{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:19:05Z","timestamp":1750306745205,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":113,"publisher":"ACM","license":[{"start":{"date-parts":[[2013,8,4]],"date-time":"2013-08-04T00:00:00Z","timestamp":1375574400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004963","name":"Seventh Framework Programme","doi-asserted-by":"publisher","award":["287615 (PARLANCE)"],"award-info":[{"award-number":["287615 (PARLANCE)"]}],"id":[{"id":"10.13039\/501100004963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2013,8,4]]},"DOI":"10.1145\/2493525.2493530","type":"proceedings-article","created":{"date-parts":[[2013,7,30]],"date-time":"2013-07-30T13:40:50Z","timestamp":1375191650000},"page":"19-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Machine learning for interactive systems and robots"],"prefix":"10.1145","author":[{"given":"Heriberto","family":"Cuay\u00e1huitl","sequence":"first","affiliation":[{"name":"Heriot-Watt University, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martijn","family":"van Otterlo","sequence":"additional","affiliation":[{"name":"Radboud University Nijmegen, Nijmegen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nina","family":"Dethlefs","sequence":"additional","affiliation":[{"name":"Heriot-Watt University, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lutz","family":"Frommberger","sequence":"additional","affiliation":[{"name":"University of Bremen, Bremen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2013,8,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/3120007.3120018"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.07.002"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"e_1_3_2_1_5_1","first-page":"12","volume-title":"ICML","author":"Atkeson C. G.","year":"1997","unstructured":"C. G. Atkeson and S. Schaal . Robot Learning From Demonstration . In ICML , pages 12 -- 20 , 1997 . C. G. Atkeson and S. Schaal. Robot Learning From Demonstration. In ICML, pages 12--20, 1997."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2493527"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022140919877"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"e_1_3_2_1_9_1","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"Bishop C. M.","year":"2006","unstructured":"C. M. Bishop . Pattern Recognition and Machine Learning (Information Science and Statistics) . Springer-Verlag New York, Inc. , Secaucus, NJ, USA , 2006 . C. M. Bishop. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag New York, Inc., Secaucus, NJ, USA, 2006."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326844"},{"key":"e_1_3_2_1_12_1","first-page":"478","volume-title":"IJCAI","author":"Boutilier C.","year":"1999","unstructured":"C. Boutilier . Sequential Optimality and Coordination in Multiagent Systems . In IJCAI , pages 478 -- 485 , 1999 . C. Boutilier. Sequential Optimality and Coordination in Multiagent Systems. In IJCAI, pages 478--485, 1999."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-010-9197-9"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157693"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2898607.2898816"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/1734454.1734562"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2500422"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.21437\/Interspeech.2011-298","volume-title":"INTERSPEECH","author":"Cuay\u00e1huitl H.","year":"2011","unstructured":"H. Cuay\u00e1huitl and N. Dethlefs . Optimizing situated dialogue management in unknown environments . In INTERSPEECH , pages 1009 -- 1012 , 2011 . H. Cuay\u00e1huitl and N. Dethlefs. Optimizing situated dialogue management in unknown environments. In INTERSPEECH, pages 1009--1012, 2011."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1966407.1966410"},{"key":"e_1_3_2_1_23_1","first-page":"7","volume-title":"Dialogue Systems Using Online Learning: Beyond Empirical Methods. In NAACL-HLT Workshop on Future Directions and Needs in the Spoken Dialog Community: Tools and Data, SDCTD '12","author":"Cuay\u00e1huitl H.","year":"2012","unstructured":"H. Cuay\u00e1huitl and N. Dethlefs . Dialogue Systems Using Online Learning: Beyond Empirical Methods. In NAACL-HLT Workshop on Future Directions and Needs in the Spoken Dialog Community: Tools and Data, SDCTD '12 , pages 7 -- 8 , Stroudsburg, PA, USA , 2012 . Association for Computational Linguistics. H. Cuay\u00e1huitl and N. Dethlefs. Dialogue Systems Using Online Learning: Beyond Empirical Methods. In NAACL-HLT Workshop on Future Directions and Needs in the Spoken Dialog Community: Tools and Data, SDCTD '12, pages 7--8, Stroudsburg, PA, USA, 2012. Association for Computational Linguistics."