{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:22:54Z","timestamp":1776975774587,"version":"3.51.4"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319293387","type":"print"},{"value":"9783319293394","type":"electronic"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-29339-4_2","type":"book-chapter","created":{"date-parts":[[2016,1,28]],"date-time":"2016-01-28T15:59:18Z","timestamp":1453996758000},"page":"16-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Interactive Learning of Continuous Actions from Corrective Advice Communicated by Humans"],"prefix":"10.1007","author":[{"given":"Carlos","family":"Celemin","sequence":"first","affiliation":[]},{"given":"Javier","family":"Ruiz-del-Solar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,1,29]]},"reference":[{"issue":"5","key":"2_CR1","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"BD Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Rob. Auton. Syst. 57(5), 469\u2013483 (2009)","journal-title":"Rob. Auton. Syst."},{"issue":"11","key":"2_CR2","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1016\/S1364-6613(02)02016-8","volume":"6","author":"C Breazeal","year":"2002","unstructured":"Breazeal, C., Scassellati, B.: Robots that imitate humans. Trends Cogn. Sci. 6(11), 481\u2013487 (2002)","journal-title":"Trends Cogn. Sci."},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Ng, A.Y.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the Twenty-First International Conference on Machine Learning. ACM (2004)","DOI":"10.1145\/1015330.1015430"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Meri\u00e7li, C., Veloso, M., Akin, H.L.: Complementary humanoid behavior shaping using corrective demonstration. In: 10th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 334\u2013339. IEEE (2010)","DOI":"10.1109\/ICHR.2010.5686326"},{"issue":"2","key":"2_CR5","first-page":"68","volume":"8","author":"\u00c7 Meri\u00e7li","year":"2011","unstructured":"Meri\u00e7li, \u00c7., Veloso, M., Akin, H.L.: Task refinement for autonomous robots using complementary corrective human feedback. Int. J. Adv. Rob. Syst. 8(2), 68 (2011)","journal-title":"Int. J. Adv. Rob. Syst."},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Argall, B.D., Browning, B., Veloso, M.: Learning robot motion control with demonstration and advice-operators. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems IROS 2008, pp. 399\u2013404. IEEE (2008)","DOI":"10.1109\/IROS.2008.4651020"},{"issue":"4","key":"2_CR7","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1109\/TRO.2008.926867","volume":"24","author":"N Mitsunaga","year":"2008","unstructured":"Mitsunaga, N., Smith, C., Kanda, T., Ishiguro, H., Hagita, N.: Adapting robot behavior for human\u2013robot interaction. IEEE Trans. Rob. 24(4), 911\u2013916 (2008)","journal-title":"IEEE Trans. Rob."},{"key":"2_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-642-16952-6_49","volume-title":"Advances in Artificial Intelligence \u2013 IBERAMIA 2010","author":"AC Tenorio-Gonzalez","year":"2010","unstructured":"Tenorio-Gonzalez, A.C., Villase\u00f1or-Pineda, L., Morales, E.F.: Dynamic reward shaping: training a robot by voice. In: Kuri-Morales, A., Simari, G.R. (eds.) IBERAMIA 2010. LNCS, vol. 6433, pp. 483\u2013492. Springer, Heidelberg (2010)"},{"key":"2_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-642-25085-9_65","volume-title":"Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications","author":"A Le\u00f3n","year":"2011","unstructured":"Le\u00f3n, A., Morales, E.F., Altamirano, L., Ruiz, J.R.: Teaching a robot to perform task through imitation and on-line feedback. In: San Martin, C., Kim, S.-W. (eds.) CIARP 2011. LNCS, vol. 7042, pp. 549\u2013556. Springer, Heidelberg (2011)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Suay, H.B., Chernova, S.: Effect of human guidance and state space size on interactive reinforcement learning. In: RO-MAN 2011, pp. 1\u20136. IEEE (2011)","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Pilarski, P.M., Dawson, M.R., Degris, T., Fahimi, F., Carey, J.P., Sutton, R.S. Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning. In: IEEE International Conference on Rehabilitation Robotics (ICORR), pp. 1\u20137. IEEE (2011)","DOI":"10.1109\/ICORR.2011.5975338"},{"key":"2_CR12","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/TSMC.2013.2291714","volume":"44","author":"PM Yanik","year":"2014","unstructured":"Yanik, P.M., Manganelli, J., Merino, J., Threatt, A.L., Brooks, J.O., Green, K.E., Walker, I.D.: A gesture learning interface for simulated robot path shaping with a human teacher. IEEE Trans. Hum.-Mach. Syst. 44, 41\u201354 (2014)","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Thomaz, A.L., Hoffman, G., Breazeal, C.: Reinforcement learning with human teachers: understanding how people want to teach robots. In: The 15th IEEE International Symposium on Robot and Human Interactive Communication, ROMAN 2006, pp. 352\u2013357. IEEE (2006)","DOI":"10.1109\/ROMAN.2006.314459"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Thomaz, A.L., Breazeal, C.: Asymmetric interpretations of positive and negative human feedback for a social learning agent. In: The 16th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2007, pp. 720\u2013725. IEEE (2007)","DOI":"10.1109\/ROMAN.2007.4415180"},{"key":"2_CR15","unstructured":"Knox, W.B., Stone, P.: TAMER: training an agent manually via evaluative reinforcement. In: 7th IEEE International Conference on Development and Learning, ICDL 2008, pp. 292\u2013297. IEEE (2008)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Knox, W.B., Stone, P.: Interactively shaping agents via human reinforcement: the TAMER framework. In: Proceedings of the Fifth International Conference on Knowledge Capture, pp. 9\u201316. ACM (2009)","DOI":"10.1145\/1597735.1597738"},{"issue":"2","key":"2_CR17","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s10489-012-0412-6","volume":"39","author":"NA Vien","year":"2013","unstructured":"Vien, N.A., Ertel, W., Chung, T.C.: Learning via human feedback in continuous state and action spaces. Appl. Intell. 39(2), 267\u2013278 (2013)","journal-title":"Appl. Intell."},{"key":"2_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-319-18615-3_45","volume-title":"RoboCup 2014: Robot World Cup XVIII","author":"L Leottau","year":"2015","unstructured":"Leottau, L., Ruiz-del-Solar, J., Celemin, C.: Ball dribbling for humanoid biped robots: a reinforcement learning and fuzzy control approach. In: Bianchi, R.A., Akin, H., Ramamoorthy, S., Sugiura, K. (eds.) RoboCup 2014. LNCS, vol. 8992, pp. 549\u2013561. Springer, Heidelberg (2015)"},{"key":"2_CR19","volume-title":"Reinforcement Learning: an Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: an Introduction. MIT Press, Cambridge (1998)"},{"key":"2_CR20","volume-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators","author":"L Busoniu","year":"2010","unstructured":"Busoniu, L., Babuska, R., De Schutter, B., Ernst, D.: Reinforcement Learning and Dynamic Programming Using Function Approximators. CRC Press, Boca Raton (2010)"},{"key":"2_CR21","unstructured":"Celemin, C.: A hand-gesture interface for interactive learning. Internal report, Advanced Mining Technology Center, Universidad de Chile (2014). (in Spanish)"}],"container-title":["Lecture Notes in Computer Science","RoboCup 2015: Robot World Cup XIX"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-29339-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T06:02:40Z","timestamp":1719295360000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-29339-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319293387","9783319293394"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-29339-4_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"29 January 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}