{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,21]],"date-time":"2026-11-21T17:39:23Z","timestamp":1795282763962,"version":"4.10.3"},"reference-count":240,"publisher":"Emerald","issue":"1-2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,3,27]]},"abstract":"<jats:p>As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it. This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning. This work provides an introduction to imitation learning. It covers the underlying assumptions, approaches, and how they relate; the rich set of algorithms developed to tackle the problem; and advice on effective tools and implementation.<\/jats:p>\n                  <jats:p>We intend this paper to serve two audiences. First, we want to familiarize machine learning experts with the challenges of imitation learning, particularly those arising in robotics, and the interesting theoretical and practical distinctions between it and more familiar frameworks like statistical supervised learning theory and reinforcement learning. Second, we want to give roboticists and experts in applied artificial intelligence a broader appreciation for the frameworks and tools available for imitation learning.<\/jats:p>\n                  <jats:p>We organize our work by dividing imitation learning into directly replicating desired behavior (sometimes called behavioral cloning [Bain and Sammut, 1996]) and learning the hidden objectives of the desired behavior from demonstrations (called inverse optimal control [Kalman, 1964] or inverse reinforcement learning [Russell, 1998]). In addition to method analysis, we discuss the design decisions a practitioner must make when selecting an imitation learning approach. Moreover, application examples\u2014such as robots that play table tennis Kober and Peters, 2009 and programs that play the game of Go Silver et al. 2016\u2014illustrate the properties and motivations behind different forms of imitation learning. We conclude by presenting a set of open questions and point towards possible future research directions.<\/jats:p>","DOI":"10.1561\/2300000053","type":"journal-article","created":{"date-parts":[[2018,3,27]],"date-time":"2018-03-27T05:20:13Z","timestamp":1522128013000},"page":"1-179","source":"Crossref","is-referenced-by-count":342,"title":["An Algorithmic Perspective on Imitation Learning"],"prefix":"10.1108","volume":"7","author":[{"given":"Takayuki","family":"Osa","sequence":"first","affiliation":[{"name":"University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joni","family":"Pajarinen","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Darmstadt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerhard","family":"Neumann","sequence":"additional","affiliation":[{"name":"University of Lincoln"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J. Andrew","family":"Bagnell","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pieter","family":"Abbeel","sequence":"additional","affiliation":[{"name":"University of California, Berkeley"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Peters","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Darmstadt"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"140","published-online":{"date-parts":[[2018,3,27]]},"reference":[{"key":"2026040113104679600_ref001","doi-asserted-by":"crossref","DOI":"10.1145\/1015330.1015430","article-title":"Apprenticeship learning via inverse reinforcement learning","volume-title":"Proceedings of the international conference on Machine learning (ICML)","author":"Abbeel","year":"2004"},{"issue":"13","key":"2026040113104679600_ref002","doi-asserted-by":"crossref","first-page":"1608","DOI":"10.1177\/0278364910371999","article-title":"Autonomous helicopter aerobatics through apprenticeship learning","volume":"29","author":"Abbeel","year":"2010","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref003","doi-asserted-by":"crossref","DOI":"10.1007\/978-4-431-55978-8","volume-title":"Information Geometry and Its Applications","author":"Amari","year":"2016"},{"key":"2026040113104679600_ref004","first-page":"2831","article-title":"Interaction primitives for human-robot cooperation tasks","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Ben Amor","year":"2014"},{"key":"2026040113104679600_ref005","volume-title":"Optimal Control: Linear Quadratic Methods","author":"Anderson","year":"1990"},{"key":"2026040113104679600_ref006","doi-asserted-by":"crossref","DOI":"10.1109\/IROS.2016.7759596","article-title":"Optimal control and inverse optimal control by distribution matching","volume-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Arenz","year":"2016"},{"issue":"5","key":"2026040113104679600_ref007","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","article-title":"A survey of robot learning from demonstration","volume":"57","author":"Argall","year":"2009","journal-title":"Robotics and Autonomous Systems"},{"key":"2026040113104679600_ref008","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Arjovsky","year":"2017"},{"key":"2026040113104679600_ref009","first-page":"12","article-title":"Robot learning from demonstration","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Atkeson","year":"1997"},{"key":"2026040113104679600_ref010","doi-asserted-by":"crossref","unstructured":"C. G.\n              Atkeson\n            , Andrew W.Moore, and StefanSchaal. Locally weighted learning for control. Artificial Intelligence Review, 11(1):75\u2013113, 1997. ISSN 1573-7462. URLhttp:\/\/dx.doi.org\/10.1023\/A:1006511328852.","DOI":"10.1023\/A:1006511328852"},{"key":"2026040113104679600_ref011","author":"Bagnell","year":"2015"},{"key":"2026040113104679600_ref012","first-page":"103","article-title":"A framework for behavioural cloning","volume":"15","author":"Bain","year":"1996","journal-title":"Machine Intelligence"},{"issue":"3","key":"2026040113104679600_ref013","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.cognition.2009.07.005","article-title":"Action understanding as inverse planning","volume":"113","author":"Baker","year":"2009","journal-title":"Cognition"},{"key":"2026040113104679600_ref014","volume-title":"Predicting Structured Data (Neural Information Processing)","author":"BakIr","year":"2007"},{"key":"2026040113104679600_ref015","article-title":"End-to-end differentiable adversarial imitation learning","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Baram","year":"2017"},{"key":"2026040113104679600_ref016","doi-asserted-by":"crossref","DOI":"10.4249\/scholarpedia.3824","article-title":"Learning by demonstration","author":"Billard","year":"2013","journal-title":"Scholarpedia"},{"key":"2026040113104679600_ref017","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1007\/978-3-540-30301-5_60","volume-title":"Springer handbook of robotics","author":"Billard","year":"2008"},{"key":"2026040113104679600_ref018","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1007\/978-3-319-32552-1_74","volume-title":"Handbook of robotics","author":"Billard","year":"2016"},{"key":"2026040113104679600_ref019","volume-title":"Pattern recognition and machine learning","author":"Bishop","year":"2006"},{"key":"2026040113104679600_ref020","first-page":"4911","article-title":"Infinite time horizon maximum causal entropy inverse reinforcement learning","volume-title":"Proceedings of the IEEE Conference on Decision and Control (CDC)","author":"Bloem","year":"2014"},{"key":"2026040113104679600_ref021","first-page":"173","article-title":"Multi-robot inverse reinforcement learning under occlusion with interactions","volume-title":"Proceedings of the International Conference on Autonomous Agents & Multiagent Systems (AAMAS)","author":"Bogert","year":"2014"},{"key":"2026040113104679600_ref022","first-page":"1867","article-title":"Toward