{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T22:23:04Z","timestamp":1778797384754,"version":"3.51.4"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2012,7,4]],"date-time":"2012-07-04T00:00:00Z","timestamp":1341360000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J of Soc Robotics"],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1007\/s12369-012-0163-x","type":"journal-article","created":{"date-parts":[[2012,7,3]],"date-time":"2012-07-03T15:39:07Z","timestamp":1341329947000},"page":"409-421","source":"Crossref","is-referenced-by-count":50,"title":["How Humans Teach Agents"],"prefix":"10.1007","volume":"4","author":[{"given":"W. Bradley","family":"Knox","sequence":"first","affiliation":[]},{"given":"Brian D.","family":"Glass","sequence":"additional","affiliation":[]},{"given":"Bradley C.","family":"Love","sequence":"additional","affiliation":[]},{"given":"W. Todd","family":"Maddox","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,7,4]]},"reference":[{"key":"163_CR1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1015330.1015430","volume-title":"Proceedings of the twenty-first international conference on machine learning","author":"P Abbeel","year":"2004","unstructured":"Abbeel P, Ng A (2004) Apprenticeship learning via inverse reinforcement learning. In: Proceedings of the twenty-first international conference on machine learning. ACM, New York, p\u00a01"},{"key":"163_CR2","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1145\/1228716.1228725","volume-title":"Proceedings of the ACM\/IEEE international conference on Human-robot interaction","author":"B Argall","year":"2007","unstructured":"Argall B, Browning B, Veloso M (2007) Learning by demonstration with critique from a human teacher. In: Proceedings of the ACM\/IEEE international conference on Human-robot interaction. ACM, New York, pp 57\u201364"},{"issue":"5","key":"163_CR3","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"B Argall","year":"2009","unstructured":"Argall B, Chernova S, Veloso M, Browning B (2009) A survey of robot learning from demonstration. Robot Auton Syst 57(5):469\u2013483","journal-title":"Robot Auton Syst"},{"key":"163_CR4","volume-title":"Neuro-dynamic programming","author":"D Bertsekas","year":"1996","unstructured":"Bertsekas D, Tsitsiklis J (1996) Neuro-dynamic programming. Athena Scientific, Nashua"},{"key":"163_CR5","volume-title":"Learning and behavior: a contemporary synthesis","author":"M Bouton","year":"2007","unstructured":"Bouton M (2007) Learning and behavior: a contemporary synthesis. Sinauer Associates, Sunderland"},{"key":"163_CR6","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/2376.001.0001","volume-title":"Designing sociable robots","author":"C Breazeal","year":"2004","unstructured":"Breazeal C (2004) Designing sociable robots. MIT Press, Cambridge"},{"issue":"1","key":"163_CR7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1613\/jair.2584","volume":"34","author":"S Chernova","year":"2009","unstructured":"Chernova S, Veloso M (2009) Interactive policy learning through confidence-based autonomy. J Artif Intell Res 34(1):1\u201325","journal-title":"J Artif Intell Res"},{"key":"163_CR8","first-page":"385","volume-title":"8th IEEE-RAS international conference on humanoid robots","author":"S Chernova","year":"2009","unstructured":"Chernova S, Veloso M (2009) Teaching collaborative multi-robot tasks through demonstration. In: 8th IEEE-RAS international conference on humanoid robots, Humanoids, 2008. IEEE Press, New York, pp 385\u2013390."},{"issue":"1","key":"163_CR9","first-page":"103","volume":"4","author":"K Dautenhahn","year":"2007","unstructured":"Dautenhahn K (2007) Methodology and themes of human-robot interaction: a growing research field. Int J Adv Robot Syst 4(1):103\u2013108","journal-title":"Int J Adv Robot Syst"},{"issue":"3","key":"163_CR10","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1080\/0300443032000153598","volume":"174","author":"J Dobbs","year":"2004","unstructured":"Dobbs J, Arnold D, Doctoroff G (2004) Attention in the preschool classroom: the relationships among child gender, child misbehavior, and types of teacher attention. Early Child Dev Care 174(3):281\u2013295","journal-title":"Early Child Dev Care"},{"key":"163_CR11","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1145\/1349822.1349856","volume-title":"Proceedings of the 3rd ACM\/IEEE international conference on human robot interaction","author":"V Evers","year":"2008","unstructured":"Evers V, Maldonado H, Brodecki T, Hinds P (2008) Relational vs. group self-construal: untangling the role of national culture in hri. In: Proceedings of the 3rd ACM\/IEEE international conference on human robot interaction. ACM, New York, pp 255\u2013262"},{"issue":"2","key":"163_CR12","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1037\/h0035185","volume":"9","author":"B Fagot","year":"1973","unstructured":"Fagot B (1973) Influence of teacher behavior in the preschool. Dev Psychol 9(2):198","journal-title":"Dev Psychol"},{"key":"163_CR13","first-page":"2483","volume-title":"IEEE