron.2012.10.038","volume":"76","author":"AM Bastos","year":"2012","unstructured":"Bastos, A.M., Usrey, W.M., Adams, R.A., Mangun, G.R., Fries, P., Friston, K.J. (2012). Canonical microcircuits for predictive coding. Neuron, 76(4), 695\u2013711.","journal-title":"Neuron"},{"key":"500_CR9","doi-asserted-by":"crossref","unstructured":"Behera, L., Gopal, M., Chaudhury, S. (1995). Self-organizing neural networks for learning inverse dynamics of robot manipulator. In IEEE\/IAS International conference on industrial automation and control (I A & C\u201995) (pp. 457\u2013460).","DOI":"10.1109\/IACC.1995.465797"},{"issue":"1","key":"500_CR10","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1152\/jn.00600.2002","volume":"89","author":"RW Berg","year":"2003","unstructured":"Berg, R.W., & Kleinfeld, D. (2003). Rhythmic whisking by rat: Retraction as well as protraction of the vibrissae is under active muscular control. Journal of Neurophysiol, 89(1), 104\u2013117.","journal-title":"Journal of Neurophysiol"},{"key":"500_CR11","unstructured":"Bhatnagar, S., Sutton, R., Ghavamzadeh, M., Lee, M. (2007). Incremental natural actor-critic algorithms. In Twenty-first annual conference on advances in neural information processing systems (pp. 105\u2013112)."},{"issue":"1","key":"500_CR12","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1038\/npp.2010.121","volume":"36","author":"R Cools","year":"2011","unstructured":"Cools, R., Nakamura, K., Daw, N.D. (2011). Serotonin and dopamine: Unifying affective, activational, and decision functions. Neuropsychopharmacology, 36(1), 98\u2013113.","journal-title":"Neuropsychopharmacology"},{"key":"500_CR13","doi-asserted-by":"crossref","unstructured":"Der, R., & Martius, G. (2012). The playful machine. Cognitive System Monographia. Springer.","DOI":"10.1007\/978-3-642-20253-7"},{"issue":"2","key":"500_CR14","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.conb.2011.11.013","volume":"22","author":"M Deschenes","year":"2012","unstructured":"Deschenes, M., Moore, J.W., Kleinfeld, D. (2012). Sniffing and whisking in rodents. Current Opinion in Neurobiology, 22(2), 243\u2013250.","journal-title":"Current Opinion in Neurobiology"},{"issue":"9","key":"500_CR15","doi-asserted-by":"crossref","first-page":"e44, 272","DOI":"10.1371\/journal.pone.0044272","volume":"7","author":"D Deutsch","year":"2012","unstructured":"Deutsch, D., Pietr, M., Knutsen, P.M., Ahissar, E., Schneidman, E. (2012). Fast feedback in active sensing: touch-induced changes to whisker-object interaction. PLoS One, 7(9), e44, 272.","journal-title":"PLoS One"},{"issue":"8","key":"500_CR16","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1038\/nrn2411","volume":"9","author":"ME Diamond","year":"2008","unstructured":"Diamond, M.E., von Heimendahl, M., Knutsen, P.M., Kleinfeld, D., Ahissar, E. (2008). Where and what in the whisker sensorimotor system. Natural Reviews Neuroscience, 9(8), 601\u2013612.","journal-title":"Natural Reviews Neuroscience"},{"key":"500_CR17","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/s11031-006-9028-7","volume":"30","author":"AJ Elliot","year":"2006","unstructured":"Elliot, A.J. (2006). The hierarchical model of approach-avoidance motivation. Motivaton and Emotion, 30, 111\u2013116.","journal-title":"Motivaton and Emotion"},{"issue":"26","key":"500_CR18","doi-asserted-by":"crossref","first-page":"15330","DOI":"10.1073\/pnas.261273898","volume":"98","author":"EE Fanselow","year":"2001","unstructured":"Fanselow, E.E., Sameshima, K., Baccala, L.A., Nicolelis, M.A. (2001). Thalamic bursting in rats during different awake behavioral states. Proceedings of the National Academy of Sciences of the United States of America, 98(26), 15330\u20135.","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"issue":"0","key":"500_CR19","first-page":"3","volume":"103","author":"D Feldmeyer","year":"2012","unstructured":"Feldmeyer, D., Brecht, M., Helmchen, F., Petersen, C.CH., Poulet, J.FA., Staiger, J.F., Luhmann, H.J., Schwarz, C. (2012). Barrel cortex function. Progress