{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:53:42Z","timestamp":1777654422131,"version":"3.51.4"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T00:00:00Z","timestamp":1698883200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T00:00:00Z","timestamp":1698883200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Humans generate intricate whole-body motions by planning, executing and combining individual limb movements. We investigated this fundamental aspect of motor control and approached the problem of autonomous task completion by hierarchical generative modelling with multi-level planning, emulating the deep temporal architecture of human motor control. We explored the temporal depth of nested timescales, where successive levels of a forward or generative model unfold, for example, object delivery requires both global planning and local coordination of limb movements. This separation of temporal scales suggests the advantage of hierarchically organizing the global planning and local control of individual limbs. We validated our proposed formulation extensively through physics simulation. Using a hierarchical generative model, we showcase that an embodied artificial intelligence system, a humanoid robot, can autonomously complete a complex task requiring a holistic use of locomotion, manipulation and grasping: the robot adeptly retrieves and transports a box, opens and walks through a door, kicks a football and exhibits robust performance even in the presence of body damage and ground irregularities. Our findings demonstrated the efficacy and feasibility of human-inspired motor control for an embodied artificial intelligence robot, highlighting the viability of the formulized hierarchical architecture for achieving autonomous completion of challenging goal-directed tasks.<\/jats:p>","DOI":"10.1038\/s42256-023-00752-z","type":"journal-article","created":{"date-parts":[[2023,11,2]],"date-time":"2023-11-02T13:03:18Z","timestamp":1698930198000},"page":"1402-1414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Hierarchical generative modelling for autonomous robots"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2349-4192","authenticated-orcid":false,"given":"Kai","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noor","family":"Sajid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7984-8909","authenticated-orcid":false,"given":"Karl","family":"Friston","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6357-7419","authenticated-orcid":false,"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,2]]},"reference":[{"key":"752_CR1","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/nature14178","volume":"519","author":"N Li","year":"2015","unstructured":"Li, N., Chen, T.-W., Guo, Z. V., Gerfen, C. R. & Svoboda, K. A motor cortex circuit for motor planning and movement. Nature 519, 51\u201356 (2015).","journal-title":"Nature"},{"key":"752_CR2","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/j.neuron.2012.08.011","volume":"76","author":"CJ Honey","year":"2012","unstructured":"Honey, C. J. et al. Slow cortical dynamics and the accumulation of information over long timescales. Neuron 76, 423\u2013434 (2012).","journal-title":"Neuron"},{"key":"752_CR3","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1038\/nn.3862","volume":"17","author":"JD Murray","year":"2014","unstructured":"Murray, J. D. et al. A hierarchy of intrinsic timescales across primate cortex. Nat. Neurosci. 17, 1661\u20131663 (2014).","journal-title":"Nat. Neurosci."},{"key":"752_CR4","doi-asserted-by":"publisher","unstructured":"Merel, J. et al. Hierarchical visuomotor control of humanoids. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1811.09656 (2018).","DOI":"10.48550\/arXiv.1811.09656"},{"key":"752_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13239-6","volume":"10","author":"J Merel","year":"2019","unstructured":"Merel, J., Botvinick, M. & Wayne, G. Hierarchical motor control in mammals and machines. Nat. Commun. 10, 5489 (2019).","journal-title":"Nat. Commun."},{"key":"752_CR6","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MRA.2019.2943395","volume":"26","author":"A Kheddar","year":"2019","unstructured":"Kheddar, A. et al. Humanoid robots in aircraft manufacturing: the airbus use cases. IEEE Robot. Autom. Mag. 26, 30\u201345 (2019).","journal-title":"IEEE Robot. Autom. Mag."