international conference on robotics and automation","author":"D Grollman","year":"2007","unstructured":"Grollman D, Jenkins O (2007) Dogged learning for robots. In: IEEE international conference on robotics and automation, 2007. IEEE Press, New York, pp 2483\u20132488"},{"issue":"1","key":"163_CR14","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1207\/s15327051hci1901&2_7","volume":"19","author":"P Hinds","year":"2004","unstructured":"Hinds P, Roberts T, Jones H (2004) Whose job is it anyway? A\u00a0study of human-robot interaction in a collaborative task. Hum-Comput Interact 19(1):151\u2013181","journal-title":"Hum-Comput Interact"},{"key":"163_CR15","volume-title":"AAMAS","author":"C Isbell","year":"2006","unstructured":"Isbell C, Kearns M, Singh S, Shelton C, Stone P, Kormann D (2006) Cobot in LambdaMOO: an adaptive social statistics agent. In: AAMAS"},{"key":"163_CR16","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1007\/978-3-642-22362-4_31","volume-title":"User modeling, adaption and personalization","author":"T Kaochar","year":"2011","unstructured":"Kaochar T, Peralta R, Morrison C, Fasel I, Walsh T, Cohen P (2011) Towards understanding how humans teach robots. In: User modeling, adaption and personalization, pp\u00a0347\u2013352"},{"key":"163_CR17","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1145\/1514095.1514102","volume-title":"Proceedings of the 4th ACM\/IEEE international conference on human robot interaction","author":"E Kim","year":"2009","unstructured":"Kim E, Leyzberg D, Tsui K, Scassellati B (2009) How people talk when teaching a robot. In: Proceedings of the 4th ACM\/IEEE international conference on human robot interaction. ACM, New York, pp 23\u201330"},{"key":"163_CR18","volume-title":"The 5th international conference on knowledge capture","author":"W Knox","year":"2009","unstructured":"Knox W, Stone P (2009) Interactively shaping agents via human reinforcement: the TAMER framework. In: The 5th international conference on knowledge capture"},{"key":"163_CR19","volume-title":"Proceedings of 7th ACM\/IEEE international conference on Human-Robot interaction, Late-Breaking reports session (HRI 2012)","author":"WB Knox","year":"2012","unstructured":"Knox WB, Breazeal C, Stone P (2012) Learning from feedback on actions past and intended. In: Proceedings of 7th ACM\/IEEE international conference on Human-Robot interaction, Late-Breaking reports session (HRI 2012)"},{"key":"163_CR20","volume-title":"Proceedings of the 11th international conference on autonomous agents and multiagent systems (AAMAS)","author":"WB Knox","year":"2012","unstructured":"Knox WB, Stone P (2012) Reinforcement learning with human and MDP reward. In: Proceedings of the 11th international conference on autonomous agents and multiagent systems (AAMAS)"},{"key":"163_CR21","volume-title":"The AAAI-2004 workshop on supervisory control of learning and adaptive systems","author":"G Kuhlmann","year":"2004","unstructured":"Kuhlmann G, Stone P, Mooney R, Shavlik J (2004) Guiding a reinforcement learner with natural language advice: initial results in RoboCup soccer. In: The AAAI-2004 workshop on supervisory control of learning and adaptive systems"},{"issue":"3","key":"163_CR22","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1075\/is.7.3.03mac","volume":"7","author":"K MacDorman","year":"2006","unstructured":"MacDorman K, Ishiguro H (2006) The uncanny advantage of using androids in cognitive and social science research. Interact Stud 7(3):297\u2013337","journal-title":"Interact Stud"},{"key":"163_CR23","first-page":"21","volume-title":"Proceedings of the XXVII annual meeting of the cognitive science society","author":"K MacDorman","year":"2005","unstructured":"MacDorman K, Minato T, Shimada M, Itakura S, Cowley S, Ishiguro H (2005) Assessing human likeness by eye contact in an android testbed. In: Proceedings of the XXVII annual meeting of the cognitive science society, pp 21\u201323"},{"issue":"1","key":"163_CR24","first-page":"251","volume":"22","author":"R Maclin","year":"1996","unstructured":"Maclin R, Shavlik J (1996) Creating advice-taking reinforcement learners. Mach Learn 22(1):251\u2013281","journal-title":"Mach Learn"},{"issue":"5","key":"163_CR25","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1109\/3468.952716","volume":"31","author":"M Nicolescu","year":"2002","unstructured":"Nicolescu M, Mataric M (2002) Learning and interacting in human-robot domains. IEEE Trans Syst Man Cybern, Part A, Syst Hum 31(5):419\u2013430","journal-title":"IEEE Trans Syst Man Cybern, Part A, Syst Hum"},{"key":"163_CR26","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1145\/860575.860614","volume-title":"AAMAS","author":"M Nicolescu","year":"2003","unstructured":"Nicolescu M, Mataric M (2003) Natural methods for robot task learning: instructive demonstrations, generalization and practice. In: AAMAS. ACM, New York, pp 241\u2013248"},{"key":"163_CR27","series-title":"Advances in neural information processing systems","volume-title":"ALVINN: an autonomous land vehicle in a neural network","author":"D