},{"key":"e_1_3_2_1_24_1","first-page":"27","volume-title":"ECAI Workshop on Machine Learning for Interactive Systems (MLIS)","author":"Cuay\u00e1huitl H.","year":"2012","unstructured":"H. Cuay\u00e1huitl and N. Dethlefs . Hierarchical multiagent reinforcement learning for coordinating verbal and non-verbal actions in robots . In ECAI Workshop on Machine Learning for Interactive Systems (MLIS) , pages 27 -- 29 , Montpellier, France , 2012 . H. Cuay\u00e1huitl and N. Dethlefs. Hierarchical multiagent reinforcement learning for coordinating verbal and non-verbal actions in robots. In ECAI Workshop on Machine Learning for Interactive Systems (MLIS), pages 27--29, Montpellier, France, 2012."},{"key":"e_1_3_2_1_25_1","first-page":"95","volume-title":"COLING (Demos)","author":"Cuay\u00e1huitl H.","year":"2012","unstructured":"H. Cuay\u00e1huitl , I. Kruijff-Korbayov\u00e1 , and N. Dethlefs . Hierarchical Dialogue Policy Learning using Flexible State Transitions and Linear Function Approximation . In COLING (Demos) , pages 95 -- 102 , 2012 . H. Cuay\u00e1huitl, I. Kruijff-Korbayov\u00e1, and N. Dethlefs. Hierarchical Dialogue Policy Learning using Flexible State Transitions and Linear Function Approximation. In COLING (Demos), pages 95--102, 2012."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622262.1622268"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390194"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1046920.1088690"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2493531"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1160633.1160762"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2493535"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2493534"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511973000","volume-title":"Machine Learning: The Art and Science of Algorithms that Make Sense of Data","author":"Flach P.","year":"2012","unstructured":"P. Flach . Machine Learning: The Art and Science of Algorithms that Make Sense of Data . Cambridge University Press , 2012 . P. Flach. Machine Learning: The Art and Science of Algorithms that Make Sense of Data. Cambridge University Press, 2012."},{"key":"e_1_3_2_1_34_1","volume-title":"Technical Report UCRL-ID-148494","author":"Fodor I. K.","year":"2002","unstructured":"I. K. Fodor . A Survey of Dimension Reduction Techniques . Technical Report UCRL-ID-148494 , Center for Applied Scientific Computing , Lawrence Livermore National Laboratory, June 2002 . I. K. Fodor. A Survey of Dimension Reduction Techniques. Technical Report UCRL-ID-148494, Center for Applied Scientific Computing, Lawrence Livermore National Laboratory, June 2002."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.5555\/1972513"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1177\/1059712310391484"},{"key":"e_1_3_2_1_37_1","first-page":"789","volume-title":"Encycl. of Machine Learning","author":"F\u00fcrnkranz J.","year":"2010","unstructured":"J. F\u00fcrnkranz and E. H\u00fcllermeier . Preference Learning . In Encycl. of Machine Learning , pages 789 -- 795 . 2010 . J. F\u00fcrnkranz and E. H\u00fcllermeier. Preference Learning. In Encycl. of Machine Learning, pages 789--795. 2010."},{"key":"e_1_3_2_1_38_1","volume-title":"Preference-based Reinforcement Learning: A Formal Framework and a Policy Iteration Algorithm. Machine Learning, 89(1-2)","author":"F\u00fcrnkranz J.","year":"2012","unstructured":"J. F\u00fcrnkranz , E. H\u00fcllermeier , W. Cheng , and S.-H. Park . Preference-based Reinforcement Learning: A Formal Framework and a Policy Iteration Algorithm. Machine Learning, 89(1-2) , 2012 . J. F\u00fcrnkranz, E. H\u00fcllermeier, W. Cheng, and S.-H. Park. Preference-based Reinforcement Learning: A Formal Framework and a Policy Iteration Algorithm. Machine Learning, 89(1-2), 2012."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163950"},{"key":"e_1_3_2_1_40_1","first-page":"72","volume-title":"Advanced Lectures on Machine Learning","author":"Ghahramani Z.","year":"2003","unstructured":"Z. Ghahramani . Unsupervised Learning . In Advanced Lectures on Machine Learning , pages 72 -- 112 , 2003 . Z. Ghahramani. Unsupervised Learning. In Advanced Lectures on Machine Learning, pages 72--112, 2003."