estimating others transition models under occlusion for multi-robot irl","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","author":"Bogert","year":"2015"},{"key":"2026040113104679600_ref023","first-page":"1034","article-title":"Expectation-maximization for inverse reinforcement learning with hidden data","volume-title":"Proceedings of the International Conference on Autonomous Agents & Multiagent Systems (AAMAS)","author":"Bogert","year":"2016"},{"key":"2026040113104679600_ref024","article-title":"Relative entropy inverse reinforcement learning","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTAT)","author":"Boularias","year":"2011"},{"key":"2026040113104679600_ref025","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/978-3-642-33486-3_15","article-title":"Structured apprenticeship learning","volume-title":"European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD)","author":"Boularias","year":"2012"},{"key":"2026040113104679600_ref026","volume-title":"Learning in modular systems","author":"Bradley","year":"2010"},{"key":"2026040113104679600_ref027","article-title":"Robot learning with task-parameterized generative models","author":"Calinon","year":"2015","journal-title":"In Proceedings of International Symposium on Robotics Research (ISRR)"},{"issue":"1","key":"2026040113104679600_ref028","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11370-015-0187-9","article-title":"A tutorial on task-parameterized movement learning and retrieval","volume":"9","author":"Calinon","year":"2016","journal-title":"Intelligent Service Robotics (Springer),"},{"key":"2026040113104679600_ref029","first-page":"255","article-title":"Incremental learning of gestures by imitation in a humanoid robot","volume-title":"Proceedings of the ACM\/IEEE International Conference on Human-Robot Interaction (HRI)","author":"Calinon","year":"2007"},{"issue":"15","key":"2026040113104679600_ref030","doi-asserted-by":"crossref","first-page":"20592076","DOI":"10.1163\/016918609X12529294461843","article-title":"Statistical learning by imitation of competing constraints in joint space and task space","volume":"23","author":"Calinon","year":"2009","journal-title":"Advanced Robotics"},{"issue":"2","key":"2026040113104679600_ref031","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1109\/TSMCB.2006.886952","article-title":"On learning, representing and generalizing a task in a humanoid robot","volume":"37","author":"Calinon","year":"2007","journal-title":"IEEE Transactions on Systems, Man and Cybernetics, Part B"},{"issue":"2","key":"2026040113104679600_ref032","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1109\/MRA.2010.936947","article-title":"Learning and reproduction of gestures by imitation","volume":"17","author":"Calinon","year":"2010","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"2026040113104679600_ref033","first-page":"3413","article-title":"Encoding the time and space constraints of a task in explicit-duration hidden Markov model","volume-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Calinon","year":"2011"},{"issue":"2","key":"2026040113104679600_ref034","article-title":"Behavioral cloning: A correction","volume":"16","author":"Camacho","year":"1995","journal-title":"AI MAGAZINE"},{"key":"2026040113104679600_ref035","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1177\/0278364908097884","article-title":"A hybrid approach to intricate motion, manipulation and task planning","volume":"28","author":"Cambon","year":"2009","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref036","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4684-8586-8_18","article-title":"Man-machine co-operation on a learning task","author":"Chambers","year":"1969","journal-title":"Computer Graphics: Techniques and Applications"},{"key":"2026040113104679600_ref037","unstructured":"K.\n              Chang\n            , A.Krishnamurthy, A.Agarwal, H.Daum\u00e9III, and J.Langford. Learning to search better than your teacher. In Proceedings of the International Conference on Machine Learning (ICML), 2015. URLhttp:\/\/hal3.name\/docs\/#daume15lols"},{"key":"2026040113104679600_ref038","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.2584","article-title":"Interactive policy learning through confidencebased autonomy","volume":"34","author":"Chernova","year":"2009","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"Mar","key":"2026040113104679600_ref039","first-page":"691","article-title":"Inverse reinforcement learning in partially observable environments","volume":"12","author":"Choi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2026040113104679600_ref040","first-page":"1989","article-title":"Map inference for bayesian inverse reinforcement learning","author":"Choi","year":"2011","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"issue":"4","key":"2026040113104679600_ref041","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1109\/TCYB.2014.2336867","article-title":"Hierarchical bayesian inverse reinforcement learning","volume":"45","author":"Choi","year":"2015","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"2","key":"2026040113104679600_ref042","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/S1077-3142(03)00009-2","article-title":"A new point matching algorithm for non-rigid registration","volume":"89","author":"Chui","year":"2003","journal-title":"Computer Vision and Image Understanding"},{"key":"2026040113104679600_ref043","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","author":"Chung","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref044","doi-asserted-by":"crossref","DOI":"10.1145\/1390156.1390175","article-title":"Learning for control from multiple demonstrations","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Coates","year":"2008"},{"issue":"3","key":"2026040113104679600_ref045","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Machine Learning"},{"issue":"3","key":"2026040113104679600_ref046","doi-asserted-by":"crossref","first-page":"389405","DOI":"10.1007\/s10514-015-9454-z","article-title":"Active reward learning with a novel acquisition function","volume":"39","author":"Daniel","year":"2015","journal-title":"Autonomous Robots"},{"key":"2026040113104679600_ref047","article-title":"Advances in structured prediction","volume-title":"Tutorials in the International Conference on Machine Learning (ICML)","author":"Daum\u00e9","year":"2015"},{"key":"2026040113104679600_ref048","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1007\/s10994-009-5106-x","article-title":"Search-based structured prediction","volume":"75","author":"Daum\u00e9","year":"2009","journal-title":"Machine Learning"},{"key":"2026040113104679600_ref049","first-page":"150","article-title":"Model based bayesian exploration","volume-title":"Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence","author":"Dearden","year":"1999"},{"key":"2026040113104679600_ref050","article-title":"Efficient reinforcement learning using gaussian processes","author":"Deisenroth","year":"2010","journal-title":"KIT Scientific Publishing"},{"key":"2026040113104679600_ref051","article-title":"PILCO: A model-based and dataefficient approach to policy search","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Deisenroth","year":"2011"},{"issue":"2","key":"2026040113104679600_ref052","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1109\/TPAMI.2013.218","article-title":"Gaussian processes for dataefficient learning in robotics and control","volume":"37","author":"Deisenroth","year":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1-2","key":"2026040113104679600_ref053","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"Deisenroth","journal-title":"Foundations