{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T19:13:47Z","timestamp":1778094827895,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2009,6,17]],"date-time":"2009-06-17T00:00:00Z","timestamp":1245196800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Auton Robot"],"published-print":{"date-parts":[[2009,7]]},"DOI":"10.1007\/s10514-009-9121-3","type":"journal-article","created":{"date-parts":[[2009,6,16]],"date-time":"2009-06-16T13:14:42Z","timestamp":1245158082000},"page":"25-53","source":"Crossref","is-referenced-by-count":127,"title":["Learning to search: Functional gradient techniques for imitation learning"],"prefix":"10.1007","volume":"27","author":[{"given":"Nathan D.","family":"Ratliff","sequence":"first","affiliation":[]},{"given":"David","family":"Silver","sequence":"additional","affiliation":[]},{"given":"J. Andrew","family":"Bagnell","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2009,6,17]]},"reference":[{"key":"9121_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., & Ng, A. Y. (2004). Apprenticeship learning via inverse reinforcement learning. In ICML \u201904: Proceedings of the twenty-first international conference on machine learning.","DOI":"10.1145\/1015330.1015430"},{"key":"9121_CR2","volume-title":"Optimal control: linear quadratic methods","author":"B. D. O. Anderson","year":"1990","unstructured":"Anderson, B. D. O., & Moore, J. B. (1990). Optimal control: linear quadratic methods. Englewood Cliffs: Prentice Hall."},{"key":"9121_CR3","doi-asserted-by":"crossref","unstructured":"Argall, B., Chernova, S., Veloso, M., & Browning, B. (2009). A survey of robot learning from demonstration. Robotics and Autonomous Systems.","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"9121_CR4","unstructured":"Atkeson, C., Schaal, S., & Moore, A. (1995). Locally weighted learning. AI Review."},{"key":"9121_CR5","volume-title":"Machine intelligence agents","author":"M. Bain","year":"1995","unstructured":"Bain, M., & Sammut, C. (1995). A framework for behavioral cloning. In Machine intelligence agents. London: Oxford University Press."},{"key":"9121_CR6","doi-asserted-by":"crossref","unstructured":"Boyd, S., Ghaoui, L. E., Feron, E., & Balakrishnan, V. (1994). Linear matrix inequalities in system and control theory. Society for Industrial and Applied Mathematics (SIAM).","DOI":"10.1137\/1.9781611970777"},{"key":"9121_CR7","doi-asserted-by":"crossref","unstructured":"Calinon, S., Guenter, F., & Billard, A. (2007). On learning, representing and generalizing a task in a humanoid robot. In IEEE Transactions on Systems, Man and Cybernetics, Part B. Special issue on robot learning by observation, demonstration and imitation, 37, 286\u2013298.","DOI":"10.1109\/TSMCB.2006.886952"},{"key":"9121_CR8","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511546921","volume-title":"Prediction, learning, and games","author":"N. Cesa-Bianchi","year":"2006","unstructured":"Cesa-Bianchi, N., & Lugosi, G. (2006). Prediction, learning, and games. New York: Cambridge University Press."},{"key":"9121_CR9","unstructured":"Chestnutt, J., Kuffner, J., Nishiwaki, K., & Kagami, S. (2003). Planning biped navigation strategies in complex environments. In Proceedings of the IEEE-RAS, international conference on humanoid robots. Karlsruhe, Germany."},{"key":"9121_CR10","doi-asserted-by":"crossref","unstructured":"Chestnutt, J., Lau, M., Cheng, G., Kuffner, J., Hodgins, J., & Kanade, T. (2005). Footstep planning for the Honda ASIMO humanoid. In Proceedings of the IEEE, international conference on robotics and automation.","DOI":"10.1109\/ROBOT.2005.1570188"},{"key":"9121_CR11","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1073\/pnas.0437847100","volume":"100","author":"D. L. Donoho","year":"2003","unstructured":"Donoho, D. L., & Elad, M. (2003). Maximal sparsity representation via l1 minimization. Proceedings of the National Academy Sciences, 100, 2197\u20132202.","journal-title":"Proceedings of the National Academy Sciences"},{"key":"9121_CR12","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1002\/rob.20109","volume":"23","author":"D. Ferguson","year":"2006","unstructured":"Ferguson, D., & Stentz, A. (2006). Using interpolation to improve path planning: The field D* algorithm. Journal of Field Robotics, 23, 79\u2013101.","journal-title":"Journal of Field Robotics"},{"key":"9121_CR13","unstructured":"Friedman, J. H. (1999a). Greedy function approximation: A gradient boosting machine. Annals of Statistics."},{"key":"9121_CR14","unstructured":"Gordon, G. (1999). Approximate solutions to Markov decision processes. Doctoral dissertation, Robotics Institute, Carnegie Mellon University."