{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T12:02:23Z","timestamp":1725796943939},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319088631"},{"type":"electronic","value":"9783319088648"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-08864-8_19","type":"book-chapter","created":{"date-parts":[[2014,7,8]],"date-time":"2014-07-08T09:55:33Z","timestamp":1404813333000},"page":"198-209","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement-Driven Shaping of Sequence Learning in Neural Dynamics"],"prefix":"10.1007","author":[{"given":"Matthew","family":"Luciw","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sohrob","family":"Kazerounian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulia","family":"Sandamirskaya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregor","family":"Sch\u00f6ner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"19_CR1","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/BF00337259","volume":"27","author":"S. Amari","year":"1977","unstructured":"Amari, S.: Dynamics of pattern formation in lateral-inhibition type neural fields. Biological Cybernetics\u00a027, 77\u201387 (1977)","journal-title":"Biological Cybernetics"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Asada, M., Noda, S., Tawaratsumida, S., Hosoda, K.: Purposive behavior acquisition for a real robot by vision-based reinforcement learning. In: Recent Advances in Robot Learning, pp. 163\u2013187. Springer (1996)","DOI":"10.1007\/978-1-4613-0471-5_7"},{"issue":"5","key":"19_CR3","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1177\/02783640022066950","volume":"19","author":"E. Bicho","year":"2000","unstructured":"Bicho, E., Mallet, P., Sch\u00f6ner, G.: Target representation on an autonomous vehicle with low-level sensors. The International Journal of Robotics Research\u00a019(5), 424\u2013447 (2000)","journal-title":"The International Journal of Robotics Research"},{"issue":"3","key":"19_CR4","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1177\/105971239400200302","volume":"2","author":"M. Colombetti","year":"1994","unstructured":"Colombetti, M., Dorigo, M.: Training agents to perform sequential behavior. Adaptive Behavior\u00a02(3), 247\u2013275 (1994)","journal-title":"Adaptive Behavior"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Dorigo, M.: Robot shaping: an experiment in behaviour engineering. The MIT Press (1998)","DOI":"10.7551\/mitpress\/5988.001.0001"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Duran, B., Sandamirskaya, Y.: Neural dynamics of hierarchically organized sequences: a robotic implementation. In: Proceedings of 2012 IEEE-RAS International Conference on Humanoid Robots, Humanoids (2012)","DOI":"10.1109\/HUMANOIDS.2012.6651544"},{"key":"19_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-3-642-33269-2_4","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2012","author":"B. Dur\u00e1n","year":"2012","unstructured":"Dur\u00e1n, B., Sandamirskaya, Y., Sch\u00f6ner, G.: A dynamic field architecture for the generation of hierarchically organized sequences. In: Villa, A.E.P., Duch, W., \u00c9rdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part I. LNCS, vol.\u00a07552, pp. 25\u201332. Springer, Heidelberg (2012)"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Frank, M., Leitner, J., Stollenga, M., F\u00f6rster, A., Schmidhuber, J.: Curiosity driven reinforcement learning for motion planning on humanoids. Frontiers in Neurorobotics\u00a07 (2013)","DOI":"10.3389\/fnbot.2013.00025"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Gomez, F., Miikkulainen, R.: 2-D pole-balancing with recurrent evolutionary networks. In: Proceedings of the International Conference on Artificial Neural Networks, pp. 425\u2013430. Citeseer (1998)","DOI":"10.1007\/978-1-4471-1599-1_63"},{"key":"19_CR10","unstructured":"Graziano, V., Gomez, F.J., Ring, M.B., Schmidhuber, J.: T-learning. CoRR abs\/1201.0292 (2012)"},{"key":"19_CR11","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/0022-2496(78)90016-0","volume":"3","author":"S. Grossberg","year":"1978","unstructured":"Grossberg, S.: Behavioral contrast in short-term memory: Serial binary memory models or parallel continuous memory models? Journal of Mathematical Psychology\u00a03, 199\u2013219 (1978)","journal-title":"Journal of Mathematical