in Neurobiology, 103(0), 3\u201327.","journal-title":"Progress in Neurobiology"},{"issue":"1\u20132","key":"500_CR20","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/S0166-4328(01)00292-3","volume":"125","author":"SE File","year":"2001","unstructured":"File, S.E. (2001). Factors controlling measures of anxiety and responses to novelty in the mouse. Behavioural Brain Research, 125(1\u20132), 151\u20137.","journal-title":"Behavioural Brain Research"},{"issue":"6","key":"500_CR21","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1007\/s00422-007-0145-5","volume":"96","author":"T Flash","year":"2007","unstructured":"Flash, T., & Handzel, A.A. (2007). Affine differential geometry analysis of human arm movements. Biological Cybernetics, 96(6), 577\u2013601.","journal-title":"Biological Cybernetics"},{"issue":"6","key":"500_CR22","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1016\/j.conb.2005.10.011","volume":"15","author":"T Flash","year":"2005","unstructured":"Flash, T., & Hochner, B. (2005). Motor primitives in vertebrates and invertebrates. Current Opinion in Neurobiology, 15(6), 660\u20136.","journal-title":"Current Opinion in Neurobiology"},{"issue":"50","key":"500_CR23","doi-asserted-by":"crossref","first-page":"21, 335","DOI":"10.1073\/pnas.0812513106","volume":"106","author":"E Fonio","year":"2009","unstructured":"Fonio, E., Benjamini, Y., Golani, I. (2009). Freedom of movement and the stability of its unfolding in free exploration of mice. Proceedings of the National Academy of Sciences of the United States of America, 106(50), 21, 335\u201340.","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"500_CR24","unstructured":"Fox, C.J., Girdhar, N., Gurney, K.N. (2008). A causal bayesian network view of reinforcement learning. In Twenty-first international florida artificial intelligence research society conference (pp. 109\u2013110). AAAI Press."},{"issue":"2","key":"500_CR25","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/nrn2787","volume":"11","author":"K Friston","year":"2010","unstructured":"Friston, K. (2010). The free-energy principle: a unified brain theory?. Nature Reviews Neuroscience, 11(2), 127\u201338.","journal-title":"Nature Reviews Neuroscience"},{"issue":"6","key":"500_CR26","first-page":"507","volume":"18","author":"L Frommberger","year":"2010","unstructured":"Frommberger, L., & Wolter, D. (2010). Structural knowledge transfer by spatial abstraction for reinforcement learning agents. Adaptive Behavior - Animals, Animats, Software Agents, Robot, Adaptive System, 18(6), 507\u2013525.","journal-title":"Adaptive Behavior - Animals, Animats, Software Agents, Robot, Adaptive System"},{"issue":"14","key":"500_CR27","doi-asserted-by":"crossref","first-page":"5374","DOI":"10.1523\/JNEUROSCI.21-14-05374.2001","volume":"21","author":"P Gao","year":"2001","unstructured":"Gao, P., Bermejo, R., Zeigler, H.P. (2001). Whisker deafferentation and rodent whisking patterns: Behavioral evidence for a central pattern generator. Journal of Neuroscience, 21(14), 5374\u20135380.","journal-title":"Journal of Neuroscience"},{"key":"500_CR28","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neunet.2012.02.024","volume":"32","author":"G Gordon","year":"2012","unstructured":"Gordon, G., & Ahissar, E. (2012). Hierarchical curiosity loops and active sensing. Neural Network, 32, 119\u201329.","journal-title":"Neural Network"},{"key":"500_CR29","doi-asserted-by":"crossref","first-page":"20","DOI":"10.3389\/fnsys.2011.00020","volume":"5","author":"G Gordon","year":"2011","unstructured":"Gordon, G., Kaplan, D.M., Lankow, B., Little, D.Y., Sherwin, J., Suter, B.A., Thaler, L. (2011). Toward an integrated approach to perception and action: conference report and future directions. Frontiers System Neuroscience, 5, 20.","journal-title":"Frontiers System Neuroscience"},{"issue":"2","key":"500_CR30","doi-asserted-by":"crossref","first-page":"862","DOI":"10.1152\/jn.90783.2008","volume":"101","author":"RA Grant","year":"2009","unstructured":"Grant, R.A., Mitchinson, B., Fox, C.W., Prescott, T.J. (2009). Active