},{"key":"752_CR7","unstructured":"Schmaus, P. et al. IEEE Aerospace Conference (IEEE, 2019)."},{"key":"752_CR8","doi-asserted-by":"crossref","unstructured":"Oliver, G., Lanillos, P. & Cheng, G. An empirical study of active inference on a humanoid robot. IEEE Trans. Cogn. Develop. Syst., 14, 462\u2013471 (2021).","DOI":"10.1109\/TCDS.2021.3049907"},{"key":"752_CR9","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1002\/rob.21571","volume":"32","author":"M Johnson","year":"2015","unstructured":"Johnson, M. et al. Team IHMC\u2019s lessons learned from the DARPA robotics challenge trials. J. Field Rob. 32, 192\u2013208 (2015).","journal-title":"J. Field Rob."},{"key":"752_CR10","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MRA.2019.2940964","volume":"26","author":"I Kumagai","year":"2019","unstructured":"Kumagai, I. et al. Toward industrialization of humanoid robots: autonomous plasterboard installation to improve safety and efficiency. IEEE Robot. Autom. Mag. 26, 20\u201329 (2019).","journal-title":"IEEE Robot. Autom. Mag."},{"key":"752_CR11","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1109\/LRA.2018.2798285","volume":"3","author":"AW Winkler","year":"2018","unstructured":"Winkler, A. W., Bellicoso, C. D., Hutter, M. & Buchli, J. Gait and trajectory optimization for legged systems through phase-based end-effector parameterization. IEEE Robot. Autom. Let. 3, 1560\u20131567 (2018).","journal-title":"IEEE Robot. Autom. Let."},{"key":"752_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1613\/jair.1.11633","volume":"68","author":"S Toyer","year":"2020","unstructured":"Toyer, S., Thi\u00e9baux, S., Trevizan, F. & Xie, L. Asnets: deep learning for generalised planning. J. Artif. Intell. Res. 68, 1\u201368 (2020).","journal-title":"J. Artif. Intell. Res."},{"key":"752_CR13","doi-asserted-by":"publisher","first-page":"172","DOI":"10.3390\/make4010009","volume":"4","author":"M Hutsebaut-Buysse","year":"2022","unstructured":"Hutsebaut-Buysse, M., Mets, K. & Latr\u00e9, S. Hierarchical reinforcement learning: a survey and open research challenges. Mach. Learn. Knowl. Extr. 4, 172\u2013221 (2022).","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"752_CR14","unstructured":"Jain, D., Iscen, A. & Caluwaerts, K. 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE, 2019)."},{"key":"752_CR15","unstructured":"Li, C., Xia, F., Martin-Martin, R. & Savarese, S. Hrl4in: hierarchical reinforcement learning for interactive navigation with mobile manipulators. In Proc. Conference on Robot Learning (eds. Kaelbling, L. P., Kragic, D. & Sugiura, K.) 603\u2013616 (PMLR, 2020)."},{"key":"752_CR16","unstructured":"Findeisen, W. et al. Control and Coordination in Hierarchical Systems (Wiley, 1980)."},{"key":"752_CR17","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R. S., Precup, D. & Singh, S. Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112, 181\u2013211 (1999).","journal-title":"Artif. Intell."},{"key":"752_CR18","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1162\/jocn_a_00204","volume":"24","author":"S Uithol","year":"2012","unstructured":"Uithol, S., van Rooij, I., Bekkering, H. & Haselager, P. Hierarchies in action and motor control. J. Cogn. Neurosci. 24, 1077\u20131086 (2012).","journal-title":"J. Cogn. Neurosci."},{"key":"752_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s002210050712","volume":"126","author":"GE Loeb","year":"1999","unstructured":"Loeb, G. E., Brown, I. E. & Cheng, E. J. A hierarchical foundation for models of sensorimotor control. Exp. Brain Res. 126, 1\u201318 (1999).","journal-title":"Exp. Brain Res."},{"key":"752_CR20","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1016\/S0893-6080(99)00060-X","volume":"12","author":"J Tani","year":"1999","unstructured":"Tani, J. & Nolfi, S. Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems. Neural Netw. 12, 1131\u20131141 (1999).","journal-title":"Neural Netw."},{"key":"752_CR21","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1016\/j.tics.2012.08.006","volume":"16","author":"M Botvinick","year":"2012","unstructured":"Botvinick, M. & Toussaint, M. Planning as inference. Trends Cogn. Sci. 16, 485\u2013488 (2012).","journal-title":"Trends Cogn. Sci."