Psychology"},{"issue":"1","key":"19_CR12","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1121\/1.3589258","volume":"130","author":"S. Grossberg","year":"2011","unstructured":"Grossberg, S., Kazerounian, S.: Laminar cortical dynamics of conscious speech perception: Neural model of phonemic restoration using subsequent context in noise. The Journal of the Acoustical Society of America\u00a0130(1), 440\u2013460 (2011)","journal-title":"The Journal of the Acoustical Society of America"},{"key":"19_CR13","unstructured":"Gullapalli, V.: Reinforcement learning and its application to control. PhD thesis, Citeseer (1992)"},{"issue":"1","key":"19_CR14","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/TRO.2008.2010360","volume":"25","author":"G. Indiveri","year":"2009","unstructured":"Indiveri, G.: Swedish wheeled omnidirectional mobile robots: kinematics analysis and control. IEEE Transactions on Robotics\u00a025(1), 164\u2013171 (2009)","journal-title":"IEEE Transactions on Robotics"},{"key":"19_CR15","unstructured":"James, M.R., Singh, S.: Sarsalandmark: an algorithm for learning in pomdps with landmarks. In: Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems-Volume 1, pp. 585\u2013591. International Foundation for Autonomous Agents and Multiagent Systems (2009)"},{"key":"19_CR16","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbing","year":"1996","unstructured":"Kaelbing, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Kazerounian, S., Luciw, M., Richter, M., Sandamirskaya, Y.: Autonomous reinforcement of behavioral sequences in neural dynamics. In: International Joint Conference on Neural Networks, IJCNN (2013)","DOI":"10.1109\/IJCNN.2013.6706877"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Konidaris, G., Barto, A.: Autonomous shaping: Knowledge transfer in reinforcement learning. In: Proceedings of the 23rd international conference on Machine learning, pp. 489\u2013496. ACM (2006)","DOI":"10.1145\/1143844.1143906"},{"key":"19_CR19","unstructured":"Loch, J., Singh, S.: Using eligibility traces to find the best memoryless policy in partially observable markov decision processes. In: Proceedings of the Fifteenth International Conference on Machine Learning. Citeseer (1998)"},{"key":"19_CR20","first-page":"181","volume":"94","author":"M.J. Mataric","year":"1994","unstructured":"Mataric, M.J.: Reward functions for accelerated learning. ICML\u00a094, 181\u2013189 (1994)","journal-title":"ICML"},{"key":"19_CR21","unstructured":"McGovern, A., Sutton, R.S., Fagg, A.H.: Roles of macro-actions in accelerating reinforcement learning. In: Grace Hopper celebration of women in computing, vol.\u00a01317 (1997)"},{"issue":"3","key":"19_CR22","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1901\/jeab.2004.82-317","volume":"82","author":"G.B. Peterson","year":"2004","unstructured":"Peterson, G.B.: A day of great illumination: Bf skinner\u2019s discovery of shaping. Journal of the Experimental Analysis of Behavior\u00a082(3), 317\u2013328 (2004)","journal-title":"Journal of the Experimental Analysis of Behavior"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Piaget, J.: The origins of intelligence in children. International Universities Press, New York (1952)","DOI":"10.1037\/11494-000"},{"key":"19_CR24","unstructured":"Randlov, J., Alstrom, P.: Learning to drive a bicycle using reinforcement learning and shaping. In: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 463\u2013471 (1998)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Richter, M., Sandamirskaya, Y., Sch\u00f6ner, G.: A robotic architecture for action selection and behavioral organization inspired by human cognition. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, IROS (2012)","DOI":"10.1109\/IROS.2012.6386153"},{"key":"19_CR26","unstructured":"Rummery, G., Niranjan, M.: On-line Q-learning using connectionist systems. University of Cambridge, Department of Engineering (1994)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Sandamirskaya, Y., Richter, M., Sch\u00f6ner, G.: A neural-dynamic architecture for behavioral organization of an embodied agent. In: IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL EPIROB 2011 (2011)","DOI":"10.1109\/DEVLRN.2011.6037353"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Sandamirskaya, Y., Sch\u00f6ner, G.: Dynamic field theory of sequential action: A model and its implementation on an embodied