{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:33:05Z","timestamp":1791567185985,"version":"4.3.4"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,2,13]],"date-time":"2015-02-13T00:00:00Z","timestamp":1423785600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2016,1]]},"DOI":"10.1007\/s10458-015-9283-7","type":"journal-article","created":{"date-parts":[[2015,2,12]],"date-time":"2015-02-12T07:46:57Z","timestamp":1423727217000},"page":"30-59","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["Learning behaviors via human-delivered discrete feedback: modeling implicit feedback strategies to speed up learning"],"prefix":"10.1007","volume":"30","author":[{"given":"Robert","family":"Loftin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"MacGlashan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael L.","family":"Littman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew E.","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeff","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David L.","family":"Roberts","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,2,13]]},"reference":[{"key":"9283_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., & Ng, A. Y. (2004). Apprenticeship learning via inverse reinforcement learning. In Proceedings of the Twenty-First International Conference on Machine Learning.","DOI":"10.1145\/1015330.1015430"},{"key":"9283_CR2","doi-asserted-by":"crossref","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 (pp. 57\u201364).","DOI":"10.1145\/1228716.1228725"},{"issue":"5","key":"9283_CR3","doi-asserted-by":"crossref","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. (2009). A survey of robot learning from demonstration. Robotics and Autonomous Systems, 57(5), 469\u2013483.","journal-title":"Robotics and Autonomous Systems"},{"key":"9283_CR4","unstructured":"Atkeson, C. G., & Schaal, S. (1997). Robot learning from demonstration. In Proceedings of the Fourteenth International Conference on machine learning."},{"key":"9283_CR5","unstructured":"Cakmak, M., & Lopes, M. (2012). Algorithmic and human teaching of sequential decision tasks. In Proceedings of the Twenty-sixth AAAI Conference on artificial intelligence (pp. 1536\u20131542)."},{"key":"9283_CR6","doi-asserted-by":"crossref","unstructured":"Chernova, S., & Veloso, M. (2007). Confidence-based policy learning from demonstration using gaussian mixture models. In Proceedings of the 6th International Conference on autonomous agents and multiagent systems.","DOI":"10.1145\/1329125.1329407"},{"issue":"1","key":"9283_CR7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society. Series B (Methodological), 39(1), 1\u201338.","journal-title":"Journal of the Royal Statistical Society. Series B (Methodological)"},{"key":"9283_CR8","unstructured":"Griffith, S., Subramanian, K., Scholz, J., Isbell, C., & Thomaz, A. L. (2013). Policy shaping: Integrating human feedback with reinforcement learning. Advances in Neural Information Processing Systems, 26."},{"key":"9283_CR9","doi-asserted-by":"crossref","unstructured":"Heer, J., Good, N. S., Ramirez, A., Davis, M., & Mankoff, J. (2004). Presiding over accidents: system direction of human action. In Proceedings of the SIGCHI Conference on human factors in computing systems (pp. 463\u2013470).","DOI":"10.1145\/985692.985751"},{"issue":"1","key":"9283_CR10","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1017\/S0962728600026683","volume":"13","author":"E Hiby","year":"2004","unstructured":"Hiby, E., Rooney, N., & Bradshaw, J. (2004). Dog training methods: Their use, effectiveness and interaction with behaviour and welfare. Animal Welfare, 13(1), 63\u201370.","journal-title":"Animal Welfare"},{"key":"9283_CR11","doi-asserted-by":"crossref","unstructured":"Isbell, C., Shelton, C., Kearns, M., Singh, S., & Stone, P. (2001). A social reinforcement learning agent. In Proceedings of the Fifth International Conference on Autonomous Agents (pp. 377\u2013384).","DOI":"10.1145\/375735.376334"},{"key":"9283_CR12","doi-asserted-by":"crossref","unstructured":"Judah, K., Fern, A., Tadepalli, P., & Goetschalckx, R. (2014). Imitation learning with demonstrations and shaping rewards. In Proceedings of the twenty-eighth AAAI Conference on Artificial Intelligence (pp. 1890\u20131896).","DOI":"10.1609\/aaai.v28i1.9024"},{"key":"9283_CR13","doi-asserted-by":"crossref","unstructured":"Judah, K., Roy, S., Fern, A., & Dietterich, T. G. (2010). Reinforcement learning via practice and critique advice. In Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (pp. 481\u2013486).","DOI":"10.1609\/aaai.v24i1.7690"},{"key":"9283_CR14","unstructured":"Khan, F., Zhu, X., & Mutlu, B. (2011). How do humans teach: On curriculum learning and teaching dimension. In Proceedings of the Twenty-fifth Annual Conference on Neural Information Processing Systems (pp. 1449\u20131457)."