{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:10:58Z","timestamp":1740107458729,"version":"3.37.3"},"reference-count":88,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,3,3]],"date-time":"2022-03-03T00:00:00Z","timestamp":1646265600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,3]],"date-time":"2022-03-03T00:00:00Z","timestamp":1646265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000001","name":"u.s. national science foundation","doi-asserted-by":"crossref","award":["ECCS-1501044","EPCN-1903781"],"award-info":[{"award-number":["ECCS-1501044","EPCN-1903781"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Biol Cybern"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s00422-022-00922-z","type":"journal-article","created":{"date-parts":[[2022,3,3]],"date-time":"2022-03-03T08:04:06Z","timestamp":1646294646000},"page":"307-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Human motor learning is robust to control-dependent noise"],"prefix":"10.1007","volume":"116","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4359-2937","authenticated-orcid":false,"given":"Bo","family":"Pang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leilei","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhong-Ping","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,3]]},"reference":[{"issue":"1","key":"922_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0170466","volume":"12","author":"L Acerbi","year":"2017","unstructured":"Acerbi L, Vijayakumar S, Wolpert DM (2017) Target uncertainty mediates sensorimotor error correction. PLoS ONE 12(1):1\u201321","journal-title":"PLoS ONE"},{"key":"922_CR2","unstructured":"\u00c5str\u00f6m KJ, Wittenmark B (1995) Adaptive control, 2nd edn. Addison-Wesley, Reading"},{"issue":"8","key":"922_CR3","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1038\/nrn3289","volume":"13","author":"DR Bach","year":"2012","unstructured":"Bach DR, Dolan RJ (2012) Knowing how much you don\u2019t know: a neural organization of uncertainty estimates. Nat Rev Neurosci 13(8):572\u2013586","journal-title":"Nat Rev Neurosci"},{"key":"922_CR4","volume-title":"Robust control toolbox user\u2019s guide","author":"G Balas","year":"2007","unstructured":"Balas G, Chiang R, Packard A, Safonov M (2007) Robust control toolbox user\u2019s guide. The Math Works Inc, Tech Rep"},{"issue":"3","key":"922_CR5","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1007\/s11768-011-1005-3","volume":"9","author":"DP Bertsekas","year":"2011","unstructured":"Bertsekas DP (2011) Approximate policy iteration: a survey and some new methods. J Control Theory Appl 9(3):310\u2013335","journal-title":"J Control Theory Appl"},{"key":"922_CR6","volume-title":"Reinforcement learning and optimal control","author":"DP Bertsekas","year":"2019","unstructured":"Bertsekas DP (2019) Reinforcement learning and optimal control. Athena Scientific, Belmont"},{"issue":"6","key":"922_CR7","doi-asserted-by":"publisher","first-page":"4150","DOI":"10.1137\/18M1214147","volume":"57","author":"T Bian","year":"2019","unstructured":"Bian T, Jiang ZP (2019) Continuous-time robust dynamic programming. SIAM J Control Optim 57(6):4150\u20134174","journal-title":"SIAM J Control Optim"},{"issue":"12","key":"922_CR8","doi-asserted-by":"publisher","first-page":"4170","DOI":"10.1109\/TAC.2016.2550518","volume":"61","author":"T Bian","year":"2016","unstructured":"Bian T, Jiang Y, Jiang ZP (2016) Adaptive dynamic programming for stochastic systems with state and control dependent noise. IEEE Trans Autom Control 61(12):4170\u20134175","journal-title":"IEEE Trans Autom Control"},{"issue":"3","key":"922_CR9","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1162\/neco_a_01260","volume":"32","author":"T Bian","year":"2020","unstructured":"Bian T, Wolpert DM, Jiang ZP (2020) Model-free robust optimal feedback mechanisms of biological motor control. Neural Comput 32(3):562\u2013595","journal-title":"Neural