touch sensing in the rat: anticipatory and regulatory control of whisker movements during surface exploration. Journal of Neurophysiology, 101(2), 862\u201374.","journal-title":"Journal of Neurophysiology"},{"issue":"2","key":"500_CR31","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1002\/dev.20591","volume":"54","author":"RA Grant","year":"2012","unstructured":"Grant, R.A., Mitchinson, B., Prescott, T.J. (2012). The development of whisker control in rats in relation to locomotion. Developmental Psychobiology, 54(2), 151\u2013168.","journal-title":"Developmental Psychobiology"},{"issue":"1428","key":"500_CR32","doi-asserted-by":"crossref","first-page":"1809","DOI":"10.1098\/rstb.2002.1171","volume":"357","author":"RW Guillery","year":"2012","unstructured":"Guillery, R.W., & Sherman, S.M. (2012). The thalamus as a monitor of motor outputs. Philosophical Transactions R Society London B Biological Sciences, 357(1428), 1809\u20131821.","journal-title":"Philosophical Transactions R Society London B Biological Sciences"},{"issue":"5","key":"500_CR33","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1152\/jn.01016.2009","volume":"103","author":"O Harish","year":"2010","unstructured":"Harish, O., & Golomb, D. (2010). Control of the firing patterns of vibrissa motoneurons by modulatory and phasic synaptic inputs: a modeling study. Journal of Neurophysiology, 103(5), 2684\u201399.","journal-title":"Journal of Neurophysiology"},{"issue":"4","key":"500_CR34","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1037\/h0058114","volume":"43","author":"HF Harlow","year":"1950","unstructured":"Harlow, H.F. (1950). Learning and satiation of response in intrinsically motivated complex puzzle performance by monkeys. Journal of Comparative & Physiological Psychology, 43(4), 289\u201394.","journal-title":"Journal of Comparative & Physiological Psychology"},{"issue":"13","key":"500_CR35","first-page":"3438","volume":"28","author":"DN Hill","year":"2008","unstructured":"Hill, D.N., Bermejo, R., Zeigler, H.P., Kleinfeld, D. (2008). Biomechanics of the vibrissa motor plant in rat: Rhythmic whisking consists of triphasic neuromuscular activity. Journal of Neurophysiology, 28(13), 3438\u20133455.","journal-title":"Journal of Neurophysiology"},{"issue":"3","key":"500_CR36","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.neubiorev.2006.11.004","volume":"31","author":"RN Hughes","year":"2007","unstructured":"Hughes, R.N. (2007). Neotic preferences in laboratory rodents: issues, assessment and substrates. Neuroscience and Biobehavioral, 31(3), 441\u201364.","journal-title":"Neuroscience and Biobehavioral"},{"key":"500_CR37","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W. (1996). Reinforcement learning: a survey. Journal of Artificial Intelligence Research, 4, 237\u2013285.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"500_CR38","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1016\/S0959-4388(99)00028-8","volume":"9","author":"MM Kawato","year":"1999","unstructured":"Kawato, M.M. (1999). Internal models for motor control and trajectory planning. Current Opinion in Neurobiology, 9, 718\u2013727.","journal-title":"Current Opinion in Neurobiology"},{"issue":"4","key":"500_CR39","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1016\/j.conb.2006.06.009","volume":"16","author":"D Kleinfeld","year":"2006","unstructured":"Kleinfeld, D., Ahissar, E., Diamond, M.E. (2006). Active sensation: insights from the rodent vibrissa sensorimotor system. Current Opinion in Neurobiology, 16(4), 435\u201344.","journal-title":"Current Opinion in Neurobiology"},{"issue":"1","key":"500_CR40","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.neuron.2008.05.013","volume":"59","author":"PM Knutsen","year":"2008","unstructured":"Knutsen, P.M., Biess, A., Ahissar, E. (2008). Vibrissal kinematics in 3d: Tight coupling of azimuth, elevation, and torsion across different whisking modes. Neuron, 59(1), 35\u201342.","journal-title":"Neuron"},{"key":"500_CR41","unstructured":"Konidaris, G., & Barto, A. (2007). Building portable options: skill transfer in reinforcement learning. In Proceedings of the 20th international joint conference on artifical intelligence (pp. 895\u2013900). Hyderabad: Morgan Kaufmann."