},{"key":"9283_CR15","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1007\/978-3-319-02675-6_46","volume":"8239","author":"W Knox","year":"2013","unstructured":"Knox, W., Stone, P., & Breazeal, C. (2013). Training a robot via human feedback: A case study. Social Robotics, Lecture Notes in Computer Science, 8239, 460\u2013470.","journal-title":"Social Robotics, Lecture Notes in Computer Science"},{"issue":"4","key":"9283_CR16","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1007\/s12369-012-0163-x","volume":"4","author":"WB Knox","year":"2012","unstructured":"Knox, W. B., Glass, B. D., Love, B. C., Maddox, W. T., & Stone, P. (2012). How humans teach agents\u2014a new experimental perspective. International Journal of Social Robotics, 4(4), 409\u2013421.","journal-title":"International Journal of Social Robotics"},{"key":"9283_CR17","doi-asserted-by":"crossref","unstructured":"Knox, W. B., & Stone, P. (2009). Interactively shaping agents via human reinforcement: The tamer framework. In Proceedings of the Fifth International Conference on Knowledge Capture (pp. 9\u201316).","DOI":"10.1145\/1597735.1597738"},{"key":"9283_CR18","unstructured":"Knox, W. B., Taylor, M. E., & Stone, P. (2011). Understanding human teaching modalities in reinforcement learning environments: A preliminary report. In Proceedings of the Workshop on Agents Learning Interactively from Human Teachers (at IJCAI-11)."},{"key":"9283_CR19","unstructured":"Li, G., Hung, H., Whiteson, S., & Knox, W. B. (2013). Using informative behavior to increase engagement in the TAMER framework. In Proceedings of the Twelfth International Conference on Autonomous Agents and Multiagent Systems (pp. 909\u2013916)."},{"key":"9283_CR20","unstructured":"Lu, T., Pal, D., Pal, M. (2010). Contextual multi-armed bandits. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics."},{"key":"9283_CR21","unstructured":"Ng, A. Y., & Russell, S. J. (2000). Algorithms for inverse reinforcement learning. In Proceedings of the Seventeenth International Conference on Machine Learning (pp. 663\u2013670)."},{"key":"9283_CR22","unstructured":"Ramachandran, D. (2007). Bayesian inverse reinforcement learning. In Proceedings of the Twentieth International Joint Conference on Artificial Intelligence."},{"key":"9283_CR23","volume-title":"The behavior of organisms: An experimental analysis","author":"BF Skinner","year":"1938","unstructured":"Skinner, B. F. (1938). The behavior of organisms: An experimental analysis. New York: Appleton-Century."},{"key":"9283_CR24","volume-title":"Science and human behavior","author":"BF Skinner","year":"1953","unstructured":"Skinner, B. F. (1953). Science and human behavior. New York: Macmillan."},{"key":"9283_CR25","volume-title":"Reinforcement learning: An introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., & Barto, A. (1998). Reinforcement learning: An introduction. Cambridge: MIT Press."},{"key":"9283_CR26","doi-asserted-by":"crossref","unstructured":"Tesauro, G. (1990). Neurogammon: A neural-network backgammon program. In Proceedings of the International Joint Conference on Neural Networks (pp. 33\u201339). IEEE.","DOI":"10.1109\/IJCNN.1990.137821"},{"key":"9283_CR27","unstructured":"Thomaz, A. L., Breazeal, C. (2006). Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance. In Proceedings of the Twenty-first AAAI Conference on Artificial Intelligence (pp. 1000\u20131005)."},{"key":"9283_CR28","unstructured":"Ziebart, B. D., Maas, A., Bagnell, J. A., & Dey, A. K. (2008). Maximum entropy inverse reinforcement learning. In Proceedings of the Twenty-third AAAI conference on artificial intelligence."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-015-9283-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-015-9283-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-015-9283-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,5]],"date-time":"2023-08-05T10:25:30Z","timestamp":1691231130000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-015-9283-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,13]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,1]]}},"alternative-id":["9283"],"URL":"https:\/\/doi.org\/10.1007\/s10458-015-9283-7","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,2,13]]}}}