Comput"},{"issue":"20","key":"922_CR10","doi-asserted-by":"publisher","first-page":"6472","DOI":"10.1523\/JNEUROSCI.3075-08.2009","volume":"29","author":"DA Braun","year":"2009","unstructured":"Braun DA, Aertsen A, Wolpert DM, Mehring C (2009) Learning optimal adaptation strategies in unpredictable motor tasks. J Neurosci 29(20):6472\u20136478","journal-title":"J Neurosci"},{"issue":"6862","key":"922_CR11","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1038\/35106566","volume":"414","author":"E Burdet","year":"2001","unstructured":"Burdet E, Osu R, Franklin DW, Milner TE, Kawato M (2001) The central nervous system stabilizes unstable dynamics by learning optimal impedance. Nature 414(6862):446\u2013449","journal-title":"Nature"},{"issue":"1","key":"922_CR12","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1007\/s00422-005-0025-9","volume":"94","author":"E Burdet","year":"2006","unstructured":"Burdet E, Tee KP, Mareels I, Milner TE, Chew CM, Franklin DW, Osu R, Kawato M (2006) Stability and motor adaptation in human arm movements. Biol Cybern 94(1):20\u201332","journal-title":"Biol Cybern"},{"key":"922_CR13","doi-asserted-by":"crossref","unstructured":"\u010cesonis J, Franklin DW (2020) Time-to-target simplifies optimal control of visuomotor feedback responses. eNeuro 7(2):ENEURO.0514\u201319.2020","DOI":"10.1523\/ENEURO.0514-19.2020"},{"key":"922_CR14","doi-asserted-by":"crossref","unstructured":"\u010cesonis J, Franklin DW (2021) Mixed-horizon optimal feedback control as a model of human movement. arXiv preprint arXiv:210406275","DOI":"10.51628\/001c.29674"},{"issue":"36","key":"922_CR15","doi-asserted-by":"publisher","first-page":"12465","DOI":"10.1523\/JNEUROSCI.0902-15.2015","volume":"35","author":"T Cluff","year":"2015","unstructured":"Cluff T, Scott SH (2015) Apparent and actual trajectory control depend on the behavioral context in upper limb motor tasks. J Neurosci 35(36):12465\u201312476","journal-title":"J Neurosci"},{"issue":"41","key":"922_CR16","doi-asserted-by":"publisher","first-page":"8135","DOI":"10.1523\/JNEUROSCI.0770-19.2019","volume":"39","author":"F Crevecoeur","year":"2019","unstructured":"Crevecoeur F, Scott SH, Cluff T (2019) Robust control in human reaching movements: a model-free strategy to compensate for unpredictable disturbances. J Neurosci 39(41):8135\u20138148","journal-title":"J Neurosci"},{"issue":"1","key":"922_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1523\/ENEURO.0149-19.2019","volume":"7","author":"F Crevecoeur","year":"2020","unstructured":"Crevecoeur F, Thonnard JL, Lef\u00e8vre P (2020) A very fast time scale of human motor adaptation: within movement adjustments of internal representations during reaching. eNeuro 7(1):1\u201316","journal-title":"eNeuro"},{"issue":"4","key":"922_CR18","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1016\/j.neuroimage.2009.04.096","volume":"47","author":"M d\u2019Acremont","year":"2009","unstructured":"d\u2019Acremont M, Lu ZL, Li X, Van der Linden M, Bechara A (2009) Neural correlates of risk prediction error during reinforcement learning in humans. NeuroImage 47(4):1929\u20131939","journal-title":"NeuroImage"},{"issue":"4","key":"922_CR19","doi-asserted-by":"publisher","first-page":"2038","DOI":"10.1152\/jn.01311.2006","volume":"98","author":"IR Fiete","year":"2007","unstructured":"Fiete IR, Fee MS, Seung HS (2007) Model of birdsong learning based on gradient estimation by dynamic perturbation of neural conductances. J Neurophysiol 98(4):2038\u20132057","journal-title":"J Neurophysiol"},{"issue":"6","key":"922_CR20","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1037\/h0055392","volume":"47","author":"PM Fitts","year":"1954","unstructured":"Fitts PM (1954) The information capacity of the human motor system in controlling the amplitude of movement. J Exp Psychol 47(6):381","journal-title":"J Exp