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-006-7035-4"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005246"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225072"},{"key":"e_1_3_2_1_44_1","volume-title":"Reinforcement Learning: State-of-the-Art","author":"Hester T.","year":"2012","unstructured":"T. Hester and P. Stone . Learning and using models . In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art , chapter 4. Springer , 2012 . T. Hester and P. Stone. Learning and using models. In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art, chapter 4. Springer, 2012."},{"key":"e_1_3_2_1_45_1","first-page":"242","volume-title":"ICML","author":"Hu J.","year":"1998","unstructured":"J. Hu and M. P. Wellman . Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm . In ICML , pages 242 -- 250 , 1998 . J. Hu and M. P. Wellman. Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm. In ICML, pages 242--250, 1998."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2493533"},{"key":"e_1_3_2_1_47_1","first-page":"200","volume-title":"ICML","author":"Joachims T.","year":"1999","unstructured":"T. Joachims . Transductive Inference for Text Classification using Support Vector Machines . In ICML , pages 200 -- 209 , 1999 . T. Joachims. Transductive Inference for Text Classification using Support Vector Machines. In ICML, pages 200--209, 1999."},{"key":"e_1_3_2_1_48_1","first-page":"237","volume":"4","author":"Kaelbling L.","year":"1996","unstructured":"L. Kaelbling , M. Littman , and A. Moore . Reinforcement Learning: A Survey. JAIR , 4 : 237 -- 285 , 1996 . L. Kaelbling, M. Littman, and A. Moore. Reinforcement Learning: A Survey. JAIR, 4:237--285, 1996.","journal-title":"Reinforcement Learning: A Survey. JAIR"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-012-0163-x"},{"key":"e_1_3_2_1_50_1","volume-title":"Reinforcement Learning: State-of-the-Art","author":"Kober J.","year":"2012","unstructured":"J. Kober and J. Peters . Reinforcement learning in robotics: A survey . In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art , chapter 18. Springer , 2012 . J. Kober and J. Peters. Reinforcement learning in robotics: A survey. In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art, chapter 18. Springer, 2012."},{"key":"e_1_3_2_1_51_1","volume-title":"University of Massachusetts Amherst","author":"Konidaris G.","year":"2011","unstructured":"G. Konidaris . Autonomous Robot Skill Acquisition. PhD thesis, Department of Computer Science , University of Massachusetts Amherst , May 2011 . G. Konidaris. Autonomous Robot Skill Acquisition. PhD thesis, Department of Computer Science, University of Massachusetts Amherst, May 2011."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2493528"},{"key":"e_1_3_2_1_53_1","first-page":"1107","volume-title":"IJCAI","author":"Konidaris G.","year":"2009","unstructured":"G. Konidaris and A. G. Barto . Efficient Skill Learning using Abstraction Selection . In IJCAI , pages 1107 -- 1112 , 2009 . G. Konidaris and A. G. Barto. Efficient Skill Learning using Abstraction Selection. In IJCAI, pages 1107--1112, 2009."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143906"},{"issue":"3","key":"e_1_3_2_1_55_1","first-page":"249","article-title":"Supervised Machine Learning","volume":"31","author":"Kotsiantis S. B.","year":"2007","unstructured":"S. B. Kotsiantis . Supervised Machine Learning : A Review of Classification Techniques. Informatica (Slovenia) , 31 ( 3 ): 249 -- 268 , 2007 . S. B. Kotsiantis. Supervised Machine Learning: A Review of Classification Techniques. Informatica (Slovenia), 31(3):249--268, 2007.","journal-title":"A Review of Classification Techniques. Informatica (Slovenia)"},{"key":"e_1_3_2_1_56_1","first-page":"535","volume-title":"ICML","author":"Lauer M.","year":"2000","unstructured":"M. Lauer and M. A. Riedmiller . An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems . In ICML , pages 535 -- 542 , 2000 . M. Lauer and M. A. Riedmiller. An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems. In ICML, pages 535--542, 2000."},{"key":"e_1_3_2_1_57_1","volume-title":"Reinforcement Learning: State-of-the-Art","author":"Lazaric A.","year":"2012","unstructured":"A. Lazaric . Transfer in reinforcement learning: A framework and a survey . In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art , chapter 5. Springer , 2012 . A. Lazaric. Transfer in reinforcement learning: A framework and a survey. In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art, chapter 5. Springer, 2012."