and Trends in Robotics"},{"key":"2026040113104679600_ref054","first-page":"3876","article-title":"Multi-task policy search for robotics","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Deisenroth","year":"2014"},{"issue":"5","key":"2026040113104679600_ref055","doi-asserted-by":"crossref","first-page":"2581","DOI":"10.1109\/TMECH.2015.2510165","article-title":"Learning compliant movement primitives through demonstration and statistical generalization","volume":"21","author":"Deni\u0161a","year":"2016","journal-title":"IEEE\/ASME Transactions on Mechatronics"},{"key":"2026040113104679600_ref056","first-page":"1","article-title":"Direct loss minimization inverse optimal control","author":"Doerr","year":"2015","journal-title":"Proceedings of Robotics: Science and Systems (R :SS)"},{"key":"2026040113104679600_ref057","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.artint.2012.04.006","article-title":"Reinforcement learning with limited reinforcement: Using bayes risk for active learning in pomdps","volume":"187","author":"Doshi-Velez","year":"2012","journal-title":"Artificial Intelligence"},{"issue":"2","key":"2026040113104679600_ref058","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1109\/TPAMI.2013.191","article-title":"Bayesian nonparametric methods for partially-observable reinforcement learning","volume":"37","author":"Doshi-Velez","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026040113104679600_ref059","first-page":"2339","article-title":"Movement primitives via optimization","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Dragan","year":"2015"},{"key":"2026040113104679600_ref060","unstructured":"Y.\n              Duan\n            , M.Andrychowicz, B. C.Stadie, J.Ho, J.Schneider, I.Sutskever, P.Abbeel, and W.Zaremba. One-shot imitation learning. arXiv preprint, abs\/1703.07326, 2017. URL http:\/\/arxiv.org\/abs\/1703.07326."},{"key":"2026040113104679600_ref061","first-page":"123","article-title":"Maximum entropy distribution estimation with generalized regularization","volume-title":"Proceedings of the International Conference on Computational Learning Theory (COLT)","author":"Dud\u00edk","year":"2006"},{"key":"2026040113104679600_ref062","article-title":"Inverse optimal control with linearly-solvable mdps","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Dvijotham","year":"2010"},{"issue":"3","key":"2026040113104679600_ref063","doi-asserted-by":"crossref","DOI":"10.5772\/5611","article-title":"Robot learning from demonstration: a task-level planning approach","volume":"5","author":"Ekvall","year":"2008","journal-title":"International Journal of Advanced Robotic Systems"},{"key":"2026040113104679600_ref064","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1177\/1059712313491614","article-title":"Probabilistic modelbased imitation learning","volume":"21","author":"Englert","year":"2013","journal-title":"Adaptive Behavior"},{"key":"2026040113104679600_ref065","first-page":"1535","article-title":"Learning multiple collaborative tasks with a mixture of interaction primitives","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Ewerton","year":"2015"},{"key":"2026040113104679600_ref066","doi-asserted-by":"crossref","DOI":"10.1109\/HUMANOIDS.2016.7803300","article-title":"Incremental imitation learning of context-dependent motor skills","volume-title":"Proceedings of IEEE international Conference on Humanoid Robots (HUMANOIDS)","author":"Ewerton","year":"2016"},{"issue":"4","key":"2026040113104679600_ref067","first-page":"507","article-title":"On-line inference for multiple changepoint problems","volume":"69","author":"Fearnhead","year":"2007","journal-title":"Journal of the Royal Statistical Society: Series B"},{"key":"2026040113104679600_ref068","article-title":"A connection between generative adversarial networks, inverse reinforcement learning, and energybased models","author":"Finn","year":"2016","journal-title":"arXiv 1611.03852"},{"key":"2026040113104679600_ref069","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Finn","year":"2016"},{"key":"2026040113104679600_ref070","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Finn","year":"2017"},{"key":"2026040113104679600_ref071","article-title":"One-shot visual imitation learning via meta-learning","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","author":"Finn","year":"2017"},{"key":"2026040113104679600_ref072","article-title":"Sharing features among dynamical systems with beta processes","author":"Fox","year":"2009","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"issue":"4","key":"2026040113104679600_ref073","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1109\/TRO.2014.2304775","article-title":"Coupling movement primitives: Interaction with the environment and bimanual tasks","volume":"30","author":"Gams","year":"2014","journal-title":"IEEE Transactions on Robotics"},{"key":"2026040113104679600_ref074","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref075","first-page":"66456649","article-title":"Speech recognition with deep recurrent neural networks","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASPP)","author":"Graves","year":"2013"},{"issue":"1","key":"2026040113104679600_ref076","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1177\/0278364910376251","article-title":"Learning non-linear multivariate dynamics of motion in robotic manipulators","volume":"30","author":"Gribovskaya","year":"2011","journal-title":"International Journal of Robotics Research"},{"key":"2026040113104679600_ref077","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/978-3-642-00616-6_7","volume-title":"Creating brain-like intelligence: From basic principles to complex intelligent systems","author":"Grimes","year":"2009"},{"key":"2026040113104679600_ref078","article-title":"Dynamic imitation in a humanoid robot through nonparametric probabilistic inference","author":"Grimes","year":"2006","journal-title":"Proceedings of Robotics: Science and Systems (R:SS)"},{"key":"2026040113104679600_ref079","article-title":"Learning nonparametric models for probabilistic imitation","author":"Grimes","year":"2006","journal-title":"Advances in Neural Information Processing Systems 19"},{"key":"2026040113104679600_ref080","article-title":"Boosted backpropagation learning for training deep modular networks","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Grubb","year":"2010"},{"key":"2026040113104679600_ref081","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","volume-title":"Proceedings of the Internatinal Conference on Learning Representatinos (ICLR)","author":"Gupta","year":"2017"},{"key":"2026040113104679600_ref082","article-title":"Cooperative inverse reinforcement learning","author":"Hadfield-Menell","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"issue":"10","key":"2026040113104679600_ref083","doi-asserted-by":"crossref","first-page":"2201","DOI":"10.1162\/089976601750541778","article-title":"Mosaic model for sensorimotor learning and control","volume":"13","author":"Haruno","year":"2001","journal-title":"Neural Computation"},{"key":"2026040113104679600_ref084","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2017.7989183","article-title":"Supervisory teleoperation with online learning and optimal control","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Havoutis","year":"2017"},{"issue":"3-4","key":"2026040113104679600_ref085","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1561\/2400000013","article-title":"Introduction to online convex optimization","volume":"2","author":"Hazan","year":"2016","journal-title":"Foundations and Trends \u00ae\u00b0 in