agent. In: Scassellati, B., Deak, G. (eds.) International Conference on Development and Learning ICDL 2008, paper 53, 8 pages (2008)","DOI":"10.1109\/DEVLRN.2008.4640818"},{"issue":"10","key":"19_CR29","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1016\/j.neunet.2010.07.012","volume":"23","author":"Y. Sandamirskaya","year":"2010","unstructured":"Sandamirskaya, Y., Sch\u00f6ner, G.: An embodied account of serial order: How instabilities drive sequence generation. Neural Networks\u00a023(10), 1164\u20131179 (2010)","journal-title":"Neural Networks"},{"issue":"3","key":"19_CR30","first-page":"231","volume":"22","author":"L.M. Sasksida","year":"1998","unstructured":"Sasksida, L.M., Raymond, S.M., Touretzky, D.S.: Shaping robot behavior using principles from instrumental conditioning. Robotics and Autonomous Systems\u00a022(3), 231\u2013249 (1998)","journal-title":"Robotics and Autonomous Systems"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: Curious model-building control systems. In: Proceedings of the International Joint Conference on Neural Networks, Singapore. Volume\u00a02, pp. 1458\u20131463. IEEE Press (1991)","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"19_CR32","first-page":"10571","volume-title":"International Encyclopedia of the Social & Behavioral Sciences, Oxford, Pergamon","author":"G. Sch\u00f6ner","year":"2002","unstructured":"Sch\u00f6ner, G.: Dynamical systems approaches to neural systems and behavior. In: Smelser, N.J., Baltes, P.B. (eds.) International Encyclopedia of the Social & Behavioral Sciences, Oxford, Pergamon, pp. 10571\u201310575. Pergamon Press, Oxford (2002)"},{"key":"19_CR33","unstructured":"Selfridge, O.G., Sutton, R.S., Barto, A.G.: Training and tracking in robotics. In: IJCAI, pp. 670\u2013672. Citeseer (1985)"},{"key":"19_CR34","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.neunet.2011.10.004","volume":"26","author":"M.R. Silver","year":"2012","unstructured":"Silver, M.R., Grossberg, S., Bullock, D., Histed, M.H., Miller, E.K.: A neural model of sequential movement planning and control of eye movements: Item-order-rank working memory and saccade selection by the supplementary eye fields. Neural Networks\u00a026, 29\u201358 (2012)","journal-title":"Neural Networks"},{"key":"19_CR35","unstructured":"Skinner, B.F.: The behavior of organisms: An experimental analysis (1938)"},{"key":"19_CR36","volume-title":"Robot modeling and control","author":"M.W. Spong","year":"2006","unstructured":"Spong, M.W., Hutchinson, S., Vidyasagar, M.: Robot modeling and control. John Wiley & Sons, New York (2006)"},{"key":"19_CR37","unstructured":"Sutton, R., Barto, A.: Reinforcement learning: An introduction, vol.\u00a01. Cambridge Univ. Press (1998)"},{"key":"19_CR38","volume-title":"Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches","author":"S.B. Thrun","year":"1992","unstructured":"Thrun, S.B.: The role of exploration in learning control. In: Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches. Van Nostrand Reinhold, New York (1992)"},{"issue":"3-4","key":"19_CR39","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1177\/105971239700500302","volume":"5","author":"D.S. Touretzky","year":"1997","unstructured":"Touretzky, D.S., Saksida, L.M.: Operant conditioning in skinnerbots. Adaptive Behavior\u00a05(3-4), 219\u2013247 (1997)","journal-title":"Adaptive Behavior"},{"key":"19_CR40","unstructured":"Webots: Commercial Mobile Robot Simulation Software, http:\/\/www.cyberbotics.com"},{"issue":"02","key":"19_CR41","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1142\/S0219843604000149","volume":"1","author":"J. Weng","year":"2004","unstructured":"Weng, J.: Developmental robotics: Theory and experiments. International Journal of Humanoid Robotics\u00a01(02), 199\u2013236 (2004)","journal-title":"International Journal of Humanoid Robotics"}],"container-title":["Lecture Notes in Computer Science","From Animals to Animats 13"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-08864-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,21]],"date-time":"2020-08-21T22:26:27Z","timestamp":1598048787000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-08864-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319088631","9783319088648"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-08864-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]}}}