},{"key":"e_1_3_2_1_58_1","first-page":"2685","volume-title":"INTERSPEECH","author":"Lemon O.","year":"2007","unstructured":"O. Lemon and O. Pietquin . Machine Learning for Spoken Dialogue Systems . In INTERSPEECH , pages 2685 -- 2688 , 2007 . O. Lemon and O. Pietquin. Machine Learning for Spoken Dialogue Systems. In INTERSPEECH, pages 2685--2688, 2007."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091574.3091594"},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings Of The National Conference On Artificial Intelligence (AAAI)","author":"Liu Y.","year":"2006","unstructured":"Y. Liu and P. Stone . Value-function-based transfer for reinforcement learning using structure mapping . In Proceedings Of The National Conference On Artificial Intelligence (AAAI) , Boston, MA , July 2006 . Y. Liu and P. Stone. Value-function-based transfer for reinforcement learning using structure mapping. In Proceedings Of The National Conference On Artificial Intelligence (AAAI), Boston, MA, July 2006."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/3121646.3121650"},{"key":"e_1_3_2_1_62_1","volume-title":"Machine learning","author":"Mitchell T. M.","year":"1997","unstructured":"T. M. Mitchell . Machine learning . McGraw Hill series in Computer Science. McGraw-Hill , 1997 . T. M. Mitchell. Machine learning. McGraw Hill series in Computer Science. McGraw-Hill, 1997."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225042"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/1957656.1957786"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070719.2070725"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007692713085"},{"key":"e_1_3_2_1_67_1","volume-title":"Human-level artificial intelligence? be serious! AI Magazine","author":"Nilsson N. J.","year":"2005","unstructured":"N. J. Nilsson . Human-level artificial intelligence? be serious! AI Magazine , 2005 . N. J. Nilsson. Human-level artificial intelligence? be serious! AI Magazine, 2005."},{"key":"e_1_3_2_1_68_1","volume-title":"Reinforcement Learning: State-of-the-Art","author":"Nowe A.","year":"2012","unstructured":"A. Nowe , P. Vrancx , and Y.-M. D. Hauwere . Game theory and multi-agent reinforcement learning . In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art , chapter 14. Springer , 2012 . A. Nowe, P. Vrancx, and Y.-M. D. Hauwere. Game theory and multi-agent reinforcement learning. In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art, chapter 14. Springer, 2012."},{"key":"e_1_3_2_1_69_1","volume-title":"M","author":"Oliehoek F. A.","year":"2012","unstructured":"F. A. Oliehoek . Decentralized POMD Ps . In M . Wiering and M. van Otterlo, editors, Reinforcement Learning : State-of-the-Art, chapter 15. Springer , 2012 . F. A. Oliehoek. Decentralized POMDPs. In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art, chapter 15. Springer, 2012."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2500421"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"e_1_3_2_1_73_1","volume-title":"Understanding Intelligence","author":"Pfeifer R.","year":"1999","unstructured":"R. Pfeifer and C. Scheier . Understanding Intelligence . The MIT Press, Cambridge , Massachusetts , 1999 . R. Pfeifer and C. Scheier. Understanding Intelligence. The MIT Press, Cambridge, Massachusetts, 1999."},{"key":"e_1_3_2_1_74_1","volume-title":"ISAIM","author":"Poupart P.","year":"2008","unstructured":"P. Poupart and N. A. Vlassis . Model-based Bayesian Reinforcement Learning in Partially Observable Domains . In ISAIM , 2008 . P. Poupart and N. A. Vlassis. Model-based Bayesian Reinforcement Learning in Partially Observable Domains. In ISAIM, 2008."},{"key":"e_1_3_2_1_75_1","volume-title":"Proceedings of the Third International Symposium on Adaptive Systems: Evolutionary Computation and Probabilistic Graphical Models","author":"Pyeatt L. D.","year":"1998","unstructured":"L. D. Pyeatt and A. E. Howe . Decision Tree Function Approximation in Reinforcement Learning. Technical report , In Proceedings of the Third International Symposium on Adaptive Systems: Evolutionary Computation and Probabilistic Graphical Models , 1998 . L. D. Pyeatt and A. E. Howe. Decision Tree Function Approximation in Reinforcement Learning. Technical report, In Proceedings of the Third International Symposium on Adaptive Systems: Evolutionary Computation and Probabilistic Graphical Models, 1998."