Optimization"},{"key":"2026040113104679600_ref086","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11775","article-title":"Optiongan: Learning joint reward-policy options using generative adversarial inverse reinforcement learning","volume-title":"In the Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Henderson","year":"2018"},{"issue":"8","key":"2026040113104679600_ref087","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1162\/089976602760128018","article-title":"Training products of experts by minimizing contrastive divergence","volume":"14","author":"Hinton","year":"2002","journal-title":"Neural Computation"},{"key":"2026040113104679600_ref088","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"Adances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref089","article-title":"Model-free imitation learning with policy optimization","volume-title":"Proceedings of the International Conference on International Conference on Machine Learning (ICML)","author":"Ho","year":"2016"},{"issue":"8","key":"2026040113104679600_ref090","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural computation"},{"key":"2026040113104679600_ref091","first-page":"2587","article-title":"Biologically-inspired dynamical systems for movement generation: Automatic real-time goal adaptation and obstacle avoidance","volume-title":"Proceedings of IEEE International Conference on Robotics and Automation (ICRA)","author":"Hoffmann","year":"2009"},{"key":"2026040113104679600_ref092","doi-asserted-by":"crossref","DOI":"10.1109\/IROS.2015.7353475","article-title":"Leveraging appearance priors in non-rigid registration with applications to manipulation of deformable objects","volume-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Huang","year":"2015"},{"key":"2026040113104679600_ref093","article-title":"Learning attractor landscapes for learning motor primitives","author":"Ijspeert","year":"2002","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref094","first-page":"1398","article-title":"Movement imitation with nonlinear dynamical systems in humanoid robots","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Ijspeert","year":"2002"},{"issue":"2","key":"2026040113104679600_ref095","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1162\/NECO_a_00393","article-title":"Dynamical movement primitives: Learning attractor models for motor behaviors","volume":"25","author":"Ijspeert","year":"2013","journal-title":"Neural Computation"},{"key":"2026040113104679600_ref096","doi-asserted-by":"crossref","DOI":"10.1177\/0278364904042199","article-title":"Embodied symbol emergence based on mimesis theory","author":"Inamura","year":"2004","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref097","doi-asserted-by":"crossref","DOI":"10.1162\/neco.1991.3.1.79","article-title":"Adaptive mixtures of local experts","author":"Jacobs","year":"1991","journal-title":"Neural Computation"},{"key":"2026040113104679600_ref098","doi-asserted-by":"crossref","DOI":"10.1177\/0278364915581193","article-title":"Learning preferences for manipulation tasks from online coactive feedback","author":"Jain","year":"2015","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref099","doi-asserted-by":"crossref","unstructured":"E. T.\n              Jaynes\n            \n          . Information theory and statistical mechanics. Physical Review, 106:620\u2013630, May1957. URLhttp:\/\/link.aps.org\/doi\/10. 1103\/PhysRev.106.620","DOI":"10.1103\/PhysRev.106.620"},{"key":"2026040113104679600_ref100","first-page":"1331","article-title":"Learning objective functions for manipulation","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Kalakrishnan","year":"2013"},{"issue":"1","key":"2026040113104679600_ref101","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1115\/1.3653115","article-title":"When is a linear control system optimal?","volume":"86","author":"Kalman","year":"1964","journal-title":"Trans. ASME, J. Basic Eng., Ser. D."},{"issue":"4","key":"2026040113104679600_ref102","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1109\/70.246054","article-title":"Toward automatic robot instruction from perception-recognizing a grasp from observation","volume":"9","author":"Kang","year":"1993","journal-title":"IEEE Transactions on Robotics and Automation"},{"key":"2026040113104679600_ref103","first-page":"3128","article-title":"Deep visual-semantic alignments for generating image descriptions","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Karpathy","year":"2015"},{"key":"2026040113104679600_ref104","volume-title":"Nonlinear systems","author":"Khalil","year":"1996"},{"issue":"5","key":"2026040113104679600_ref105","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1109\/TRO.2011.2159412","article-title":"Learning stable nonlinear dynamical systems with gaussian mixture models","volume":"27","author":"Khansari-Zadeh","year":"2011","journal-title":"IEEE Transactions on Robotics"},{"issue":"6","key":"2026040113104679600_ref106","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1016\/j.robot.2014.03.001","article-title":"Learning control lyapunov function to ensure stability of dynamical system-based robot reaching motions","volume":"62","author":"Khansari-Zadeh","year":"2014","journal-title":"Robotics and Autonomous Systems"},{"issue":"5","key":"2026040113104679600_ref107","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1109\/TRO.2014.2316022","article-title":"Catching objects in flight","volume":"30","author":"Kim","year":"2014","journal-title":"IEEE Transactions on Robotics"},{"key":"2026040113104679600_ref108","first-page":"201","article-title":"Activity forecasting","volume-title":"European Conference on Computer Vision (ECCV)","author":"Kitani","year":"2012"},{"key":"2026040113104679600_ref109","first-page":"2112","article-title":"Learning motor primitives for robotics","volume-title":"Proceedings of IEEE International Conference on Robotics and Automation","author":"Kober","year":"2009"},{"key":"2026040113104679600_ref110","first-page":"834","article-title":"Learning perceptual coupling for motor primitives","volume-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robot Systems (IROS)","author":"Kober","year":"2008"},{"key":"2026040113104679600_ref111","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1177\/0278364913495721","article-title":"Reinforcement learning in robotics: A survey","volume":"32","author":"Kober","year":"2013","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref112","first-page":"793","article-title":"A dynamic hmm for on-line segmentation of sequential data","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NIPS)","author":"Kohlmorgen","year":"2001"},{"key":"2026040113104679600_ref113","article-title":"Hierarchical apprenticeship learning with application to quadruped locomotion","author":"Kolter","year":"2008","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"issue":"3","key":"2026040113104679600_ref114","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1177\/0278364911428653","article-title":"Robot learning from demonstration by constructing skill trees","volume":"31","author":"Konidaris","year":"2011","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref115","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v28i1.9004","article-title":"Constructing symbolic representations for high-level planning","volume-title":"Proceedings of the Twenty-Eighth Conference on Artificial Intelligence (AAAI)","author":"Konidaris","year":"2014"},{"key":"2026040113104679600_ref116","unstructured":"S.\n              Krishnan\n            , A.Garg, R.Liaw, L.Miller, F. T.Pokorny, and K.Goldberg. HIRL: hierarchical inverse reinforcement learning for long-horizon tasks with delayed rewards. CoRR, abs\/604.06508, 2016. URL http:\/\/arxiv.org\/abs\/1604.06508."