},{"key":"752_CR22","unstructured":"Wolpert, D. M., Ghahramani, Z. & Jordan, M. Forward dynamic models in human motor control: psychophysical evidence. Adv. Neural Inf. Process. Syst. 7, 43\u201350 (1994)."},{"key":"752_CR23","unstructured":"Attias, H. Planning by probabilistic inference. In Proc. Ninth International Workshop on Artificial Intelligence and Statistics (eds Bishop, C. M. and Frey, B. J.) 9\u201316 (PMLR, 2003)."},{"key":"752_CR24","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.cognition.2009.07.005","volume":"113","author":"CL Baker","year":"2009","unstructured":"Baker, C. L., Saxe, R. & Tenenbaum, J. B. Action understanding as inverse planning. Cognition 113, 329\u2013349 (2009).","journal-title":"Cognition"},{"key":"752_CR25","doi-asserted-by":"publisher","first-page":"20141335","DOI":"10.1098\/rsif.2014.1335","volume":"12","author":"D Maisto","year":"2015","unstructured":"Maisto, D., Donnarumma, F. & Pezzulo, G. Divide et impera: subgoaling reduces the complexity of probabilistic inference and problem solving. J. R. Soc. Interface 12, 20141335 (2015).","journal-title":"J. R. Soc. Interface"},{"key":"752_CR26","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/s00422-018-0753-2","volume":"112","author":"R Kaplan","year":"2018","unstructured":"Kaplan, R. & Friston, K. J. Planning and navigation as active inference. Biol. Cybern. 112, 323\u2013343 (2018).","journal-title":"Biol. Cybern."},{"key":"752_CR27","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/S0893-6080(02)00214-9","volume":"16","author":"J Tani","year":"2003","unstructured":"Tani, J. Learning to generate articulated behavior through the bottom-up and the top-down interaction processes. Neural Netw. 16, 11\u201323 (2003).","journal-title":"Neural Netw."},{"key":"752_CR28","doi-asserted-by":"publisher","first-page":"564","DOI":"10.3390\/e22050564","volume":"22","author":"T Matsumoto","year":"2020","unstructured":"Matsumoto, T. & Tani, J. Goal-directed planning for habituated agents by active inference using a variational recurrent neural network. Entropy 22, 564 (2020).","journal-title":"Entropy"},{"key":"752_CR29","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1016\/S0531-5131(03)00190-0","volume":"1250","author":"M Haruno","year":"2003","unstructured":"Haruno, M., Wolpert, D. M. & Kawato, M. Hierarchical MOSAIC for movement generation. Int. Congr. Ser. 1250, 575\u2013590 (2003).","journal-title":"Int. Congr. Ser."},{"key":"752_CR30","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/S0921-8890(01)00113-0","volume":"36","author":"J Morimoto","year":"2001","unstructured":"Morimoto, J. & Doya, K. Acquisition of stand-up behavior by a real robot using hierarchical reinforcement learning. Rob. Autom. Syst. 36, 37\u201351 (2001).","journal-title":"Rob. Autom. Syst."},{"key":"752_CR31","doi-asserted-by":"crossref","unstructured":"Baltieri, M. & Buckley, C. L. Generative models as parsimonious descriptions of sensorimotor loops. Behav. Brain Sci. 42, e218 (2019).","DOI":"10.1017\/S0140525X19001353"},{"key":"752_CR32","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1162\/NETN_a_00018","volume":"1","author":"KJ Friston","year":"2017","unstructured":"Friston, K. J., Parr, T. & de Vries, B. The graphical brain: belief propagation and active inference. Net. Neurosci. 1, 381\u2013414 (2017).","journal-title":"Net. Neurosci."},{"key":"752_CR33","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.tics.2018.01.009","volume":"22","author":"G Pezzulo","year":"2018","unstructured":"Pezzulo, G., Rigoli, F. & Friston, K. J. Hierarchical active inference: a theory of motivated control. Trends Cogn. Sci. 22, 294\u2013306 (2018).","journal-title":"Trends Cogn. Sci."},{"key":"752_CR34","doi-asserted-by":"crossref","unstructured":"Feldman, A. G. & Levin, M. F. in Progress in Motor Control (ed. Sternad, D.) 699\u2013726 (Springer, 2009).","DOI":"10.1007\/978-0-387-77064-2_38"},{"key":"752_CR35","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1016\/j.cognition.2008.08.011","volume":"113","author":"MM Botvinick","year":"2009","unstructured":"Botvinick, M. M., Niv, Y. & Barto, A. G. Hierarchically organized behavior and its neural foundations: a reinforcement learning perspective. Cognition 113, 262\u2013280 (2009).","journal-title":"Cognition"},{"key":"752_CR36","doi-asserted-by":"publisher","first-page":"552","DOI":"10.3390\/e22050552","volume":"22","author":"T Parr","year":"2020","unstructured":"Parr, T., Sajid, N. & Friston, K. J. Modules or mean-fields? Entropy 22, 552 (2020).","journal-title":"Entropy"},{"key":"752_CR37","doi-asserted-by":"publisher","unstructured":"Lanillos, P. et al. Active inference in robotics and artificial agents: survey and challenges. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2112.01871 (2021).","DOI":"10.48550\/arXiv.2112.01871"},{"key":"752_CR38","doi-asserted-by":"publisher","first-page":"1799","DOI":"10.1093\/brain\/awab085","volume":"144","author":"T Parr","year":"2021","unstructured":"Parr, T., Limanowski, J., Rawji, V. & Friston, K. The computational neurology of movement under active inference. Brain 144, 1799\u20131818 (2021).","journal-title":"Brain"},{"key":"752_CR39","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.conb.2017.08.010","volume":"46","author":"L Aitchison","year":"2017","unstructured":"Aitchison, L. & Lengyel, M. With or without you: predictive coding and Bayesian inference in the brain. Curr. Opin. Neurobiol. 46, 219\u2013227 (2017).","journal-title":"Curr. Opin. Neurobiol."},{"key":"752_CR40","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s00221-008-1667-3","volume":"194","author":"AG Feldman","year":"2009","unstructured":"Feldman, A. G. New insights into action\u2013perception coupling. Exp. Brain Res. 194, 39\u201358 (2009).","journal-title":"Exp. Brain Res."},{"key":"752_CR41","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s00429-012-0475-5","volume":"218","author":"RA Adams","year":"2013","unstructured":"Adams, R. A., Shipp, S. & Friston, K. J. Predictions not commands: active inference in the motor system. Brain Struct. Funct. 218, 611\u2013643 (2013).","journal-title":"Brain Struct. Funct."},{"key":"752_CR42","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1016\/j.tins.2013.09.004","volume":"36","author":"S Shipp","year":"2013","unstructured":"Shipp, S., Adams, R. A. & Friston, K. J. Reflections on agranular architecture: predictive coding in the motor cortex. Trends Neurosci. 36, 706\u2013716 (2013).","journal-title":"Trends Neurosci."},{"key":"752_CR43","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1080\/00222895.1993.9942050","volume":"25","author":"RC Miall","year":"1993","unstructured":"Miall, R. C., Weir, D. J., Wolpert, D. M. & Stein, J. F. Is the cerebellum a smith predictor? J. Mot. Behav. 25, 203\u2013216 (1993).","journal-title":"J. Mot. Behav."},{"key":"752_CR44","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s12311-013-0511-x","volume":"13","author":"LF Koziol","year":"2014","unstructured":"Koziol, L. F. et al. Consensus paper: the cerebellum\u2019s role in movement and cognition. Cerebellum 13, 151\u2013177 (2014).","journal-title":"Cerebellum"},{"key":"752_CR45","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/B978-0-444-63356-9.00010-8","volume":"210","author":"N Ramnani","year":"2014","unstructured":"Ramnani, N. Automatic and controlled processing in the corticocerebellar system. Prog. Brain Res. 210, 255\u2013285 (2014).","journal-title":"Prog. Brain Res."},{"key":"752_CR46","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1126\/science.1857964","volume":"253","author":"E Bizzi","year":"1991","unstructured":"Bizzi, E., Mussa-Ivaldi, F. A. & Giszter, S. Computations underlying the execution of movement: a biological perspective. Science 253, 287\u2013291 (1991).","journal-title":"Science"},{"key":"752_CR47","unstructured":"Atkeson, C. G. et al. 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids) (IEEE, 2015)."},{"key":"752_CR48","doi-asserted-by":"publisher","first-page":"970890","DOI":"10.3389\/frobt.2022.970890","volume":"9","author":"K Yuan","year":"2022","unstructured":"Yuan, K. & Li, Z. Multi-expert synthesis for versatile locomotion and manipulation skills. Front. Robot. AI 9, 970890 (2022).","journal-title":"Front. Robot. AI"},{"key":"752_CR49","doi-asserted-by":"publisher","first-page":"eabb2174","DOI":"10.1126\/scirobotics.abb2174","volume":"5","author":"C Yang","year":"2020","unstructured":"Yang, C., Yuan, K., Zhu, Q., Yu, W. & Li, Z. Multi-expert learning of adaptive legged locomotion. Sci. Robot. 5, eabb2174 (2020).","journal-title":"Sci. Robot."},{"key":"752_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/NECO_a_00912","volume":"29","author":"K Friston","year":"2017","unstructured":"Friston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P. & Pezzulo, G. Active inference: a process theory. Neural Comput. 