Psychol"},{"issue":"7","key":"922_CR21","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1523\/JNEUROSCI.05-07-01688.1985","volume":"5","author":"T Flash","year":"1985","unstructured":"Flash T, Hogan N (1985) The coordination of arm movements: an experimentally confirmed mathematical model. J Neurosci 5(7):1688\u20131703","journal-title":"J Neurosci"},{"issue":"3","key":"922_CR22","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/j.neuron.2011.10.006","volume":"72","author":"DW Franklin","year":"2011","unstructured":"Franklin DW, Wolpert DM (2011) Computational mechanisms of sensorimotor control. Neuron 72(3):425\u2013442","journal-title":"Neuron"},{"issue":"2","key":"922_CR23","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s00221-003-1443-3","volume":"151","author":"DW Franklin","year":"2003","unstructured":"Franklin DW, Burdet E, Osu R, Kawato M, Milner TE (2003) Functional significance of stiffness in adaptation of multijoint arm movements to stable and unstable dynamics. Exp Brain Res 151(2):145\u2013157","journal-title":"Exp Brain Res"},{"issue":"44","key":"922_CR24","doi-asserted-by":"publisher","first-page":"11165","DOI":"10.1523\/JNEUROSCI.3099-08.2008","volume":"28","author":"DW Franklin","year":"2008","unstructured":"Franklin DW, Burdet E, Peng Tee K, Osu R, Chew CM, Milner TE, Kawato M (2008) CNS learns stable, accurate, and efficient movements using a simple algorithm. J Neurosci 28(44):11165\u201311173","journal-title":"J Neurosci"},{"issue":"1","key":"922_CR25","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1152\/jn.01029.2012","volume":"111","author":"J Gaveau","year":"2014","unstructured":"Gaveau J, Berret B, Demougeot L, Fadiga L, Pozzo T, Papaxanthis C (2014) Energy-related optimal control accounts for gravitational load: comparing shoulder, elbow, and wrist rotations. J Neurophysiol 111(1):4\u201316","journal-title":"J Neurophysiol"},{"issue":"5258","key":"922_CR26","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1126\/science.272.5258.117","volume":"272","author":"H Gomi","year":"1996","unstructured":"Gomi H, Kawato M (1996) Equilibrium-point control hypothesis examined by measured arm stiffness during multijoint movement. Science 272(5258):117\u2013120","journal-title":"Science"},{"issue":"2","key":"922_CR27","doi-asserted-by":"publisher","first-page":"7392","DOI":"10.1016\/j.ifacol.2020.12.1268","volume":"53","author":"BJ Gravell","year":"2020","unstructured":"Gravell BJ, Esfahani PM, Summers TH (2020) Robust control design for linear systems via multiplicative noise. IFAC-PapersOnLine 53(2):7392\u20137399","journal-title":"IFAC-PapersOnLine"},{"issue":"12","key":"922_CR28","doi-asserted-by":"publisher","first-page":"2747","DOI":"10.1523\/JNEUROSCI.2125-20.2021","volume":"41","author":"AM Hadjiosif","year":"2021","unstructured":"Hadjiosif AM, Krakauer JW, Haith AM (2021) Did we get sensorimotor adaptation wrong? Implicit adaptation as direct policy updating rather than forward-model-based learning. J Neurosci 41(12):2747\u20132761","journal-title":"J Neurosci"},{"issue":"6902","key":"922_CR29","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/nature00974","volume":"419","author":"RHR Hahnloser","year":"2002","unstructured":"Hahnloser RHR, Kozhevnikov AA, Fee MS (2002) An ultra-sparse code underliesthe generation of neural sequences in a songbird. Nature 419(6902):65\u201370","journal-title":"Nature"},{"key":"922_CR30","first-page":"1","volume-title":"Progress in motor control","author":"AM Haith","year":"2013","unstructured":"Haith AM, Krakauer JW (2013) Model-based and model-free mechanisms of human motor learning. In: Richardson MJ, Riley MA, Shockley K (eds) Progress in motor control. Springer, New York, pp 1\u201321"},{"issue":"6695","key":"922_CR31","doi-asserted-by":"publisher","first-page":"780","DOI":"10.1038\/29528","volume":"394","author":"CM Harris","year":"1998","unstructured":"Harris CM, Wolpert DM (1998) Signal-dependent noise determines motor planning. Nature 