},{"issue":"(6","key":"500_CR42","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/j.conb.2008.11.003","volume":"18","author":"H Lalazar","year":"2008","unstructured":"Lalazar, H., & Vaadia, E. (2008). Neural basis of sensorimotor learning: modifying internal models. Current Opinion in Neurobiology, 18((6)), 573\u2013581.","journal-title":"Current Opinion in Neurobiology"},{"issue":"1","key":"500_CR43","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.neuron.2006.10.036","volume":"53","author":"SC Leiser","year":"2007","unstructured":"Leiser, S.C., & Moxon, K.A. (2007). Responses of trigeminal ganglion neurons during natural whisking behaviors in the awake rat. Neuron, 53(1), 117\u201333.","journal-title":"Neuron"},{"key":"500_CR44","doi-asserted-by":"crossref","unstructured":"Little, D.Y., & Sommer, F.T. (2013). Learning and exploration in action-perception loops. Frontiers in Neural Circuits (in press).","DOI":"10.3389\/fncir.2013.00037"},{"issue":"6008","key":"500_CR45","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1126\/science.1195797","volume":"330","author":"F Matyas","year":"2010","unstructured":"Matyas, F., Sreenivasan, V., Marbach, F., Wacongne, C., Barsy, B., Mateo, C., Aronoff, R., Petersen, C.C. (2010). Motor control by sensory cortex. Science, 330(6008), 1240\u20133.","journal-title":"Science"},{"issue":"1","key":"500_CR46","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/0376-6357(86)90069-0","volume":"12","author":"R Misslin","year":"1986","unstructured":"Misslin, R., & Cigrang, M. (1986). Does neophobia necessarily imply fear or anxiety?. Behavior Processes, 12(1), 45\u201350.","journal-title":"Behavior Processes"},{"issue":"1613","key":"500_CR47","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1098\/rspb.2006.0347","volume":"274","author":"B Mitchinson","year":"2007","unstructured":"Mitchinson, B., Martin, C.J., Grant, R.A., Prescott, T.J. (2007). Feedback control in active sensing: rat exploratory whisking is modulated by environmental contact. Proceedings of the Biological Sciences, 274(1613), 1035\u201341.","journal-title":"Proceedings of the Biological Sciences"},{"issue":"7","key":"500_CR48","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1038\/nn1712","volume":"9","author":"M Miyazaki","year":"2006","unstructured":"Miyazaki, M., Yamamoto, S., Uchida, S., Kitazawa, S. (2006). Bayesian calibration of simultaneity in tactile temporal order judgment. Nature Neuroscience, 9(7), 875\u20137.","journal-title":"Nature Neuroscience"},{"key":"500_CR49","unstructured":"Moldovan, T.M., & Abbeel, P. (2012). Safe exploration in markov decision processes. In ICML 2012."},{"key":"500_CR50","unstructured":"Ngo, H., Luciw, M., Foerster, A., Schmidhuber, J. (2012). Learning skills from play: Artificial curiosity on a katana robot arm. In IJCNN 2012."},{"issue":"5215","key":"500_CR51","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.1126\/science.7761855","volume":"268","author":"MA Nicolelis","year":"1995","unstructured":"Nicolelis, M.A., Baccala, L.A., Lin, R.C., Chapin, J.K. (1995). Sensorimotor encoding by synchronous neural ensemble activity at multiple levels of the somatosensory system. Science, 268(5215), 1353\u20138.","journal-title":"Science"},{"issue":"3","key":"500_CR52","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1007\/s00213-006-0502-4","volume":"191","author":"Y Niv","year":"2007","unstructured":"Niv, Y., Daw, N.D., Joel, D., Dayan, P. (2007). Tonic dopamine: opportunity costs and the control of response vigor. Psychopharmacol (Berl), 191(3), 507\u2013520.","journal-title":"Psychopharmacol (Berl)"},{"issue":"2","key":"500_CR53","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1109\/TEVC.2006.890271","volume":"11","author":"PY