{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T05:16:59Z","timestamp":1739510219231,"version":"3.37.0"},"publisher-location":"Berlin, Heidelberg","reference-count":36,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642045110"},{"type":"electronic","value":"9783642045127"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-04512-7_11","type":"book-chapter","created":{"date-parts":[[2009,11,24]],"date-time":"2009-11-24T05:03:41Z","timestamp":1259039021000},"page":"207-224","source":"Crossref","is-referenced-by-count":1,"title":["Incorporating Expert Advice into Reinforcement Learning Using Constructive Neural Networks"],"prefix":"10.1007","author":[{"given":"Robert","family":"Ollington","sequence":"first","affiliation":[]},{"given":"Peter","family":"Vamplew","sequence":"additional","affiliation":[]},{"given":"John","family":"Swanson","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"11_CR1","first-page":"81","volume":"5","author":"C.W. Anderson","year":"1993","unstructured":"Anderson, C.W.: Q-learning with hidden unit restarting. Advances in Neural Information Processing Systems\u00a05, 81\u201388 (1993)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Baird, L.: Residual algorithms: Reinforcement learning with function approximation. In: Proceedings of the Twelfth International Conference on Machine Learning, pp. 30\u201337 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"11_CR3","unstructured":"Bellemare, M., Precup, D., Rivest, F.: Reinforcement Learning Using Cascade-Correlation Neural Networks, Technical Report RL-3.04, McGill University, Canada (2004)"},{"key":"11_CR4","unstructured":"Clouse, J.: Learning from an automated training agent. In: Working Notes of the ICML 1995 Workshop on Agents that Learn from Other Agents (1995)"},{"key":"11_CR5","unstructured":"Clouse, J., Utgoff, P.: Two kinds of training information for evaluation function learning. In: Proceedings of the Ninth Annual Conference on Artificial Intelligence, pp. 596\u2013600 (1991)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Clouse, J., Utgoff, P.: A teaching method for reinforcement learning. In: Proceedings of the Ninth International Workshop on Machine Learning, pp. 92\u2013101 (1992)","DOI":"10.1016\/B978-1-55860-247-2.50017-6"},{"key":"11_CR7","first-page":"402","volume-title":"International Conference on Algorithmic Learning Theory","author":"R. Coulom","year":"2002","unstructured":"Coulom, R.: Feedforward Neural Networks in Reinforcement Learning Applied to High-dimensional Motor Control. In: International Conference on Algorithmic Learning Theory, pp. 402\u2013413. Springer, Heidelberg (2002)"},{"key":"11_CR8","first-page":"1017","volume":"8","author":"R.H. Crites","year":"1996","unstructured":"Crites, R.H., Barto, A.G.: Improving Elevator Performance Using Reinforcement Learning. Advances in Neural Information Processing Systems\u00a08, 1017\u20131023 (1996)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"11_CR9","first-page":"524","volume-title":"Advances in Neural Information Processing II","author":"S.E. Fahlman","year":"1990","unstructured":"Fahlman, S.E., Lebiere, C.: The Cascade-Correlation Learning Architecture. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing II, pp. 524\u2013532. Morgan Kauffman, San Francisco (1990)"},{"issue":"5","key":"11_CR10","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/scientificamerican1173-116","volume":"229","author":"M. Gardner","year":"1973","unstructured":"Gardner, M.: Mathematical games: Fantastic patterns traced by programmed worms. Scientific American\u00a0229(5), 116\u2013123 (1973)","journal-title":"Scientific American"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Girgen, S., Preux, P.: Incremental Basis Function Expansion in Reinforcement Learning using Cascade-Correlation Networks, Research Report No. 6505, Institut National de Recherche en Informatique et en Automatique, Lille, France (2008)","DOI":"10.1109\/ICMLA.2008.24"},{"key":"11_CR12","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/3-540-49240-2_7","volume-title":"Learning Robots","author":"A. Gro\u00dfmann","year":"1998","unstructured":"Gro\u00dfmann, A., Poli, R.: Continual Robot Learning with Constructive Neural Networks. In: Birk, A., Demiris, J. (eds.) EWLR 1997. LNCS (LNAI), vol.