394(6695):780\u2013784","journal-title":"Nature"},{"issue":"4","key":"922_CR32","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1016\/j.neuron.2011.04.012","volume":"70","author":"VS Huang","year":"2011","unstructured":"Huang VS, Haith A, Mazzoni P, Krakauer JW (2011) Rethinking motor learning and savings in adaptation paradigms: model-free memory for successful actions combines with internal models. Neuron 70(4):787\u2013801","journal-title":"Neuron"},{"key":"922_CR33","unstructured":"Huh D (2012) Rethinking optimal control of human movements. PhD thesis, UC San Diego"},{"key":"922_CR34","unstructured":"Huh D, Todorov E, Sejnowski T et\u00a0al (2010) Infinite horizon optimal control framework for goal directed movements. In: Proceedings of the 9th annual symposium on advances in computational motor control, vol\u00a012"},{"issue":"3","key":"922_CR35","doi-asserted-by":"publisher","first-page":"e1002012","DOI":"10.1371\/journal.pcbi.1002012","volume":"7","author":"J Izawa","year":"2011","unstructured":"Izawa J, Shadmehr R (2011) Learning from sensory and reward prediction errors during motor adaptation. PLoS Comput Biol 7(3):e1002012","journal-title":"PLoS Comput Biol"},{"issue":"4","key":"922_CR36","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/s00422-014-0613-7","volume":"108","author":"Y Jiang","year":"2014","unstructured":"Jiang Y, Jiang ZP (2014) Adaptive dynamic programming as a theory of sensorimotor control. Biol Cybern 108(4):459\u2013473","journal-title":"Biol Cybern"},{"issue":"2","key":"922_CR37","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11424-015-3310-2","volume":"28","author":"Y Jiang","year":"2015","unstructured":"Jiang Y, Jiang ZP (2015) A robust adaptive dynamic programming principle for sensorimotor control with signal-dependent noise. J Syst Sci Complex 28(2):261\u2013288","journal-title":"J Syst Sci Complex"},{"key":"922_CR38","doi-asserted-by":"publisher","DOI":"10.1002\/9781119132677","volume-title":"Robust adaptive dynamic programming","author":"Y Jiang","year":"2017","unstructured":"Jiang Y, Jiang ZP (2017) Robust adaptive dynamic programming. Wiley-IEEE Press, Hoboken"},{"key":"922_CR39","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1561\/2600000023","volume":"8","author":"Z Jiang","year":"2020","unstructured":"Jiang Z, Bian T, Gao W (2020) Learning-based control: a tutorial and some recent results. Found Trends Syst Control 8:176\u2013284","journal-title":"Found Trends Syst Control"},{"issue":"5","key":"922_CR40","doi-asserted-by":"publisher","first-page":"2737","DOI":"10.1152\/jn.00079.2011","volume":"106","author":"A Kadiallah","year":"2011","unstructured":"Kadiallah A, Liaw G, Kawato M, Franklin DW, Burdet E (2011) Impedance control is selectively tuned to multiple directions of movement. J Neurophysiol 106(5):2737\u20132748","journal-title":"J Neurophysiol"},{"key":"922_CR41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-78384-0","volume-title":"Reinforcement learning for optimal feedback control: a Lyapunov-based approach","author":"R Kamalapurkar","year":"2018","unstructured":"Kamalapurkar R, Walters P, Rosenfeld J, Dixon W (2018) Reinforcement learning for optimal feedback control: a Lyapunov-based approach. Springer, Berlin"},{"key":"922_CR42","volume-title":"Nonlinear systems","author":"HK Khalil","year":"2002","unstructured":"Khalil HK (2002) Nonlinear systems, 3rd edn. Prentice-Hall, Upper Saddle River","edition":"3"},{"issue":"6","key":"922_CR43","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1109\/TNNLS.2017.2773458","volume":"29","author":"B Kiumarsi","year":"2018","unstructured":"Kiumarsi B, Vamvoudakis KG, Modares H, Lewis FL (2018) Optimal and autonomous control using reinforcement learning: a survey. IEEE Trans Neural Netw Learn Syst 29(6):2042\u20132062","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"1","key":"922_CR44","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1109\/TAC.1968.1098829","volume":"13","author":"D