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273592"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2010.12.002"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_32"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2493526"},{"issue":"1","key":"e_1_3_2_1_80_1","first-page":"199","article-title":"Wizard of oz studies in hri: A systematic review and new reporting guidelines","volume":"1","author":"Riek L. D.","year":"2012","unstructured":"L. D. Riek . Wizard of oz studies in hri: A systematic review and new reporting guidelines . Journal of Human-Robot Interaction , 1 ( 1 ): 199 -- 136 , 2012 . L. D. Riek. Wizard of oz studies in hri: A systematic review and new reporting guidelines. Journal of Human-Robot Interaction, 1(1):199--136, 2012.","journal-title":"Journal of Human-Robot Interaction"},{"key":"e_1_3_2_1_81_1","volume-title":"A Multitask Representation Using Reusable Local Policy Templates","author":"Rosman B.","year":"2012","unstructured":"B. Rosman and S. Ramamoorthy . A Multitask Representation Using Reusable Local Policy Templates . 2012 . B. Rosman and S. Ramamoorthy. A Multitask Representation Using Reusable Local Policy Templates. 2012."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-011-0124-9"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888906000944"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102454"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_24"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008942012299"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2011.6005223"},{"key":"e_1_3_2_1_89_1","volume-title":"Introduction to Reinforcement Learning","author":"Sutton R. S.","year":"1998","unstructured":"R. S. Sutton and A. G. Barto . Introduction to Reinforcement Learning . MIT Press , Cambridge, MA, USA , 1 st edition, 1998 . R. S. Sutton and A. G. Barto. Introduction to Reinforcement Learning. MIT Press, Cambridge, MA, USA, 1st edition, 1998.","edition":"1"},{"key":"e_1_3_2_1_90_1","first-page":"1057","volume-title":"NIPS","author":"Sutton R. S.","year":"1999","unstructured":"R. S. Sutton , D. A. McAllester , S. P. Singh , and Y. Mansour . Policy Gradient Methods for Reinforcement Learning with Function Approximation . In NIPS , pages 1057 -- 1063 , 1999 . R. S. Sutton, D. A. McAllester, S. P. Singh, and Y. Mansour. Policy Gradient Methods for Reinforcement Learning with Function Approximation. In NIPS, pages 1057--1063, 1999."},{"key":"e_1_3_2_1_91_1","first-page":"761","volume-title":"AAMAS","author":"Sutton R. S.","year":"2011","unstructured":"R. S. Sutton , J. Modayil , M. Delp , T. Degris , P. M. Pilarski , A. White , and D. Precup . Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction. In L. Sonenberg, P. Stone, K. Tumer, and P. Yolum, editors , AAMAS , pages 761 -- 768 . IFAAMAS, 2011 . R. S. Sutton, J. Modayil, M. Delp, T. Degris, P. M. Pilarski, A. White, and D. Precup. Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction. In L. Sonenberg, P. Stone, K. Tumer, and P. Yolum, editors, AAMAS, pages 761--768. IFAAMAS, 2011."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"e_1_3_2_1_93_1","volume-title":"Morgan and Claypool Publishers","author":"Szepesv\u00e1ri C.","year":"2010","unstructured":"C. Szepesv\u00e1ri . Algorithms for Reinforcement Learning . Morgan and Claypool Publishers , 2010 . C. Szepesv\u00e1ri. Algorithms for Reinforcement Learning. Morgan and Claypool Publishers, 2010."},{"key":"e_1_3_2_1_94_1","volume-title":"M","author":"Szita I.","year":"2012","unstructured":"I. Szita . Reinforcement learning in games. In M . Wiering and M. van Otterlo, editors, Reinforcement Learning : State-of-the-Art, chapter 17. Springer , 2012 . I. Szita. Reinforcement learning in games. In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art, chapter 17. Springer, 2012."},{"key":"e_1_3_2_1_95_1","first-page":"330","volume-title":"ICML","author":"Tan M.","year":"1993","unstructured":"M. Tan . Multi-Agent Reinforcement Learning: Independent versus Cooperative Agents . In ICML , pages 330 -- 337 , 1993 . M. Tan. Multi-Agent Reinforcement Learning: Independent versus Cooperative Agents. In ICML, pages 330--337, 1993."