{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:57:14Z","timestamp":1775109434812,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2015,8,22]],"date-time":"2015-08-22T00:00:00Z","timestamp":1440201600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1007\/s10458-015-9308-2","type":"journal-article","created":{"date-parts":[[2015,8,21]],"date-time":"2015-08-21T11:49:24Z","timestamp":1440157764000},"page":"826-848","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Using informative behavior to increase engagement while learning from human reward"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1728-5711","authenticated-orcid":false,"given":"Guangliang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shimon","family":"Whiteson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"W. Bradley","family":"Knox","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hayley","family":"Hung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,8,22]]},"reference":[{"key":"9308_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., & Ng, A. Y. (2004). Apprenticeship learning via inverse reinforcement learning. In Proceedings of the 21st International Conference on Machine Learning (p. 1). ACM.","DOI":"10.1145\/1015330.1015430"},{"key":"9308_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). ACM.","DOI":"10.1145\/1228716.1228725"},{"issue":"5","key":"9308_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":"9308_CR4","first-page":"15","volume":"7","author":"DP Bertsekas","year":"1996","unstructured":"Bertsekas, D. P., & Tsitsiklis, J. N. (1996). Neuro-dynamic programming (optimization and neural computation series, 3). Athena Scientific, 7, 15\u201323.","journal-title":"Athena Scientific"},{"key":"9308_CR5","doi-asserted-by":"crossref","unstructured":"Blumberg, B., Downie, M., Ivanov, Y., Berlin, M., Johnson, M. P., & Tomlinson, B. (2002). Integrated learning for interactive synthetic characters. In ACM Transactions on Graphics (TOG) (pp. 417\u2013426). ACM.","DOI":"10.1145\/566570.566597"},{"key":"9308_CR6","unstructured":"B\u00f6hm, N., K\u00f3kai, G., & Mandl. S. (2004). Evolving a heuristic function for the game of tetris. In LWA (pp. 118\u2013122)."},{"issue":"7","key":"9308_CR7","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/2209249.2209266","volume":"55","author":"E Bouwers","year":"2012","unstructured":"Bouwers, E., Visser, J., & Van Deursen, A. (2012). Getting what you measure. Communications of the ACM, 55(7), 54\u201359.","journal-title":"Communications of the ACM"},{"key":"9308_CR8","doi-asserted-by":"crossref","unstructured":"Chao, C., Cakmak, M., & Thomaz, A. L. (2010). Transparent active learning for robots. In 5th ACM\/IEEE International Conference on Human-Robot Interaction (HRI) (pp. 317\u2013324). IEEE.","DOI":"10.1109\/HRI.2010.5453178"},{"key":"9308_CR9","doi-asserted-by":"crossref","unstructured":"Chernova, S., & Veloso, M. (2008). Multi-thresholded approach to demonstration selection for interactive robot learning. In Proceedings of the 3rd ACM\/IEEE International Conference on Human-Robot Interaction (HRI) (pp. 225\u2013232). IEEE.","DOI":"10.1145\/1349822.1349852"},{"issue":"1","key":"9308_CR10","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. Journal of Artificial Intelligence Research, 34(1), 1.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9308_CR11","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1007\/3-540-45071-8_36","volume-title":"Computing and combinatorics","author":"ED Demaine","year":"2003","unstructured":"Demaine, E. D., Hohenberger, S., & Liben-Nowell, D. (2003). Tetris is hard, even to approximate. Computing and combinatorics (pp. 351\u2013363). Berlin: Springer."