Kleinman","year":"1968","unstructured":"Kleinman D (1968) On an iterative technique for Riccati equation computations. IEEE Trans Autom Control 13(1):114\u2013115","journal-title":"IEEE Trans Autom Control"},{"issue":"4","key":"922_CR45","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1109\/TAC.1969.1099206","volume":"14","author":"D Kleinman","year":"1969","unstructured":"Kleinman D (1969) On the stability of linear stochastic systems. IEEE Trans Autom Control 14(4):429\u2013430","journal-title":"IEEE Trans Autom Control"},{"issue":"6971","key":"922_CR46","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1038\/nature02169","volume":"427","author":"KP K\u00f6rding","year":"2004","unstructured":"K\u00f6rding KP, Wolpert DM (2004) Bayesian integration in sensorimotor learning. Nature 427(6971):244\u2013247","journal-title":"Nature"},{"issue":"7","key":"922_CR47","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.tics.2006.05.003","volume":"10","author":"KP K\u00f6rding","year":"2006","unstructured":"K\u00f6rding KP, Wolpert DM (2006) Bayesian decision theory in sensorimotor control. Trends Cognit Sci 10(7):319\u2013326","journal-title":"Trends Cognit Sci"},{"key":"922_CR48","first-page":"613","volume-title":"Motor learning","author":"JW Krakauer","year":"2019","unstructured":"Krakauer JW, Hadjiosif AM, Xu J, Wong AL, Haith AM (2019) Motor learning. American Cancer Society, Atlanta, pp 613\u2013663"},{"key":"922_CR49","doi-asserted-by":"crossref","unstructured":"Li L, Imamizu H, Tanaka H (2015) Is movement duration predetermined in visually guided reaching? A comparison of finite-and infinite-horizon optimal feedback control. In: The abstracts of the international conference on advanced mechatronics: toward evolutionary fusion of IT and mechatronics: ICAM 2015.6. The Japan Society of Mechanical Engineers, pp 247\u2013248","DOI":"10.1299\/jsmeicam.2015.6.247"},{"key":"922_CR50","doi-asserted-by":"publisher","DOI":"10.1515\/9781400842643","volume-title":"Calculus of variations and optimal control theory: a concise introduction","author":"D Liberzon","year":"2012","unstructured":"Liberzon D (2012) Calculus of variations and optimal control theory: a concise introduction. Princeton University Press, Princeton"},{"issue":"35","key":"922_CR51","doi-asserted-by":"publisher","first-page":"9354","DOI":"10.1523\/JNEUROSCI.1110-06.2007","volume":"27","author":"D Liu","year":"2007","unstructured":"Liu D, Todorov E (2007) Evidence for the flexible sensorimotor strategies predicted by optimal feedback control. J Neurosci 27(35):9354\u20139368","journal-title":"J Neurosci"},{"key":"922_CR52","volume-title":"Matrix differential calculus with applications in statistics and economerices","author":"JR Magnus","year":"2007","unstructured":"Magnus JR, Neudecker H (2007) Matrix differential calculus with applications in statistics and economerices. Wiley, New York"},{"issue":"1","key":"922_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1152\/jn.00794.2011","volume":"110","author":"M Mistry","year":"2013","unstructured":"Mistry M, Theodorou E, Schaal S, Kawato M (2013) Optimal control of reaching includes kinematic constraints. J Neurophysiol 110(1):1\u201311","journal-title":"J Neurophysiol"},{"issue":"2","key":"922_CR54","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/BF00236911","volume":"42","author":"P Morasso","year":"1981","unstructured":"Morasso P (1981) Spatial control of arm movements. Exp Brain Res 42(2):223\u2013227","journal-title":"Exp Brain Res"},{"issue":"9","key":"922_CR55","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1109\/TAC.1986.1104416","volume":"31","author":"T Mori","year":"1986","unstructured":"Mori T, Fukuma N, Kuwahara M (1986) On the Lyapunov matrix differential equation. IEEE Trans Autom Control 31(9):868\u2013869","journal-title":"IEEE Trans Autom Control"},{"issue":"10","key":"922_CR56","doi-asserted-by":"publisher","first-page":"2732","DOI":"10.1523\/JNEUROSCI.05-10-02732.1985","volume":"5","author":"F