},{"key":"2026040113104679600_ref117","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2014.6907441","article-title":"Learning to predict phases of manipulation tasks as hidden states","volume-title":"Proceedings of IEEE International Conference on Robotics and Automation (ICRA)","author":"Kroemer","year":"2014"},{"key":"2026040113104679600_ref118","first-page":"1503","article-title":"Towards learning hierarchical skills for multi-phase manipulation tasks","volume-title":"Proceedings of International Conference on Robotics and Automation (ICRA)","author":"Kroemer","year":"2015"},{"issue":"C","key":"2026040113104679600_ref119","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.robot.2015.03.010","article-title":"Incremental motion learning with locally modulated dynamical systems","volume":"70","author":"Kronander","year":"2015","journal-title":"Robotics and Autonomous Systems"},{"key":"2026040113104679600_ref120","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-48995-6_30","article-title":"Inverse game theory: Learning utilities in succinct games","volume-title":"Proceedings of the International Conference on Web and Internet Economics","author":"Kuleshov","year":"2015"},{"key":"2026040113104679600_ref121","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1177\/0278364908091153","article-title":"Incremental learning, clustering and hierarchy formation of whole body motion patterns using adaptive hidden markov chains","volume":"27","author":"Kuli\u0107","year":"2008","journal-title":"The International Journal of Robotics Research"},{"issue":"1","key":"2026040113104679600_ref122","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"The Annals of Mathematical Statistics"},{"issue":"6","key":"2026040113104679600_ref123","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1109\/70.338535","article-title":"Learning by watching: extracting reusable task knowledge from visual observation of human performance","volume":"10","author":"Kuniyoshi","year":"1994","journal-title":"IEEE Transactions on Robotics and Automation"},{"key":"2026040113104679600_ref124","article-title":"Conditional random fields: probabilistic models for segmenting and labeling sequence data","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Lafferty","year":"2001"},{"issue":"14","key":"2026040113104679600_ref125","doi-asserted-by":"crossref","first-page":"1726","DOI":"10.1177\/0278364914545811","article-title":"Efficiently combining task and motion planning using geometric constraints","volume":"33","author":"Lagriffoul","year":"2014","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref126","article-title":"Iterative noise injection for scalable imitation learning","author":"Laskey","year":"2017","journal-title":"arXiv preprint"},{"key":"2026040113104679600_ref127","article-title":"Off-road obstacle avoidance through end-to-end learning","author":"LeCun","year":"2006","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref128","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2015.7138997","article-title":"Learning force-based manipulation of deformable objects from multiple demonstrations","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Lee","year":"2015"},{"key":"2026040113104679600_ref129","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2015.7139289","article-title":"A non-rigid point and normal registration algorithm with applications to learning from demonstrations","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Lee","year":"2015"},{"key":"2026040113104679600_ref130","article-title":"Mimesis model from partial observations for a humanoid robot","author":"Lee","year":"2009","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref131","doi-asserted-by":"crossref","DOI":"10.1007\/s10514-011-9234-3","article-title":"Incremental kinesthetic teaching of motion primitives using the motion refinement tube","author":"Lee","year":"2011","journal-title":"Autonomous Robots"},{"key":"2026040113104679600_ref132","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1177\/0278364910364164","article-title":"Mimetic communication model with compliant physical contact in human-humanoid interaction","volume":"29","author":"Lee","year":"2010","journal-title":"The International Journal of Robotics Research"},{"issue":"1","key":"2026040113104679600_ref133","article-title":"Open-source benchmarking for learned reaching motion generation in robotics. Paladyn","volume":"6","author":"Lemme","year":"2015","journal-title":"Journal of Behavioral Robotics"},{"key":"2026040113104679600_ref134","first-page":"1","article-title":"Biorob-arm: A quickly deployable and intrinsically safe, light- weight robot arm for service robotics applications","author":"Lens","year":"2010","journal-title":"International Symposium on Robotics (ISR)"},{"key":"2026040113104679600_ref135","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"Levine","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref136","first-page":"41","article-title":"Continuous inverse optimal control with locally optimal examples","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Levine","year":"2012"},{"key":"2026040113104679600_ref137","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","author":"Levine","year":"2011","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"issue":"1","key":"2026040113104679600_ref138","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"issue":"8","key":"2026040113104679600_ref139","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1177\/0278364917713116","article-title":"Learning movement primitive libraries through probabilistic segmentation","volume":"36","author":"Lioutikov","year":"2017","journal-title":"The International Journal of Robotics Research (IJRR)"},{"key":"2026040113104679600_ref140","article-title":"Imitation from observation: Learning to imitate behaviors from raw video via context translation","author":"Liu","year":"2017","journal-title":"arXiv"},{"key":"2026040113104679600_ref141","first-page":"31","volume-title":"Active Learning for Reward Estimation in Inverse Reinforcement Learning","author":"Lopes","year":"2009"},{"issue":"3","key":"2026040113104679600_ref142","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/2.16222","article-title":"Task-level planning of pick-and-place robot motions","volume":"22","author":"Lozano-Perez","year":"1989","journal-title":"Computer"},{"issue":"2","key":"2026040113104679600_ref143","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/s00422-014-0591-9","article-title":"Learning robotic eye-arm-hand coordination from human demonstration: a coupled dynamical systems approach","volume":"108","author":"Lukic","year":"2014","journal-title":"Biological Cybernetics"},{"key":"2026040113104679600_ref144","article-title":"Probabilistic movement primitives for coordination of multiple humanrobot collaborative tasks","author":"Maeda","year":"2016","journal-title":"Autonomous Robots"},{"key":"2026040113104679600_ref145","article-title":"Active incremental learning of robot movement primitives","volume-title":"Proceedings of the Conference on Robot Learning (CoRL)","author":"Maeda","year":"2017"},{"key":"2026040113104679600_ref146","article-title":"On the generalised distance in statistics","author":"Mahalanobis","year":"1936","journal-title":"Proceedings of the National Institute of Sciences of India"},{"key":"2026040113104679600_ref147","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.robot.2015.07.005","article-title":"Learning movement primitive attractor goals and sequential skills from kinesthetic demonstrations","volume":"74","author":"Manschitz","year":"2015","journal-title":"Robotics and Autonomous