29, 1\u201349 (2017).","journal-title":"Neural Comput."},{"key":"752_CR51","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1162\/neco_a_01357","volume":"33","author":"N Sajid","year":"2021","unstructured":"Sajid, N., Ball, P. J., Parr, T. & Friston, K. J. Active inference: demystified and compared. Neural Comput. 33, 674\u2013712 (2021).","journal-title":"Neural Comput."},{"key":"752_CR52","doi-asserted-by":"publisher","first-page":"102447","DOI":"10.1016\/j.jmp.2020.102447","volume":"99","author":"L Da Costa","year":"2020","unstructured":"Da Costa, L. et al. Active inference on discrete state-spaces: A synthesis. J. Math. Psychol. 99, 102447 (2020).","journal-title":"J. Math. Psychol."},{"key":"752_CR53","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-87005-4","volume":"11","author":"N Sajid","year":"2021","unstructured":"Sajid, N. et al. Simulating lesion-dependent functional recovery mechanisms. Sci. Rep. 11, 7475 (2021).","journal-title":"Sci. Rep."},{"key":"752_CR54","doi-asserted-by":"publisher","first-page":"1303","DOI":"10.1007\/s00415-009-5118-2","volume":"256","author":"CJG Lang","year":"2009","unstructured":"Lang, C. J. G., Kneidl, O., Hielscher-Fastabend, M. & Heckmann, J. G. Voice recognition in aphasic and non-aphasic stroke patients. J. Neurol. 256, 1303\u20131306 (2009).","journal-title":"J. Neurol."},{"key":"752_CR55","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Proc. 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (Association for Computing Machinery, 2019)."},{"key":"752_CR56","doi-asserted-by":"publisher","first-page":"2268","DOI":"10.1109\/LRA.2019.2901308","volume":"4","author":"K Yuan","year":"2019","unstructured":"Yuan, K., Chatzinikolaidis, I. & Li, Z. Bayesian optimization for whole-body control of high-degree-of-freedom robots through reduction of dimensionality. IEEE Robot. Autom. Lett. 4, 2268\u20132275 (2019).","journal-title":"IEEE Robot. Autom. Lett."},{"key":"752_CR57","unstructured":"Hasselt, H. Double Q-learning. In Advances in Neural Information Processing Systems (eds Lafferty, J. et al.) 2613\u20132621 (Curran Associates Inc., 2010)."},{"key":"752_CR58","doi-asserted-by":"crossref","unstructured":"Siciliano, B., Khatib, O. & Kr\u00f6ger, T. Springer Handbook of Robotics, Vol. 200 (Springer, 2008).","DOI":"10.1007\/978-3-540-30301-5"},{"key":"752_CR59","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/MRA.2020.2980547","volume":"27","author":"K Yuan","year":"2020","unstructured":"Yuan, K., McGreavy, C., Yang, C., Wolfslag, W. & Li, Z. Decoding motor skills of artificial intelligence and human policies: a study on humanoid and human balance control. IEEE Robot. Autom. Mag. 27, 87\u2013101 (2020).","journal-title":"IEEE Robot. Autom. Mag."},{"key":"752_CR60","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P. & Levine, S. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In Proc. 35th International Conference on Machine Learning (eds Dy, J. & Krause, A.) 1861\u20131870 (PMLR, 2018)."},{"key":"752_CR61","doi-asserted-by":"publisher","first-page":"2610","DOI":"10.1109\/LRA.2020.2972879","volume":"5","author":"C Yang","year":"2020","unstructured":"Yang, C., Yuan, K., Heng, S., Komura, T. & Li, Z. Learning natural locomotion behaviors for humanoid robots using human bias. IEEE Rob. Autom. Lett. 5, 2610\u20132617 (2020).","journal-title":"IEEE Rob. Autom. Lett."},{"key":"752_CR62","unstructured":"McGreavy, C. et al. 2020 IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2020)."}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00752-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00752-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00752-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T15:08:30Z","timestamp":1702912110000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00752-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,2]]},"references-count":62,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["752"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00752-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-965852\/v1","asserted-by":"object"}]},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,2]]},"assertion":[{"value":"12 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}