Mussa-Ivaldi","year":"1985","unstructured":"Mussa-Ivaldi F, Hogan N, Bizzi E (1985) Neural, mechanical, and geometric factors subserving arm posture in humans. J Neurosci 5(10):2732\u20132743","journal-title":"J Neurosci"},{"issue":"4","key":"922_CR57","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/j.conb.2011.05.026","volume":"21","author":"G Orb\u00e1n","year":"2011","unstructured":"Orb\u00e1n G, Wolpert DM (2011) Representations of uncertainty in sensorimotor control. Curr Opin Neurobiol 21(4):629\u2013635","journal-title":"Curr Opin Neurobiol"},{"issue":"2","key":"922_CR58","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/TAC.2020.2987313","volume":"66","author":"B Pang","year":"2020","unstructured":"Pang B, Jiang ZP (2020) Adaptive optimal control of linear periodic systems: an off-policy value iteration approach. IEEE Trans Autom Control 66(2):888\u2013894","journal-title":"IEEE Trans Autom Control"},{"key":"922_CR59","doi-asserted-by":"crossref","unstructured":"Pang B, Jiang ZP (2021) Robust reinforcement learning: a case study in linear quadratic regulation. In: The 35th AAAI conference on artificial intelligence (AAAI). pp 9303\u20139311","DOI":"10.1609\/aaai.v35i10.17122"},{"issue":"1","key":"922_CR60","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/s11768-019-8168-8","volume":"17","author":"B Pang","year":"2019","unstructured":"Pang B, Bian T, Jiang ZP (2019) Adaptive dynamic programming for finite-horizon optimal control of linear time-varying discrete-time systems. Control Theory Technol 17(1):18\u201329","journal-title":"Control Theory Technol"},{"key":"922_CR61","doi-asserted-by":"publisher","first-page":"109035","DOI":"10.1016\/j.automatica.2020.109035","volume":"118","author":"B Pang","year":"2020","unstructured":"Pang B, Jiang ZP, Mareels I (2020) Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems. Automatica 118:109035","journal-title":"Automatica"},{"key":"922_CR62","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3085510","author":"B Pang","year":"2021","unstructured":"Pang B, Bian T, Jiang ZP (2021) Robust policy iteration for continuous-time linear quadratic regulation. IEEE Trans Autom Control. https:\/\/doi.org\/10.1109\/TAC.2021.3085510","journal-title":"IEEE Trans Autom Control"},{"issue":"1424","key":"922_CR63","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1098\/rstb.2002.1101","volume":"357","author":"A Parker","year":"2002","unstructured":"Parker A, Derrington A, Blakemore C, van Beers RJ, Baraduc P, Wolpert DM (2002) Role of uncertainty in sensorimotor control. Philos Trans R So Lond Ser B Biol Sci 357(1424):1137\u20131145","journal-title":"Philos Trans R So Lond Ser B Biol Sci"},{"key":"922_CR64","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-1323-7","volume-title":"Stochastic processes and applications","author":"GA Pavliotis","year":"2014","unstructured":"Pavliotis GA (2014) Stochastic processes and applications. Springer, New York"},{"issue":"3","key":"922_CR65","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1162\/NECO_a_00410","volume":"25","author":"N Qian","year":"2013","unstructured":"Qian N, Jiang Y, Jiang ZP, Mazzoni P (2013) Movement duration, Fitts\u2019s law, and an infinite-horizon optimal feedback control model for biological motor systems. Neural Comput 25(3):697\u2013724","journal-title":"Neural Comput"},{"key":"922_CR66","unstructured":"Schmidt RA, Lee TD, Winstein C, Wulf G, Zelaznik HN (2018) Motor control and learning: a behavioral emphasis. In: Human kinetics"},{"issue":"40","key":"922_CR67","doi-asserted-by":"publisher","first-page":"12606","DOI":"10.1523\/JNEUROSCI.2826-09.2009","volume":"29","author":"LPJ Selen","year":"2009","unstructured":"Selen LPJ, Franklin DW, Wolpert DM (2009) Impedance control reduces instability that arises from motor noise. J Neurosci 29(40):12606\u201312616","journal-title":"J