Systems"},{"issue":"2","key":"2026040113104679600_ref148","doi-asserted-by":"crossref","first-page":"130","DOI":"10.2478\/v10038-009-0012-4","article-title":"Configurations of the Graf-Boklev (V-style) ski jumper model and aerodynamic parameters in a wind tunnel","volume":"10","author":"Maryniak","year":"2009","journal-title":"Human Movement"},{"issue":"8","key":"2026040113104679600_ref149","doi-asserted-by":"crossref","first-page":"1281","DOI":"10.1016\/S0893-6080(96)00043-3","article-title":"A kendama learning robot based on bidirectional theory","volume":"9","author":"Miyamoto","year":"1996","journal-title":"Neural Networks"},{"issue":"7540","key":"2026040113104679600_ref150","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"issue":"5","key":"2026040113104679600_ref151","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1109\/TAC.1973.1100365","article-title":"Nonlinear regulator theory and an inverse optimal control problem","volume":"18","author":"Moylan","year":"1973","journal-title":"IEEE Transactions on Automatic Control"},{"key":"2026040113104679600_ref152","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1177\/0278364912472380","article-title":"Learning to select and generalize striking movements in robot table tennis","volume":"32","author":"M\u00fclling","year":"2013","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref153","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2017.7989247","article-title":"Combining self-supervised learning and imitation for vision-based rope manipulation","volume-title":"Proceedings of the International Conference on Robotics and Automation (ICRA)","author":"Nair","year":"2017"},{"issue":"8","key":"2026040113104679600_ref154","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1177\/0278364907079430","article-title":"Learning from observation paradigm: leg task models for enabling a biped humanoid robot to imitate human dances","volume":"26","author":"Nakaoka","year":"2007","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref155","first-page":"395","article-title":"Multi-agent inverse reinforcement learning","volume-title":"Proceedings of the ninth International Conference on Machine Learning and Applications (ICMLA)","author":"Natarajan","year":"2010"},{"issue":"2-3","key":"2026040113104679600_ref156","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s10994-009-5110-1","article-title":"Training parsers by inverse reinforcement learning","volume":"77","author":"Neu","year":"2009","journal-title":"Machine learning"},{"key":"2026040113104679600_ref157","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Ng","year":"2000"},{"issue":"4","key":"2026040113104679600_ref158","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/s10339-011-0404-1","article-title":"Model learning for robot control: a survey","volume":"12","author":"Nguyen-Tuong","year":"2011","journal-title":"Cognitive Processing"},{"key":"2026040113104679600_ref159","first-page":"131157","article-title":"Learning grounded finite-state representations from unstructured demonstrations","volume":"34","author":"Niekum","year":"2014","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref160","first-page":"271","article-title":"Training Generative Neural Samplers using Variational Divergence Minimization","author":"Nowozin","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref161","first-page":"2845","article-title":"Action-conditional video prediction using deep networks in atari games","author":"Oh","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"issue":"3","key":"2026040113104679600_ref162","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1109\/TRO.2014.2300212","article-title":"Toward a dancing robot with listening capability: keypose-based integration of lower-, middle-, and upper-body motions for varying music tempos","volume":"30","author":"Okamoto","year":"2014","journal-title":"IEEE Transactions on Robotics"},{"key":"2026040113104679600_ref163","article-title":"Online trajectory planning in dynamic environments for surgical task automation","author":"Osa","year":"2014","journal-title":"Proceedings of Robotics: Science and Systems (R:SS)"},{"issue":"2","key":"2026040113104679600_ref164","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1109\/LRA.2017.2653850","article-title":"Guiding trajectory optimization by demonstrated distributions","volume":"2","author":"Osa","year":"2017","journal-title":"IEEE Robotics and Automation Letters (RA-L)"},{"key":"2026040113104679600_ref165","article-title":"Online trajectory planning and force control for automation of surgical tasks","author":"Osa","year":"2017","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"2026040113104679600_ref166","article-title":"Probabilistic movement primitives","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"Paraschos","year":"2013"},{"key":"2026040113104679600_ref167","volume-title":"Computer animation: algorithms and techniques","author":"Parent","year":"2002"},{"issue":"2","key":"2026040113104679600_ref168","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.jeconom.2008.12.014","article-title":"Maximum entropy autoregressive conditional heteroskedasticity model","volume":"150","author":"Park","year":"2009","journal-title":"Journal of Econometrics"},{"key":"2026040113104679600_ref169","doi-asserted-by":"crossref","DOI":"10.1109\/ROBOT.2009.5152385","article-title":"Learning and generalization of motor skills by learning from demonstration","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"Pastor","year":"2009"},{"key":"2026040113104679600_ref170","article-title":"ALVINN: An autonomous land vehicle in a neural network","author":"Pomerleau","year":"1988","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref171","article-title":"Model-based Bayesian reinforcement learning in partially observable domains","author":"Poupart","year":"2008","journal-title":"Proceedings of the Tenth International Symposium on Artificial Intelligence and Mathematics (ISAIM)"},{"issue":"2","key":"2026040113104679600_ref172","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden markov models and selected appli- cations in speech recognition","volume":"77","author":"Rabiner","year":"1989","journal-title":"Proceedings of the IEEE"},{"key":"2026040113104679600_ref173","first-page":"688","article-title":"Learning in-contact control strategies from demonstration","volume-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Racca","year":"2016"},{"key":"2026040113104679600_ref174","article-title":"Vision-based multi-task manipulation for inexpensive robots using end-to-end learning from demonstration","author":"Rahmatizadeh","year":"2017","journal-title":"arXiv"},{"key":"2026040113104679600_ref175","first-page":"2586","article-title":"Bayesian inverse reinforcement learning","volume-title":"Proceedings of the International Joint Conference on Artifical Intelligence (IJCAI)","author":"Ramachandran","year":"2007"},{"key":"2026040113104679600_ref176","volume-title":"Gaussian processes for machine learning","author":"Rasmussen","year":"2006"},{"key":"2026040113104679600_ref177","article-title":"Boosting structured prediction for imitation learning","author":"Ratliff","year":"2006","journal-title":"Advances in Neural Information Processing Systems 19"},{"key":"2026040113104679600_ref178","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s10514-009-9121-3","article-title":"Learning to search: Functional gradient techniques for imitation learning","volume":"27","author":"Ratliff","year":"2009","journal-title":"Autonomous Robots"},{"key":"2026040113104679600_ref179","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1145\/1143844.1143936","article-title":"Maximum margin