},{"key":"9121_CR15","doi-asserted-by":"crossref","first-page":"1463","DOI":"10.1109\/TRO.2008.2006703","volume":"24","author":"M. Hersch","year":"2008","unstructured":"Hersch, M., Guenter, F., Calinon, S., & Billard, A. (2008). Dynamical system modulation for robot learning via kinesthetic demonstrations. IEEE Transactions on Robotics, 24, 1463\u20131467.","journal-title":"IEEE Transactions on Robotics"},{"key":"9121_CR16","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511790423","volume-title":"Probability: The logic of science","author":"E. Jaynes","year":"2003","unstructured":"Jaynes, E. (2003). Probability: The logic of science. Cambridge: Cambridge University Press."},{"key":"9121_CR17","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1115\/1.3653115","volume":"86","author":"R. Kalman","year":"1964","unstructured":"Kalman, R. (1964). When is a linear control system optimal? Transaction ASME, Journal Basic Engineering, 86, 51\u201360.","journal-title":"Transaction ASME, Journal Basic Engineering"},{"key":"9121_CR18","unstructured":"Kelly, A., Amidi, O., Happold, M., Herman, H., Pilarski, T., Rander, P., Stentz, A., Vallidis, N., & Warner, R. (2004). Toward reliable autonomous vehicles operating in challenging environments. In Proceedings of the international symposium on experimental robotics (ISER). Singapore."},{"key":"9121_CR19","doi-asserted-by":"crossref","unstructured":"Kivinen, J., & Warmuth, M. K. (1997). Exponentiated gradient versus gradient descent for linear predictors. Information and Computation, 132.","DOI":"10.1006\/inco.1996.2612"},{"key":"9121_CR20","unstructured":"Kolter, J. Z., Abbeel, P., & Ng, A. Y. (2008). Hierarchical apprenticeship learning with application to quadruped locomotion. Neural Information Processing Systems, 20."},{"key":"9121_CR21","volume-title":"Advances in neural information processing systems","author":"A. Kulesza","year":"2008","unstructured":"Kulesza, A., & Pereira, F. (2008). Structured learning with approximate inference. In Advances in neural information processing systems. Cambridge: MIT."},{"key":"9121_CR22","volume-title":"Advances in neural information processing systems","author":"Y. LeCun","year":"2006","unstructured":"LeCun, Y., Muller, U., Ben, J., Cosatto, E., & Flepp, B. (2006). Off-road obstacle avoidance through end-to-end learning. In Advances in neural information processing systems (Vol.\u00a018). Cambridge: MIT."},{"key":"9121_CR23","volume-title":"Advances in large margin classifiers","author":"L. Mason","year":"1999","unstructured":"Mason, L., Baxter, J., Bartlett, P., & Frean, M. (1999). Functional gradient techniques for combining hypotheses. In Advances in large margin classifiers. Cambridge: MIT."},{"key":"9121_CR24","doi-asserted-by":"crossref","unstructured":"Miller, A. T., Knoop, S., Allen, P. K., & Christensen, H. I. (2003). Automatic grasp planning using shape primitives. In Proceedings of the IEEE, International conference on robotics and automation.","DOI":"10.1109\/ROBOT.2003.1241860"},{"key":"9121_CR25","doi-asserted-by":"crossref","unstructured":"Munoz, D., Bagnell, J. A. D., Vandapel, N., & Hebert, M. (2009). Contextual classification with functional max-margin Markov networks. In IEEE computer society conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2009.5206590"},{"key":"9121_CR26","unstructured":"Munoz, D., Vandapel, N., & Hebert, M. (2008). Directional associative Markov network for 3-d point cloud classification. In Fourth international symposium on 3D data processing, visualization and transmission."},{"key":"9121_CR27","unstructured":"Neu, G., & Szepesvari, C. (2007). Apprenticeship learning using inverse reinforcement learning and gradient methods. In Uncertainty in artificial intelligence (UAI)."},{"key":"9121_CR28","unstructured":"Ng, A. Y., & Russell, S. (2000). Algorithms for inverse reinforcement learning. In Proc. 17th international conf. on machine learning."},{"key":"9121_CR29","unstructured":"Pomerleau, D. (1989). ALVINN: An autonomous land vehicle in a neural network. In Advances in neural information processing systems (Vol.\u00a01)."},{"key":"9121_CR30","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"M. Puterman","year":"1994","unstructured":"Puterman, M. (1994). Markov decision processes: Discrete stochastic dynamic programming. New York: Wiley."},{"key":"9121_CR31","unstructured":"Ratliff, N., & Bagnell, J. A. (2009). Functional bundle methods. In The Learning workshop. Clearwater Beach, Florida."},{"key":"9121_CR32","doi-asserted-by":"crossref","unstructured":"Ratliff, N., Bagnell, J. A., & Zinkevich, M. (2006a). Maximum margin planning. In Twenty second international conference on machine learning (ICML06).","DOI":"10.1145\/1143844.1143936"},{"key":"9121_CR33","unstructured":"Ratliff, N., Bagnell, J. A., & Zinkevich, M. (2007a). (Online) subgradient methods for structured prediction. In Artificial intelligence and statistics. San Juan, Puerto Rico."