Neurosci"},{"key":"922_CR68","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262016964.001.0001","volume-title":"Biological learning and control: how the brain builds representations, predicts events, and makes decisions","author":"R Shadmehr","year":"2012","unstructured":"Shadmehr R, Mussa-Ivaldi S (2012) Biological learning and control: how the brain builds representations, predicts events, and makes decisions. MIT Press, Cambridge"},{"issue":"42","key":"922_CR69","doi-asserted-by":"publisher","first-page":"14617","DOI":"10.1523\/JNEUROSCI.2184-12.2012","volume":"32","author":"L Shmuelof","year":"2012","unstructured":"Shmuelof L, Huang VS, Haith AM, Delnicki RJ, Mazzoni P, Krakauer JW (2012) Overcoming motor forgetting through reinforcement of learned actions. J Neurosci 32(42):14617\u201314621a","journal-title":"J Neurosci"},{"key":"922_CR70","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.cobeha.2018.01.004","volume":"20","author":"D Sternad","year":"2018","unstructured":"Sternad D (2018) It\u2019s not (only) the mean that matters: variability, noise and exploration in skill learning. Curr Opin Behav Sci 20:183\u2013195","journal-title":"Curr Opin Behav Sci"},{"issue":"9","key":"922_CR71","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1002159","volume":"7","author":"D Sternad","year":"2011","unstructured":"Sternad D, Abe MO, Hu X, M\u00fcller H (2011) Neuromotor noise, error tolerance and velocity-dependent costs in skilled performance. PLOS Comput Biol 7(9):1\u201315","journal-title":"PLOS Comput Biol"},{"key":"922_CR72","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction, 2nd edn. MIT Press, Cambridge","edition":"2"},{"issue":"2","key":"922_CR73","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1152\/jn.00493.2016","volume":"117","author":"EB Thorp","year":"2017","unstructured":"Thorp EB, Kording KP, Mussa-Ivaldi FA (2017) Using noise to shape motor learning. J Neurophysiol 117(2):728\u2013737","journal-title":"J Neurophysiol"},{"issue":"5","key":"922_CR74","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1162\/0899766053491887","volume":"17","author":"E Todorov","year":"2005","unstructured":"Todorov E (2005) Stochastic optimal control and estimation methods adapted to the noise characteristics of the sensorimotor system. Neural Comput 17(5):1084\u20131108","journal-title":"Neural Comput"},{"issue":"11","key":"922_CR75","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1038\/nn963","volume":"5","author":"E Todorov","year":"2002","unstructured":"Todorov E, Jordan MI (2002) Optimal feedback control as a theory of motor coordination. Nat Neurosci 5(11):1226\u20131235","journal-title":"Nat Neurosci"},{"key":"922_CR76","first-page":"59","volume":"3","author":"JN Tsitsiklis","year":"2002","unstructured":"Tsitsiklis JN (2002) On the convergence of optimistic policy iteration. J Mach Learn Res 3:59\u201372","journal-title":"J Mach Learn Res"},{"issue":"7173","key":"922_CR77","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1038\/nature06390","volume":"450","author":"EC Tumer","year":"2007","unstructured":"Tumer EC, Brainard MS (2007) Performance variability enables adaptive plasticity of \u2018crystallized\u2019 adult birdsong. Nature 450(7173):1240\u20131244","journal-title":"Nature"},{"key":"922_CR78","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fncom.2014.00119","volume":"8","author":"Y Ueyama","year":"2014","unstructured":"Ueyama Y (2014) Mini-max feedback control as a computational theory of sensorimotor control in the presence of structural uncertainty. Front Comput Neurosci 8:1\u201314","journal-title":"Front Comput Neurosci"},{"issue":"2","key":"922_CR79","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/BF00204593","volume":"61","author":"Y Uno","year":"1989","unstructured":"Uno Y, Kawato M, Suzuki R (1989) Formation and control of optimal trajectory in human multijoint arm movement. Biol Cybern 61(2):89\u2013101","journal-title":"Biol