planning","volume-title":"Proceedings of the international conference on Machine learning (ICML)","author":"Ratliff","year":"2006"},{"key":"2026040113104679600_ref180","article-title":"Efficient reductions for imitation learning","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Ross","year":"2010"},{"key":"2026040113104679600_ref181","article-title":"Reinforcement and imitation learning via interactive no-regret learning","author":"Ross","year":"2014","journal-title":"Arxiv preprint"},{"key":"2026040113104679600_ref182","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"Ross","year":"2011"},{"key":"2026040113104679600_ref183","first-page":"1765","article-title":"Learning monocular reactive uav control in cluttered natural environments","volume-title":"Proceedings of IEEE International Conference on Robotics and Automation (ICRA)","author":"Ross","year":"2013"},{"key":"2026040113104679600_ref184","first-page":"1","article-title":"Learning controllers for reactive and proactive behaviors in human-robot collaboration","author":"Rozo","year":"2016","journal-title":"Frontiers in Robotics and AI"},{"key":"2026040113104679600_ref185","doi-asserted-by":"crossref","DOI":"10.1145\/279943.279964","article-title":"Learning agents for uncertain environments (extended abstract)","volume-title":"Proceedings of the Eleventh Annual Conference on Computational Learning Theory","author":"Russell","year":"1998"},{"key":"2026040113104679600_ref186","first-page":"3082","volume-title":"Handbook of Econometrics","author":"Rust","year":"1994"},{"issue":"1","key":"2026040113104679600_ref187","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","article-title":"Dynamic programming algorithm optimization for spoken word recognition","volume":"26","author":"Sakoe","year":"1978","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"2026040113104679600_ref188","first-page":"385","article-title":"Learning to fly","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Sammut","year":"1992"},{"key":"2026040113104679600_ref189","first-page":"1040","article-title":"Learning from demonstration","author":"Schaal","year":"1997","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"issue":"6","key":"2026040113104679600_ref190","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/S1364-6613(99)01327-3","article-title":"Is imitation learning the route to humanoid robots?","volume":"3","author":"Schaal","year":"1999","journal-title":"Trends in Cognitive Sciences"},{"issue":"8","key":"2026040113104679600_ref191","doi-asserted-by":"crossref","first-page":"2047","DOI":"10.1162\/089976698300016963","article-title":"Constructive incremental learning from only local information","volume":"10","author":"Schaal","year":"1998","journal-title":"Neural Computation"},{"key":"2026040113104679600_ref192","article-title":"Learning movement primitives","author":"Schaal","year":"2004","journal-title":"Proceedings of the International Symposium on Robotics Research (ISRR)"},{"key":"2026040113104679600_ref193","article-title":"Exploiting model uncertainty estimates for safe dynamic control learning","author":"Schneider","year":"1997","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"2026040113104679600_ref194","article-title":"Learning from demonstrations through the use of non-rigid registration","volume-title":"Proceedings of the International Symposium on Robotics Research (ISRR)","author":"Schulman","year":"2013"},{"key":"2026040113104679600_ref195","article-title":"Trust region policy optimization","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML)","author":"Schulman","year":"2015"},{"key":"2026040113104679600_ref196","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-89332-5","volume-title":"Basics of Applied Stochastic Processes","author":"Serfozo","year":"2009"},{"key":"2026040113104679600_ref197","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2017.XIII.050","article-title":"Unsupervised perceptual rewards for imitation learning","author":"Sermanet","year":"2017","journal-title":"Proceedings of Robotics and Science and Systems (R:SS)"},{"key":"2026040113104679600_ref198","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781107298019","volume-title":"Understanding Machine Learning: From Theory to Algorithms","author":"Shalev-Shwartz","year":"2014"},{"key":"2026040113104679600_ref199","first-page":"1060","article-title":"Inverse reinforcement learning from failure","volume-title":"Proceedings of the International Conference on Autonomous Agents & Multiagent Systems","author":"Shiarlis","year":"2016"},{"issue":"3","key":"2026040113104679600_ref200","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1016\/j.robot.2011.07.023","article-title":"Coupled dynamical system based arm-hand grasping model for learning fast adaptation strategies","volume":"60","author":"Shukla","year":"2012","journal-title":"Robotics and Autonomous Systems"},{"issue":"12","key":"2026040113104679600_ref201","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1177\/0278364910369715","article-title":"Learning from demonstration for autonomous navigation in complex unstructured terrain","volume":"29","author":"Silver","year":"2010","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref202","first-page":"200","article-title":"Active learning from demonstration for robust autonomous navigation","volume-title":"Proceedings of the International Conference on Robotics and Automation (ICRA)","author":"Silver","year":"2012"},{"key":"2026040113104679600_ref203","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/978-3-319-00065-7_26","article-title":"Learning autonomous driving styles and maneuvers from expert demonstration","author":"Silver","year":"2013","journal-title":"Experimental Robotics: The 13th International Symposium on Experimental Robotics (ISER)"},{"issue":"7587","key":"2026040113104679600_ref204","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"issue":"1","key":"2026040113104679600_ref205","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"2026040113104679600_ref206","article-title":"Third person imitation learning","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Stadie","year":"2017"},{"key":"2026040113104679600_ref207","volume-title":"Introduction to Statistical Machine Learning","author":"Sugiyama","year":"2015"},{"issue":"1","key":"2026040113104679600_ref208","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.neunet.2009.07.007","article-title":"Dimensionality reduction for density ratio estimation in high-dimensional spaces","volume":"23","author":"Sugiyama","year":"2010","journal-title":"Neural Networks"},{"key":"2026040113104679600_ref209","volume-title":"Statistical Reinforcement Learning: Modern Machine Learning Approaches","author":"Sugiyama","year":"2013"},{"key":"2026040113104679600_ref210","article-title":"Deeply aggrevated: Differentiable imitation learning for sequential prediction","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Sun","year":"2017"},{"key":"2026040113104679600_ref211","volume-title":"Reinforcement learning: An introduction","author":"Sutton","year":"1998"},{"issue":"1-2","key":"2026040113104679600_ref212","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","article-title":"Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning","volume":"112","author":"Sutton","year":"1999","journal-title":"Artificial Intelligence"},{"issue":"1","key":"2026040113104679600_ref213","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-031-01551-9","article-title":"Algorithms for reinforcement learning","volume":"4","author":"Szepesvari","year":"2010","journal-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning"},{"key":"2026040113104679600_ref214","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.1177\/0278364915587923","article-title":"Statistical