},{"key":"e_1_3_2_1_96_1","first-page":"1633","volume":"10","author":"Taylor M.","year":"2009","unstructured":"M. Taylor and P. Stone . Transfer Learning for Reinforcement Learning Domains: A Survey. JMLR , 10 : 1633 -- 1685 , 2009 . M. Taylor and P. Stone. Transfer Learning for Reinforcement Learning Domains: A Survey. JMLR, 10:1633--1685, 2009.","journal-title":"Transfer Learning for Reinforcement Learning Domains: A Survey. JMLR"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273607"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"e_1_3_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2007.09.009"},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-1381-6_1"},{"key":"e_1_3_2_1_101_1","first-page":"489","volume-title":"ICML","author":"Thrun S.","year":"1996","unstructured":"S. Thrun and J. O'Sullivan . Discovering Structure in Multiple Learning Tasks: The TC Algorithm . In ICML , pages 489 -- 497 , 1996 . S. Thrun and J. O'Sullivan. Discovering Structure in Multiple Learning Tasks: The TC Algorithm. In ICML, pages 489--497, 1996."},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157784"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_41"},{"key":"e_1_3_2_1_104_1","volume-title":"Adversarial Reinforcement Learning","author":"Uther W.","year":"1997","unstructured":"W. Uther and M. Veloso . Adversarial Reinforcement Learning . 1997 . W. Uther and M. Veloso. Adversarial Reinforcement Learning. 1997."},{"key":"e_1_3_2_1_105_1","volume-title":"Semi-Supervised Apprenticeship Learning. JMLR: EWRL10 Workshop and Conference Proceedings, 24:131--141","author":"Valko M.","year":"2012","unstructured":"M. Valko , M. Ghavamzadeh , and A. Lazaric . Semi-Supervised Apprenticeship Learning. JMLR: EWRL10 Workshop and Conference Proceedings, 24:131--141 , 2012 . M. Valko, M. Ghavamzadeh, and A. Lazaric. Semi-Supervised Apprenticeship Learning. JMLR: EWRL10 Workshop and Conference Proceedings, 24:131--141, 2012."},{"key":"e_1_3_2_1_106_1","volume-title":"Knowledge Representation and Algorithms for Adaptive Sequential Decision Making under Uncertainty in First-Order and Relational Domains","author":"van Otterlo M.","year":"2009","unstructured":"M. van Otterlo . The Logic of Adaptive Behavior : Knowledge Representation and Algorithms for Adaptive Sequential Decision Making under Uncertainty in First-Order and Relational Domains . IOS Press , Amsterdam, The Netherlands, 2009 . M. van Otterlo. The Logic of Adaptive Behavior: Knowledge Representation and Algorithms for Adaptive Sequential Decision Making under Uncertainty in First-Order and Relational Domains. IOS Press, Amsterdam, The Netherlands, 2009."},{"key":"e_1_3_2_1_107_1","volume-title":"Reinforcement Learning: State-of-the-Art","author":"van Otterlo M.","year":"2012","unstructured":"M. van Otterlo . Solving relational and first-order logical markov decision processes : A survey . In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art , chapter 8. Springer , 2012 . M. van Otterlo. Solving relational and first-order logical markov decision processes: A survey. In M. Wiering and M. van Otterlo, editors, Reinforcement Learning: State-of-the-Art, chapter 8. Springer, 2012."},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"e_1_3_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2011.941632"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","volume-title":"van Otterlo. Reinforcement Learning: State-of-the-Art","author":"Wiering M.","year":"2012","unstructured":"M. Wiering and M. van Otterlo. Reinforcement Learning: State-of-the-Art . Springer , 2012 . M. Wiering and M. van Otterlo. Reinforcement Learning: State-of-the-Art. Springer, 2012."},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493525.2493532"},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.3115\/981658.981684"},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-010-0081-8"},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1108\/17563781211255862"}],"event":{"name":"MLIS '13: Workshop on Machine Learning for Interactive Systems","sponsor":["Heriot-Watt University Heriot-Watt University","Univ. of Bremen University of Bremen","PARLANCE PARLANCE"],"location":"Beijing China","acronym":"MLIS '13"},"container-title":["Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2493525.2493530","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2493525.2493530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:28:20Z","timestamp":1750231700000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2493525.2493530"}},"subtitle":["a brief introduction"],"short-title":[],"issued":{"date-parts":[[2013,8,4]]},"references-count":113,"alternative-id":["10.1145\/2493525.2493530","10.1145\/2493525"],"URL":"https:\/\/doi.org\/10.1145\/2493525.2493530","relation":{},"subject":[],"published":{"date-parts":[[2013,8,4]]},"assertion":[{"value":"2013-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}