{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T14:17:03Z","timestamp":1725891423367},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642309465"},{"type":"electronic","value":"9783642309472"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-30947-2_9","type":"book-chapter","created":{"date-parts":[[2012,6,18]],"date-time":"2012-06-18T09:16:30Z","timestamp":1340010990000},"page":"54-64","source":"Crossref","is-referenced-by-count":1,"title":["Strategy-Based Learning through Communication with Humans"],"prefix":"10.1007","author":[{"given":"Nguyen-Thinh","family":"Le","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niels","family":"Pinkwart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"5","key":"9_CR1","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","volume":"57","author":"B.D. Argall","year":"2009","unstructured":"Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A Survey of Robot Learning From Demonstration. Robotics and Autonomous Systems\u00a057(5), 469\u2013483 (2009)","journal-title":"Robotics and Autonomous Systems"},{"doi-asserted-by":"crossref","unstructured":"G\u00f6rmer, J., Homoceanu, G., Mumme, C., Huhn, M., M\u00fcller, J.P.: JRep: Extending Repast Simphony for Jade Agent Behavior Components. In: Proceedings of the IEEE\/WIC\/ACM Int. Conf. on Intelligent Agent Technology, pp. 149\u2013154 (2011)","key":"9_CR2","DOI":"10.1109\/WI-IAT.2011.120"},{"issue":"3","key":"9_CR3","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/s10458-006-0005-z","volume":"13","author":"C. Isbell","year":"2006","unstructured":"Isbell, C., Kearns, M., Singh, S., Shelton, C., Stone, P., Kormann, D.: Cobot in LambdaMOO: A Social Statistics Agent. Autonomous Agents and Multiagent Systems\u00a013(3), 327\u2013354 (2006)","journal-title":"Autonomous Agents and Multiagent Systems"},{"key":"9_CR4","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1145\/1597735.1597738","volume-title":"Proceedings of the 15th International Conference on Knowledge Capture","author":"W.B. Knox","year":"2009","unstructured":"Knox, W.B., Stone, P.: Interactively Shaping Agents via Human Reinforcement - The TAMER Framework. In: Proceedings of the 15th International Conference on Knowledge Capture, pp. 9\u201316. ACM, New York (2009)"},{"unstructured":"Knox, W.B., Stone, P.: Combining manual feedback with subsequent MDP reward signals for reinforcement learning. In: Proceedings of the 9th Int. Conference on Autonomous Agents and Multiagent Systems, vol.\u00a01, pp. 5\u201312. AAMAS (2010)","key":"9_CR5"},{"unstructured":"Kuhlmann, G., Stone, P., Mooney, R.J., Shavlik, J.W.: Guiding a Reinforcement Learner With Natural Language Advice: Initial Results in RoboCup Soccer. In: Proceedings of the AAAI Workshop on Supervisory Control of Learning and Adaptive Systems (2004)","key":"9_CR6"},{"unstructured":"Le, N.T., Menzel, W., Pinkwart, N.: Considering Ill-definedness of Problems From The Aspect of Solution Space. In: Proceedings of the 23rd International Florida Artificial Intelligence Conference (FLAIRS), pp. 534\u2013535. AAAI Press (2010)","key":"9_CR7"},{"key":"9_CR8","first-page":"539","volume-title":"Proceedings of The 1st International Workshop on Issues and Challenges in Social Computing (WICSOC), held at the IEEE International Conference on Information Reuse and Integration (IRI)","author":"N.T. Le","year":"2011","unstructured":"Le, N.T., M\u00e4rtin, L., Pinkwart, N.: Learning Capabilities of Agents in Social Systems. In: Proceedings of The 1st International Workshop on Issues and Challenges in Social Computing (WICSOC), held at the IEEE International Conference on Information Reuse and Integration (IRI), pp. 539\u2013544. IEEE, NJ (2011)"},{"doi-asserted-by":"crossref","unstructured":"Moreno, D.L., Regueiro, C.V., Iglesias, R., Barro, S.: Using Prior Knowledge to Improve Reinforcement Learning in Mobile Robotics. In: Proceedings of Towards Autonomous Robotic Systems (TAROS), Technical Report Series, Report Number CSM-415, Department of Computer Science, University of Essex (2004)","key":"9_CR9","DOI":"10.1007\/11551188_10"},{"unstructured":"Ng, A.Y., Kim, H.J., Jordan, M.I., Sastry, S.: Inverted Autonomous Helicopter Flight Via Reinforcement Learning. In: International Symposium on Experimental Robotics. MIT Press (2004)","key":"9_CR10"},{"issue":"3","key":"9_CR11","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L. Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative Multi-agent Learning: The State of the Art. Autonomous Agents and Multi-Agent Systems\u00a011(3), 387\u2013434 (2005)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"9_CR12","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/978-3-540-74024-7_9","volume-title":"RoboCup 2006: Robot Soccer World Cup X","author":"M. Saggar","year":"2007","unstructured":"Saggar, M., D\u2019Silva, T., Kohl, N., Stone, P.: Autonomous Learning of Stable Quadruped Locomotion. In: Lakemeyer, G., Sklar, E., Sorrenti, D.G., Takahashi, T. (eds.) RoboCup 2006: Robot Soccer World Cup X. LNCS (LNAI), vol.\u00a04434, pp. 98\u2013109. Springer, Heidelberg (2007)"},{"unstructured":"Schneider, J., Wong, W.K., Moore, A., Riedmiller, M.: Distributed Value Functions. In: Proceedings of the 16th International Conference on Machine Learning, pp. 371\u2013378. Morgan Kaufmann (1999)","key":"9_CR13"},{"doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)","key":"9_CR14","DOI":"10.1109\/TNN.1998.712192"},{"unstructured":"Taylor, M.E., Suay, H.B., Chernova, S.: Integrating Reinforcement Learning with Human Demonstrations of Varying Ability. In: Proceedings of the 10th Int. Conference on Autonomous Agents and Multiagent Systems, pp. 617\u2013624. AAMAS (2011)","key":"9_CR15"},{"key":"9_CR16","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/3-540-48035-8_14","volume-title":"Developments in Applied Artificial Intelligence","author":"R. Thawonmas","year":"2002","unstructured":"Thawonmas, R., Hirayama, J.-I., Takeda, F.: Learning from Human Decision-Making Behaviors - An Application to RoboCup Software Agents. In: Hendtlass, T., Ali, M. (eds.) IEA\/AIE 2002. LNCS (LNAI), vol.\u00a02358, pp. 136\u2013145. Springer, Heidelberg (2002)"},{"key":"9_CR17","first-page":"64","volume-title":"Collaborative-learning: Cognitive","author":"G. Wei\u00df","year":"1999","unstructured":"Wei\u00df, G., Dillenbourg, P.: What is \u2019multi\u2019 in Multi-agent Learning. In: Dillenbourg (ed.) Collaborative-learning: Cognitive, pp. 64\u201380. Pergamon Press, Oxford (1999)"}],"container-title":["Lecture Notes in Computer Science","Agent and Multi-Agent Systems. Technologies and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-30947-2_9.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,18]],"date-time":"2022-01-18T16:54:09Z","timestamp":1642524849000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-30947-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642309465","9783642309472"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-30947-2_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}