},{"key":"9121_CR34","doi-asserted-by":"crossref","unstructured":"Ratliff, N., Bradley, D., Bagnell, J. A., & Chestnutt, J. (2006b). Boosting structured prediction for imitation learning. In NIPS. Vancouver, B.C.","DOI":"10.7551\/mitpress\/7503.003.0149"},{"key":"9121_CR35","doi-asserted-by":"crossref","unstructured":"Ratliff, N., Srinivasa, S., & Bagnell, J. A. (2007b). Imitation learning for locomotion and manipulation. In IEEE-RAS international conference on humanoid robots.","DOI":"10.21236\/ADA528601"},{"key":"9121_CR36","volume-title":"Advances in learning theory: methods, models and applications","author":"Y. Rifkin","year":"2003","unstructured":"Rifkin, Y., Poggio (2003). Regularized least squares classification. In Advances in learning theory: methods, models and applications. Amsterdam: IOS Press."},{"key":"9121_CR37","first-page":"941","volume":"5","author":"S. Rosset","year":"2004","unstructured":"Rosset, S., Zhu, J., & Hastie, T. (2004). Boosting as a regularized path to a maximum margin classifier. Journal Machine Learning Research, 5, 941\u2013973.","journal-title":"Journal Machine Learning Research"},{"key":"9121_CR38","unstructured":"Schaal, S., & Atkeson, C. (1994). Robot juggling: An implementation of memory-based learning. IEEE Control Systems Magazine, 14."},{"key":"9121_CR39","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-82118-9","volume-title":"Minimization methods for non-differentiable functions","author":"N. Z. Shor","year":"1985","unstructured":"Shor, N. Z. (1985). Minimization methods for non-differentiable functions. Berlin: Springer."},{"key":"9121_CR40","doi-asserted-by":"crossref","unstructured":"Silver, D., Bagnell, J. A., & Stentz, A. (2008). High performance outdoor navigation from overhead data using imitation learning. In Proceedings of Robotics Science and Systems.","DOI":"10.15607\/RSS.2008.IV.034"},{"key":"9121_CR41","doi-asserted-by":"crossref","unstructured":"Silver, D., Sofman, B., Vandapel, N., Bagnell, J. A., & Stentz, A. (2006). Experimental analysis of overhead data processing to support long range navigation. In Proceedings of the IEEE\/JRS international conference on intelligent robots and systems.","DOI":"10.1109\/IROS.2006.281686"},{"key":"9121_CR42","unstructured":"Stentz, A., Bares, J., Pilarski, T., & Stager, D. (2007). The crusher system for autonomous navigation. In AUVSI\u2019s unmanned systems."},{"key":"9121_CR43","doi-asserted-by":"crossref","unstructured":"Taskar, B., Chatalbashev, V., Guestrin, C., & Koller, D. (2005). Learning structured prediction models: A large margin approach. In Twenty second international conference on machine learning (ICML05).","DOI":"10.1145\/1102351.1102464"},{"key":"9121_CR44","unstructured":"Taskar, B., Guestrin, C., & Koller, D. (2003). Max margin Markov networks. In Advances in neural information processing systems (NIPS-14)."},{"key":"9121_CR45","volume-title":"Advances in neural information processing systems","author":"B. Taskar","year":"2006","unstructured":"Taskar, B., Lacoste-Julien, S., & Jordan, M. (2006). Structured prediction via the extragradient method. In Advances in neural information processing systems (Vol.\u00a018). Cambridge: MIT."},{"key":"9121_CR46","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1109\/TIT.2004.834793","volume":"50","author":"J. A. Tropp","year":"2004","unstructured":"Tropp, J. A. (2004). Greed is good: Algorithmic results for sparse approximation. IEEE Transactions on Information Theory, 50, 2231\u20132242.","journal-title":"IEEE Transactions on Information Theory"},{"key":"9121_CR47","doi-asserted-by":"crossref","unstructured":"Vandapel, N., Donamukkala, R. R., & Hebert, M. (2003). Quality assessment of traversability maps from aerial lidar data for an unmanned ground vehicle. In Proceedings of the IEEE\/JRS international conference on intelligent robots and systems.","DOI":"10.1109\/IROS.2003.1250645"},{"key":"9121_CR48","unstructured":"Ziebart, B., Bagnell, J. A., Mass, A., & Dey, A. (2008). Maximum entropy inverse reinforcement learning. In Twenty-third AAAI conference."},{"key":"9121_CR49","unstructured":"Zinkevich, M. (2003). Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the twentieth international conference on machine learning."}],"container-title":["Autonomous Robots"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-009-9121-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10514-009-9121-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10514-009-9121-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T17:00:58Z","timestamp":1710435658000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10514-009-9121-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,6,17]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2009,7]]}},"alternative-id":["9121"],"URL":"https:\/\/doi.org\/10.1007\/s10514-009-9121-3","relation":{},"ISSN":["0929-5593","1573-7527"],"issn-type":[{"value":"0929-5593","type":"print"},{"value":"1573-7527","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,6,17]]}}}