Oudeyer","year":"2007","unstructured":"Oudeyer, P.Y., Kaplan, F., Hafner, V.V. (2007). Intrinsic motivation systems for autonomous mental development. IEEE Transactions on Evolutionary Computations, 11(2), 265\u2013286.","journal-title":"IEEE Transactions on Evolutionary Computations"},{"key":"500_CR54","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.mechatronics.2005.08.002","volume":"16","author":"PR Ouyang","year":"2006","unstructured":"Ouyang, P.R., Zhang, W.J., Gupta, M.M. (2006). An adaptive switching learning control method for trajectory tracking of robot manipulators. Metchatronics, 16, 51\u201361.","journal-title":"Metchatronics"},{"key":"500_CR55","doi-asserted-by":"crossref","unstructured":"Pape, L., Oddo, C.M., Controzzi, M., Cipriani, C., Frster, A., Carrozza, M.C., Schmidhuber, J. (2012). Learning tactile skills through curious exploration. Frontiers in Neurorobotics, 6.","DOI":"10.3389\/fnbot.2012.00006"},{"issue":"5","key":"500_CR56","doi-asserted-by":"crossref","first-page":"307","DOI":"10.2976\/1.3171566","volume":"3","author":"D Polani","year":"2009","unstructured":"Polani, D. (2009). Information: currency of life. HFSP Journal, 3(5), 307\u201316.","journal-title":"HFSP Journal"},{"key":"500_CR57","unstructured":"Precup, D., Sutton, R.A., Dasgupta, S. (2001). Off-policy temporal difference learning with function approximation. In Proceedings of the eighteenth international conference on machine learning (pp. 417\u2013424)."},{"issue":"6","key":"500_CR58","doi-asserted-by":"crossref","first-page":"1825","DOI":"10.4249\/scholarpedia.1825","volume":"2","author":"P Redgrave","year":"2007","unstructured":"Redgrave, P. (2007). Basal ganglia. Scholarpedia, 2(6), 1825.","journal-title":"Scholarpedia"},{"issue":"18","key":"500_CR59","doi-asserted-by":"crossref","first-page":"8201","DOI":"10.1523\/JNEUROSCI.22-18-08201.2002","volume":"22","author":"MJ Richardson","year":"2002","unstructured":"Richardson, M.J., & Flash, T. (2002). Comparing smooth arm movements with the two-thirds power law and the related segmented-control hypothesis. Journal of Neuroscience, 22(18), 8201\u201311.","journal-title":"Journal of Neuroscience"},{"issue":"40","key":"500_CR60","doi-asserted-by":"crossref","first-page":"14,022","DOI":"10.1523\/JNEUROSCI.2432-12.2012","volume":"32","author":"A Saig","year":"2012","unstructured":"Saig, A., Gordon, G., Assa, E., Arieli, A., Ahissar, E. (2012). Motor-sensory confluence in tactile perception. Journal of Neuroscience, 32(40), 14,022\u201332.","journal-title":"Journal of Neuroscience"},{"key":"500_CR61","unstructured":"Schmidhuber, J. (1990). A possibility for implementing curiosity and boredom in model-building neural controllers. In Proceedings of the first international conference on simulation of adaptive behavior on from animals to animats (Vol. 116542, pp. 222? 227). MIT Press."},{"issue":"3","key":"500_CR62","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/TAMD.2010.2056368","volume":"2","author":"J Schmidhuber","year":"2010","unstructured":"Schmidhuber, J. (2010). Formal theory of creativity, fun, and intrinsic motivation (1990-2010). IEEE Transactions on Autonomous Mental Development, 2(3), 230\u2013247.","journal-title":"IEEE Transactions on Autonomous Mental Development"},{"issue":"5306","key":"500_CR63","doi-asserted-by":"crossref","first-page":"1593","DOI":"10.1126\/science.275.5306.1593","volume":"275","author":"W Schultz","year":"1997","unstructured":"Schultz, W., Dayan, P., Montague, P.R. (1997). A neural substrate of prediction and reward. Science, 275(5306), 1593\u20139.","journal-title":"Science"},{"issue":"2","key":"500_CR64","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/0006-8993(80)90065-7","volume":"195","author":"K Semba","year":"1980","unstructured":"Semba, K., Szechtman, H., Komisaruk, B.R. (1980). Synchrony among rhythmical facial tremor, neocortical \u2019alpha\u2019 waves, and thalamic non-sensory neuronal bursts in intact awake rats. Brain Research, 195(2), 281\u201398.","journal-title":"Brain