Cybern"},{"issue":"17","key":"922_CR80","doi-asserted-by":"publisher","first-page":"6969","DOI":"10.1523\/JNEUROSCI.2656-14.2015","volume":"35","author":"PA Vaswani","year":"2015","unstructured":"Vaswani PA, Shmuelof L, Haith AM, Delnicki RJ, Huang VS, Mazzoni P, Shadmehr R, Krakauer JW (2015) Persistent residual errors in motor adaptation tasks: reversion to baseline and exploratory escape. J Neurosci 35(17):6969\u20136977","journal-title":"J Neurosci"},{"issue":"3","key":"922_CR81","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/0005-1098(76)90029-7","volume":"12","author":"JL Willems","year":"1976","unstructured":"Willems JL, Willems JC (1976) Feedback stabilizability for stochastic systems with state and control dependent noise. Automatica 12(3):277\u2013283","journal-title":"Automatica"},{"key":"922_CR82","doi-asserted-by":"crossref","unstructured":"Wolpert DM (2007) Probabilistic models in human sensorimotor control. Hum Mov Sci 26(4):511\u2013524","DOI":"10.1016\/j.humov.2007.05.005"},{"issue":"5232","key":"922_CR83","doi-asserted-by":"publisher","first-page":"1880","DOI":"10.1126\/science.7569931","volume":"269","author":"D Wolpert","year":"1995","unstructured":"Wolpert D, Ghahramani Z, Jordan M (1995) An internal model for sensorimotor integration. Science 269(5232):1880\u20131882","journal-title":"Science"},{"issue":"2","key":"922_CR84","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1038\/nn.3616","volume":"17","author":"HG Wu","year":"2014","unstructured":"Wu HG, Miyamoto YR, Castro LNG, \u00d6lveczky BP, Smith MA (2014) Temporal structure of motor variability is dynamically regulated and predicts motor learning ability. Nat Neurosci 17(2):312\u2013321","journal-title":"Nat Neurosci"},{"key":"922_CR85","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1005190","volume":"12","author":"SH Yeo","year":"2016","unstructured":"Yeo SH, Franklin DW, Wolpert DM (2016) When optimal feedback control is not enough: feedforward strategies are required for optimal control with active sensing. PLOS Comput Biol 12:1\u201322","journal-title":"PLOS Comput Biol"},{"key":"922_CR86","volume-title":"Essentials of robust control","author":"K Zhou","year":"1998","unstructured":"Zhou K, Doyle JC (1998) Essentials of robust control, vol 104. Prentice Hall, Upper Saddle River"},{"issue":"1","key":"922_CR87","doi-asserted-by":"publisher","first-page":"2883","DOI":"10.3182\/20110828-6-IT-1002.02688","volume":"44","author":"SH Zhou","year":"2011","unstructured":"Zhou SH, Oetomo D, Tan Y, Burdet E, Mareels I (2011) Human motor learning through iterative model reference adaptive control. IFAC Proc Vol 44(1):2883\u20132888","journal-title":"IFAC Proc Vol"},{"issue":"5","key":"922_CR88","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1109\/TCST.2016.2615083","volume":"25","author":"SH Zhou","year":"2017","unstructured":"Zhou SH, Tan Y, Oetomo D, Freeman C, Burdet E, Mareels I (2017) Modeling of endpoint feedback learning implemented through point-to-point learning control. IEEE Trans Control Syst Technol 25(5):1576\u20131585","journal-title":"IEEE Trans Control Syst Technol"}],"container-title":["Biological Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-022-00922-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00422-022-00922-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-022-00922-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T08:02:02Z","timestamp":1674892922000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00422-022-00922-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,3]]},"references-count":88,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["922"],"URL":"https:\/\/doi.org\/10.1007\/s00422-022-00922-z","relation":{},"ISSN":["1432-0770"],"issn-type":[{"type":"electronic","value":"1432-0770"}],"subject":[],"published":{"date-parts":[[2022,3,3]]},"assertion":[{"value":"6 February 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}