},{"issue":"3","key":"9308_CR12","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1080\/02701367.1988.10605504","volume":"59","author":"DL Gill","year":"1988","unstructured":"Gill, D. L., & Deeter, T. E. (1988). Development of the sport orientation questionnaire. Research Quarterly for Exercise and Sport, 59(3), 191\u2013202.","journal-title":"Research Quarterly for Exercise and Sport"},{"key":"9308_CR13","doi-asserted-by":"crossref","unstructured":"Grollman, D. H. & Jenkins, O. C. (2007). Dogged learning for robots. In Proceedings of International Conference on Robotics and Automation (ICRA) (pp. 2483\u20132488).","DOI":"10.1109\/ROBOT.2007.363692"},{"key":"9308_CR14","doi-asserted-by":"crossref","unstructured":"Isbell, C., Shelton, C. R., Kearns, M., Singh, S., & Stone, P. (2001). A social reinforcement learning agent. In Proceedings of the 5th International Conference on Autonomous Agents (pp. 377\u2013384). ACM.","DOI":"10.1145\/375735.376334"},{"key":"9308_CR15","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 24th AAAI Conference on Artificial Intelligence (pp. 481\u2013486).","DOI":"10.1609\/aaai.v24i1.7690"},{"issue":"3","key":"9308_CR16","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/S0921-8890(02)00168-9","volume":"38","author":"F Kaplan","year":"2002","unstructured":"Kaplan, F., Oudeyer, P.-Y., Kubinyi, E., & Mikl\u00f3si, A. (2002). Robotic clicker training. Robotics and Autonomous Systems, 38(3), 197\u2013206.","journal-title":"Robotics and Autonomous Systems"},{"key":"9308_CR17","unstructured":"Knox, W. B. (2012). Learning from human-generated reward. PhD thesis, University of Texas at Austin."},{"key":"9308_CR18","doi-asserted-by":"crossref","unstructured":"Knox, W. B., & Stone, P. (2009). Interactively shaping agents via human reinforcement: The tamer framework. In Proceedings of the 5th International Conference on Knowledge Capture (pp. 9\u201316). ACM.","DOI":"10.1145\/1597735.1597738"},{"key":"9308_CR19","unstructured":"Knox, W. B., & Stone, P. (2010). Combining manual feedback with subsequent mdp reward signals for reinforcement learning. In Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems (pp. 5\u201312). International Foundation for Autonomous Agents and Multiagent Systems."},{"key":"9308_CR20","doi-asserted-by":"crossref","unstructured":"Knox, W. B., & Stone, P. (2012). Reinforcement learning from human reward: Discounting in episodic tasks. In RO-MAN, 2012 IEEE (pp. 878\u2013885). IEEE.","DOI":"10.1109\/ROMAN.2012.6343862"},{"key":"9308_CR21","unstructured":"Knox, W. B., & Stone, P. (2012). Reinforcement learning from simultaneous human and mdp reward. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (pp. 475\u2013482). International Foundation for Autonomous Agents and Multiagent Systems."},{"key":"9308_CR22","doi-asserted-by":"crossref","unstructured":"Knox, W. B., & Stone, P. (2013). Learning non-myopically from human-generated reward. In Proceedings of the 2013 International Conference on Intelligent User Interfaces (pp. 191\u2013202). ACM.","DOI":"10.1145\/2449396.2449422"},{"issue":"4","key":"9308_CR23","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. International Journal of Social Robotics, 4(4), 409\u2013421.","journal-title":"International Journal of Social Robotics"},{"issue":"05","key":"9308_CR24","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1017\/S0033291703001624","volume":"34","author":"E Lawrence","year":"2004","unstructured":"Lawrence, E., Shaw, P., Baker, D., Baron-Cohen, S., & David, A. (2004). Measuring empathy: Reliability and validity of the empathy quotient. Psychological Medicine, 34(05), 911\u2013920.","journal-title":"Psychological Medicine"},{"key":"9308_CR25","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 12th International Conference on Autonomous Agents and Multi-Agent Systems (pp. 909\u2013916). International Foundation for Autonomous Agents and Multiagent Systems."},{"issue":"1\u20133","key":"9308_CR26","first-page":"251","volume":"22","author":"R Maclin","year":"1996","unstructured":"Maclin, R., & Shavlik, J. W. (1996). Creating advice-taking reinforcement learners. Machine Learning, 22(1\u20133), 251\u2013281.","journal-title":"Machine Learning"},{"key":"9308_CR27","unstructured":"Maclin, R., Shavlik, J., Torrey, L., Walker, T., & Wild, E. (1999\/2005). Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression. In Proceedings of the National Conference on Artificial intelligence (pp. 819\u2013824). Menlo Park, CA, AAAI Press."},{"key":"9308_CR28","unstructured":"Ng, A. Y., Russell, S. J., et\u00a0al. (2000). Algorithms for inverse reinforcement learning. In Proceedings of International Conference on Machine Learning (ICML) (pp. 663\u2013670)."},{"key":"9308_CR29","doi-asserted-by":"crossref","unstructured":"Pilarski, P. M., Dawson, M. R., Degris, T., Fahimi, F., Carey, J. P., & Sutton, R. S. (2011). Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning. In Proceedings of 12th International Conference on Rehabilitation Robotics (ICORR) (pp. 1\u20137). IEEE.","DOI":"10.1109\/ICORR.2011.5975338"},{"key":"9308_CR30","doi-asserted-by":"crossref","unstructured":"Suay, H. B., & Chernova, S. (2011). Effect of human guidance and state space size on interactive reinforcement learning. In 20th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN) (pp. 1\u20136). IEEE.","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"9308_CR31","volume-title":"Reinforcement learning: An introduction","author":"R Sutton","year":"1998","unstructured":"Sutton, R., & Barto, A. (1998). Reinforcement learning: An introduction. Cambridge, MA: MIT Press."},{"issue":"12","key":"9308_CR32","doi-asserted-by":"crossref","first-page":"2936","DOI":"10.1162\/neco.2006.18.12.2936","volume":"18","author":"I Szita","year":"2006","unstructured":"Szita, I., & L\u00f6rincz, A. (2006). Learning tetris using the noisy cross-entropy method. Neural Computation, 18(12), 2936\u20132941.","journal-title":"Neural Computation"},{"key":"9308_CR33","unstructured":"Taylor, M. E., Suay, H. B., & Chernova, S. (2011). Integrating reinforcement learning with human demonstrations of varying ability. In Proceedings of the 10th International Conference on Autonomous Agents and Multiagent Systems (pp. 617\u2013624). International Foundation for Autonomous Agents and Multiagent Systems."},{"key":"9308_CR34","doi-asserted-by":"crossref","unstructured":"Tenorio-Gonzalez, A. C., Morales, E. F., & Villase\u00f1or-Pineda, L. (2010). Dynamic reward shaping: Training a robot by voice. In Advances in Artificial Intelligence\u2014IBERAMIA 2010 (pp. 483\u2013492). Springer.","DOI":"10.1007\/978-3-642-16952-6_49"},{"key":"9308_CR35","first-page":"1000","volume":"6","author":"AL Thomaz","year":"2006","unstructured":"Thomaz, A. L., & Breazeal, C. (2006). Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance. AAAI, 6, 1000\u20131005.","journal-title":"AAAI"},{"key":"9308_CR36","unstructured":"Thomaz, A. L., & Breazeal, C. (2006). Transparency and socially guided machine learning. In 5th International Conference on Development and Learning (ICDL)."},{"issue":"6","key":"9308_CR37","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1016\/j.artint.2007.09.009","volume":"172","author":"AL Thomaz","year":"2008","unstructured":"Thomaz, A. L., & Breazeal, C. (2008). Teachable robots: Understanding human teaching behavior to build more effective robot learners. Artificial Intelligence, 172(6), 716\u2013737.","journal-title":"Artificial Intelligence"},{"key":"9308_CR38","unstructured":"Thomaz, A. L., Hoffman, G., & Breazeal, C. (2005). Real-time interactive reinforcement learning for robots. In AAAI 2005 Workshop on Human Comprehensible Machine Learning."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-015-9308-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-015-9308-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-015-9308-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,13]],"date-time":"2023-08-13T09:26:51Z","timestamp":1691918811000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-015-9308-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,8,22]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2016,9]]}},"alternative-id":["9308"],"URL":"https:\/\/doi.org\/10.1007\/s10458-015-9308-2","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,8,22]]}}}