Research"},{"issue":"1","key":"500_CR65","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1038\/npp.2009.93","volume":"35","author":"SR Sesack","year":"2009","unstructured":"Sesack, S.R., & Grace, A.A. (2009). Cortico-basal ganglia reward network: Microcircuitry. Neuropsychopharmacology, 35(1), 27\u201347.","journal-title":"Neuropsychopharmacology"},{"issue":"3","key":"500_CR66","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1007\/s00221-008-1280-5","volume":"185","author":"R Shadmehr","year":"2008","unstructured":"Shadmehr, R., & Krakauer, J.W. (2008). A computational neuroanatomy for motor control. Experimentalis Brain Research, 185(3), 359\u201381.","journal-title":"Experimentalis Brain Research"},{"issue":"26","key":"500_CR67","doi-asserted-by":"crossref","first-page":"8935","DOI":"10.1523\/JNEUROSCI.0172-10.2010","volume":"30","author":"E Simony","year":"2010","unstructured":"Simony, E., Bagdasarian, K., Herfst, L., Brecht, M., Ahissar, E., Golomb, D. (2010). Temporal and spatial characteristics of vibrissa responses to motor commands. Journal of Neuroscience, 30(26), 8935\u20138952.","journal-title":"Journal of Neuroscience"},{"issue":"2","key":"500_CR68","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/TAMD.2010.2051031","volume":"2","author":"S Singh","year":"2010","unstructured":"Singh, S, Lewis, R.L., Barto, A.G., Sorg, J. (2010). Intrinsically motivated reinforcement learning: An evolutionary perspective. IEEE Transactions Autonomous Mental Development, 2(2), 70\u201382.","journal-title":"IEEE Transactions Autonomous Mental Development"},{"key":"500_CR69","first-page":"212","volume-title":"Learning options in reinforcement learning, lecture notes in computer science Vol. 2371","author":"M Stolle","year":"2002","unstructured":"Stolle, M., & Precup, D. (2002). Learning options in reinforcement learning, lecture notes in computer science (Vol. 2371, pp. 212\u2013223). Berlin Heidelberg: Springer."},{"key":"500_CR70","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R Sutton","year":"1999","unstructured":"Sutton, R., Precup, D., Singh, S. (1999). Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence in Engineering, 112, 181\u2013211.","journal-title":"Artificial Intelligence in Engineering"},{"key":"500_CR71","unstructured":"Sutton, R.A., Modayil, J., Delp, M., Degris, T., Pilarski, P.M., White, A., Precup, D. (2011). Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction. In The 10th international conference on autonomous agents and multiagent systems - volume 2, international foundation for autonomous agents and multiagent systems, 2031726 (pp. 761\u2013768)."},{"issue":"1","key":"500_CR72","first-page":"9","volume":"3","author":"RS Sutton","year":"1988","unstructured":"Sutton, R.S. (1988). Learning to predict by the methods of temporal differences. Machine Learning, 3(1), 9\u201344.","journal-title":"Machine Learning"},{"issue":"3","key":"500_CR73","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1016\/S0896-6273(03)00671-8","volume":"40","author":"M Szwed","year":"2003","unstructured":"Szwed, M., Bagdasarian, K., Ahissar, E. (2003). Encoding of vibrissal active touch. Neuron, 40(3), 621\u201330.","journal-title":"Neuron"},{"issue":"2","key":"500_CR74","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1152\/jn.00571.2005","volume":"95","author":"M Szwed","year":"2006","unstructured":"Szwed, M., Bagdasarian, K., Blumenfeld, B., Barak, O., Derdikman, D., Ahissar, E. (2006). Responses of trigeminal ganglion neurons to the radial distance of contact during active vibrissal touch. Journal of Neurophysiology, 95(2), 791\u2013802.","journal-title":"Journal of Neurophysiology"},{"issue":"6","key":"500_CR75","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1007\/s004220050447","volume":"78","author":"O Tchernichovski","year":"1998","unstructured":"Tchernichovski, O., & Benjamini, Y. (1998). The dynamics of long-term exploration in the rat. part ii. an analytical model of the kinematic structure of rat exploratory behavior. Biological Cybernetics, 78(6), 433\u201340.","journal-title":"Biological Cybernetics"},{"issue":"6","key":"500_CR76","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1007\/s004220050446","volume":"78","author":"O Tchernichovski","year":"1998","unstructured":"Tchernichovski, O., Benjamini, Y., Golani, I. (1998). The dynamics of long-term exploration in the rat. part i. a phase-plane analysis of the relationship between location and velocity. Biological Cybernetics, 78(6), 423\u201332.","journal-title":"Biological Cybernetics"},{"key":"500_CR77","unstructured":"Tinbergen, N. (1951). The study of instinct. New York: Oxford University Press."