mutual conversion between whole body motion primitives and linguistic sentences for human motions","volume":"34","author":"Takano","year":"2015","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref215","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.robot.2015.09.021","article-title":"Real-time unsupervised segmentation of human whole-body motion and its application to humanoid robot acquisition of motion symbols","volume":"75","author":"Takano","year":"2016","journal-title":"Robotics and Autonomous Systems"},{"key":"2026040113104679600_ref216","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.robot.2017.01.013","article-title":"Planning of goal-oriented motion from stochastic motion primitives and optimal controlling of joint torques in whole-body","volume":"91","author":"Takano","year":"2017","journal-title":"Robotics and Autonomous Systems"},{"issue":"1","key":"2026040113104679600_ref217","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1162\/NECO_a_00683","article-title":"Conditional density estimation with dimensionality reduction via squared-loss conditional entropy minimization","volume":"27","author":"Tangkaratt","year":"2015","journal-title":"Neural Computation"},{"key":"2026040113104679600_ref218","doi-asserted-by":"crossref","DOI":"10.1145\/1102351.1102464","volume-title":"Learning structured prediction models: a large margin approach","author":"Taskar","year":"2005"},{"key":"2026040113104679600_ref219","first-page":"4906","article-title":"Synthesis and stabilization of complex behaviors through online trajectory optimization","volume-title":"Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"Tassa","year":"2012"},{"issue":"3","key":"2026040113104679600_ref220","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/203330.203343","article-title":"Temporal difference learning and td-gammon","volume":"38","author":"Tesauro","year":"1995","journal-title":"Communications of the ACM"},{"key":"2026040113104679600_ref221","doi-asserted-by":"crossref","DOI":"10.1109\/ACC.2005.1469949","article-title":"A generalized iterative lqg method for locally-optimal feedback control of constrained nonlinear stochastic systems","volume-title":"Proceedings of the American Control Conference","author":"Todorov","year":"2005"},{"key":"2026040113104679600_ref222","first-page":"1453","article-title":"Large margin methods for structured and interdependent output variables","volume":"6","author":"Tsochantaridis","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"2026040113104679600_ref223","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.robot.2004.03.004","article-title":"Programming full-body movements for humanoid robots by observation","author":"Ude","year":"2004","journal-title":"Robotics and Autonomous Systems"},{"key":"2026040113104679600_ref224","first-page":"2074","article-title":"Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)","author":"van den Berg","year":"2010"},{"key":"2026040113104679600_ref225","volume-title":"Statistical learning theory","author":"Vapnik","year":"1998"},{"key":"2026040113104679600_ref226","first-page":"3024","article-title":"Improving multi-step prediction of learned time series models","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","author":"Venkatraman","year":"2015"},{"key":"2026040113104679600_ref227","article-title":"Improved learning of dynamics models for control","author":"Venkatraman","year":"2016","journal-title":"Proceedings of the International Symposium on Experimental Robotics (ISER)"},{"key":"2026040113104679600_ref228","first-page":"1079","article-title":"Locally weighted projection regression: An o(n) algorithm for incremental real time learning in high dimensional space","volume-title":"Proceedings of International Conference on Machine Learning (ICML)","author":"Vijayakumar","year":"2000"},{"key":"2026040113104679600_ref229","doi-asserted-by":"crossref","first-page":"2602","DOI":"10.1162\/089976605774320557","article-title":"Incremental online learning in high dimensions","volume":"17","author":"Vijayakumar","year":"2005","journal-title":"Neural Computation"},{"key":"2026040113104679600_ref230","first-page":"1169","article-title":"Computational rationalization: The inverse equilibrium problem","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Waugh","year":"2011"},{"key":"2026040113104679600_ref231","first-page":"1711","article-title":"Semantically conditioned lstm-based natural language generation for spoken dialogue systems","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Wen","year":"2015"},{"key":"2026040113104679600_ref232","article-title":"Pattern recognising control systems","author":"Widrow","year":"1964","journal-title":"Computer and Information Sciences"},{"key":"2026040113104679600_ref233","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","volume-title":"Reinforcement Learning: State-of-the-Art","author":"Wiering","year":"2012"},{"issue":"2","key":"2026040113104679600_ref234","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.artint.2009.11.011","article-title":"Hidden semi-markov models","volume":"174","author":"Yu","year":"2010","journal-title":"Artificial Intelligence"},{"key":"2026040113104679600_ref235","first-page":"435","article-title":"Cost-sensitive learning by costproportionate example weighting","volume-title":"Proceedings of the IEEE International Conference on Data Mining","author":"Zadrozny","year":"2003"},{"key":"2026040113104679600_ref236","volume-title":"Modeling purposeful adaptive behavior with the principle of maximum causal entropy","author":"Ziebart","year":"2010"},{"key":"2026040113104679600_ref237","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proceedings of the Twenty-Second Conference on Artificial Intelligence (AAAI)","author":"Ziebart","year":"2008"},{"issue":"4","key":"2026040113104679600_ref238","doi-asserted-by":"crossref","first-page":"1966","DOI":"10.1109\/TIT.2012.2234824","article-title":"The principle of maximum causal entropy for estimating interacting processes","volume":"59","author":"Ziebart","year":"2013","journal-title":"IEEE Transactions on Information Theory"},{"issue":"2","key":"2026040113104679600_ref239","doi-asserted-by":"crossref","first-page":"175191","DOI":"10.1177\/0278364910392608","article-title":"Optimization and learning for rough terrain legged locomotion","volume":"30","author":"Zucker","year":"2011","journal-title":"The International Journal of Robotics Research"},{"key":"2026040113104679600_ref240","doi-asserted-by":"crossref","first-page":"1164","DOI":"10.1177\/0278364913488805","article-title":"Chomp: covariant hamiltonian optimization for motion planning","volume":"32","author":"Zucker","year":"2013","journal-title":"The International Journal of Robotics Research"}],"container-title":["Foundations and Trends\u00ae in Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftrob\/article-pdf\/7\/1-2\/1\/11046343\/2300000053en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftrob\/article-pdf\/7\/1-2\/1\/11046343\/2300000053en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:22:15Z","timestamp":1777486935000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftrob\/article\/7\/1-2\/1\/1328576\/An-Algorithmic-Perspective-on-Imitation-Learning"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3,27]]},"references-count":240,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2018,3,27]]}},"URL":"https:\/\/doi.org\/10.1561\/2300000053","relation":{},"ISSN":["1935-8253","1935-8261"],"issn-type":[{"value":"1935-8253","type":"print"},{"value":"1935-8261","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3,27]]}}}