Pomerleau","year":"1989","unstructured":"Pomerleau D (1989) ALVINN: an autonomous land vehicle in a neural network. Advances in neural information processing systems, vol 1. Morgan Kaufmann, San Mateo"},{"key":"163_CR28","volume-title":"Don\u2019t shoot the dog! The new art of teaching and training","author":"K Pryor","year":"2002","unstructured":"Pryor K (2002) Don\u2019t shoot the dog! The new art of teaching and training. Interpet Publishing, Dorking"},{"key":"163_CR29","volume-title":"Animal training: successful animal management through positive reinforcement","author":"K Ramirez","year":"1999","unstructured":"Ramirez K (1999) Animal training: successful animal management through positive reinforcement. Shedd Aquarium, Chicago"},{"key":"163_CR30","volume-title":"IEEE international conference on robotics and automation","author":"K Reed","year":"2007","unstructured":"Reed K, Patton J, Peshkin M (2007) Replicating human-human physical interaction. In: IEEE international conference on robotics and automation"},{"issue":"2","key":"163_CR31","doi-asserted-by":"crossref","first-page":"225","DOI":"10.3758\/PBR.16.2.225","volume":"16","author":"J Rouder","year":"2009","unstructured":"Rouder J, Speckman P, Sun D, Morey R, Iverson G (2009) Bayesian t tests for accepting and rejecting the null hypothesis. Psychon Bull Rev 16(2):225\u2013237","journal-title":"Psychon Bull Rev"},{"key":"163_CR32","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1145\/1121241.1121263","volume-title":"Proceedings of the 1st ACM SIGCHI\/SIGART conference on human-robot interaction","author":"J Saunders","year":"2006","unstructured":"Saunders J, Nehaniv C, Dautenhahn K (2006) Teaching robots by moulding behavior and scaffolding the environment. In: Proceedings of the 1st ACM SIGCHI\/SIGART conference on human-robot interaction. ACM, New York, pp 118\u2013125"},{"key":"163_CR33","volume-title":"Proceedings of IEEE international conference on machine learning applications","author":"M Sridharan","year":"2011","unstructured":"Sridharan M (2011) Augmented reinforcement learning for interaction with non-expert humans in agent domains. In: Proceedings of IEEE international conference on machine learning applications"},{"key":"163_CR34","volume-title":"Reinforcement learning: an introduction","author":"R Sutton","year":"1998","unstructured":"Sutton R, Barto A (1998) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"key":"163_CR35","first-page":"2133","volume":"10","author":"B Tanner","year":"2009","unstructured":"Tanner B, White A (2009) RL-Glue: Language-independent software for reinforcement-learning experiments. J Mach Learn Res 10:2133\u20132136","journal-title":"J Mach Learn Res"},{"key":"163_CR36","doi-asserted-by":"crossref","unstructured":"Thomaz A (2006) Socially guided machine learning. PhD thesis, Citeseer","DOI":"10.1145\/1121241.1121315"},{"key":"163_CR37","volume-title":"AAAI","author":"A Thomaz","year":"2006","unstructured":"Thomaz A, Breazeal C (2006) Reinforcement learning with human teachers: evidence of feedback and guidance with implications for learning performance. In: AAAI"},{"key":"163_CR38","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/1514095.1514101","volume-title":"Proceedings of the 4th ACM\/IEEE international conference on human robot interaction","author":"A Thomaz","year":"2009","unstructured":"Thomaz A, Cakmak M (2009) Learning about objects with human teachers. In: Proceedings of the 4th ACM\/IEEE international conference on human robot interaction. ACM, New York, pp 15\u201322"},{"key":"163_CR39","volume-title":"Solving discipline and classroom management problems: methods and models for today\u2019s teachers","author":"C Wolfgang","year":"2004","unstructured":"Wolfgang C (2004) Solving discipline and classroom management problems: methods and models for today\u2019s teachers. Wiley, New York"},{"key":"163_CR40","volume-title":"International conference on artificial intelligence and pattern recognition","author":"M Woodward","year":"2009","unstructured":"Woodward M, Wood R (2009) Using Bayesian inference to learn high-level tasks from a human teacher. In: International conference on artificial intelligence and pattern recognition, AIPR-09"}],"container-title":["International Journal of Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12369-012-0163-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12369-012-0163-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12369-012-0163-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,30]],"date-time":"2019-06-30T14:00:16Z","timestamp":1561903216000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12369-012-0163-x"}},"subtitle":["A New Experimental Perspective"],"short-title":[],"issued":{"date-parts":[[2012,7,4]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2012,11]]}},"alternative-id":["163"],"URL":"https:\/\/doi.org\/10.1007\/s12369-012-0163-x","relation":{},"ISSN":["1875-4791","1875-4805"],"issn-type":[{"value":"1875-4791","type":"print"},{"value":"1875-4805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,7,4]]}}}