},{"key":"500_CR78","unstructured":"Tishby, N., & Polani, D. (2011). Information theory of decisions and actions. Springer series in cognitive and neural systems (chap. 19 pp. 601\u2013636). New York: Springer."},{"issue":"34","key":"500_CR79","doi-asserted-by":"crossref","first-page":"8838","DOI":"10.1523\/JNEUROSCI.0581-06.2006","volume":"26","author":"RB Towal","year":"2006","unstructured":"Towal, R.B., & Hartmann, M.J. (2006). Right-left asymmetries in the whisking behavior of rats anticipate head movements. Journal of Neuroscience, 26(34), 8838\u201346.","journal-title":"Journal of Neuroscience"},{"issue":"2","key":"500_CR80","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1152\/jn.01295.2007","volume":"100","author":"RB Towal","year":"2008","unstructured":"Towal, R.B., & Hartmann, M.J. (2008). Variability in velocity profiles during free-air whisking behavior of unrestrained rats. Journal of Neurophysiology, 100(2), 740\u201352.","journal-title":"Journal of Neurophysiology"},{"issue":"7126","key":"500_CR81","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1038\/nature05464","volume":"445","author":"M Vergassola","year":"2007","unstructured":"Vergassola, M., Villermaux, E., Shraiman, B.I. (2007). Infotaxis as a strategy for searching without gradients. Natural, 445(7126), 406\u20139.","journal-title":"Natural"},{"key":"500_CR82","doi-asserted-by":"crossref","unstructured":"Wawrzynski, P., & Pacut, A. (2004). Model-free off-policy reinforcement learning in continuous environment. In Proceedings of the 2004 IEEE international joint conference on neural networks, 2004. (vol 2, pp. 1091\u20131096).","DOI":"10.1109\/IJCNN.2004.1380086"},{"issue":"2","key":"500_CR83","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1142\/S0219843604000149","volume":"1","author":"J Weng","year":"2004","unstructured":"Weng, J. (2004). Developmental robotics: theory and experiments. International Journal Humanoid Robotics, 1(2), 199\u2013236.","journal-title":"International Journal Humanoid Robotics"},{"issue":"2","key":"500_CR84","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.bbr.2006.03.037","volume":"171","author":"IQ Whishaw","year":"2006","unstructured":"Whishaw, I.Q., Gharbawie, O.A., Clark, B.J., Lehmann, H. (2006). The exploratory behavior of rats in an open environment optimizes security. Behavior Brain Research, 171(2), 230\u20139.","journal-title":"Behavior Brain Research"},{"key":"500_CR85","unstructured":"Yu, C., Horev, G., Rubin, N., Derdikman, D., Haidarliu, S., Ahissar, E. (2013). Coding of object location in the vibrissal thalamocortical system. Cerebral Cortex: bht241."}],"container-title":["Journal of Computational Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10827-014-0500-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10827-014-0500-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10827-014-0500-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,10]],"date-time":"2019-08-10T06:39:38Z","timestamp":1565419178000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10827-014-0500-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,5,7]]},"references-count":87,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,10]]}},"alternative-id":["500"],"URL":"https:\/\/doi.org\/10.1007\/s10827-014-0500-1","relation":{},"ISSN":["0929-5313","1573-6873"],"issn-type":[{"value":"0929-5313","type":"print"},{"value":"1573-6873","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,5,7]]}}}