\u00a01545, pp. 95\u2013108. Springer, Heidelberg (1998)"},{"key":"11_CR13","unstructured":"Jun, L., Duckett, T.: Q-Learning with a Growing RBF Network for Behavior Learning in Mobile Robotics. In: Proc. IASTED International Conference on Robotics and Applications, Cambridge, USA (2005)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Kretchmar, R.M., Anderson, C.W.: Comparison of CMACs and RBFs for local function approximators in reinforcement learning. In: IEEE International Conference on Neural Networks, pp. 834\u2013837 (1997)","DOI":"10.1109\/ICNN.1997.616132"},{"issue":"1","key":"11_CR15","first-page":"251","volume":"22","author":"R. Maclin","year":"1996","unstructured":"Maclin, R., Shavlik, J.: Creating advice-taking reinforcement learners. Machine Learning\u00a022(1), 251\u2013281 (1996)","journal-title":"Machine Learning"},{"key":"11_CR16","unstructured":"Maclin, R., Shavlik, J., Torrey, L., Walker, T., Wild, E.: Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression. In: Proceedings of the 20th National Conference on Artificial Intelligence, pp. 819\u2013824 (2005)"},{"key":"11_CR17","unstructured":"Nechyba, M.C., Bagnell, J.A.: Stabilizing Human Control Strategies Through Reinforcement Learning. In: Proceedings of the IEEE Hong Kong Symp. on Robotics and Control (1999)"},{"key":"11_CR18","unstructured":"Nissen, S.: Large Scale Reinforcement Learning using Q-SARSA(\u03bb) and Cascading Neural Networks, M.Sc. Thesis, Department of Computer Science, University of Copenhagen, Denmark (2007)"},{"key":"11_CR19","unstructured":"Papudesi, V., Huber, M.: Learning from reinforcement and advice using composite reward functions. In: Proceedings of the 16th International FLAIRS Conference, pp. 361\u2013365 (2003)"},{"key":"11_CR20","unstructured":"Perkins, T.J., Precup, D.: Using Options for Knowledge Transfer in Reinforcement Learning, Technical Report 99-34, Department of Computer Science, University of Massachusetts (1999)"},{"key":"11_CR21","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1162\/neco.1991.3.2.213","volume":"3","author":"J. Platt","year":"1991","unstructured":"Platt, J.: A Resource-Allocating Network for Function Interpolation. Neural Computation\u00a03, 213\u2013225 (1991)","journal-title":"Neural Computation"},{"key":"11_CR22","unstructured":"Randlov, J., Alstrom, P.: Learning to Drive a Bicycle Using Reinforcement Learning and Shaping. In: International Conference on Machine Learning, pp. 463\u2013471 (1998)"},{"key":"11_CR23","unstructured":"Rivest, F., Precup, D.: Combining TD-learning with Cascade-correlation Networks. In: Twentieth International Conference on Machine Learning, Washington DC, pp. 632\u2013639 (2003)"},{"key":"11_CR24","unstructured":"Rummery, G., Niranjan, M.: On-line Q-Learning Using Connectionist Systems, Technical report, Cambridge University Engineering Department (1994)"},{"issue":"1-3","key":"11_CR25","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/S0925-2312(98)00117-9","volume":"28","author":"J.M. Santos","year":"1999","unstructured":"Santos, J.M., Touzet, C.: Exploration tuned reinforcement function. Neurocomputing\u00a028(1-3), 93\u2013105 (1999)","journal-title":"Neurocomputing"},{"key":"11_CR26","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1023\/A:1026242620248","volume":"18","author":"B. \u0160ter","year":"2003","unstructured":"\u0160ter, B., Dobnikar, A.: Adaptive Radial Basis Decomposition by Learning Vector Quantisation. Neural Processing Letters\u00a018, 17\u201327 (2003)","journal-title":"Neural Processing Letters"},{"key":"11_CR27","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning\u00a03, 9\u201344 (1988)","journal-title":"Machine Learning"},{"key":"11_CR28","first-page":"1038","volume-title":"Proceedings of the, Conference:Advances in Neural Information Processing Systems","author":"R.S. Sutton","year":"1996","unstructured":"Sutton, R.S.: Generalisation in reinforcement learning: Successful examples using sparse coarse coding. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Proceedings of the, Conference:Advances in Neural Information Processing Systems, pp. 1038\u20131044. The MIT Press, Cambridge (1996)"},{"key":"11_CR29","volume-title":"Reinforcement Learning","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, S.: Reinforcement Learning. MIT Press, Cambridge (1998)"},{"issue":"3","key":"11_CR30","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G.J. Tesauro","year":"1995","unstructured":"Tesauro, G.J.: Temporal difference learning and TD-Gammon. Communications of the ACM\u00a038(3), 58\u201368 (1995)","journal-title":"Communications of the ACM"},{"key":"11_CR31","unstructured":"Thrun, S., Schwartz, A.: Issues in Using Function Approximation for Reinforcement Learning. In: Proceedings of the Fourth Connectionist Models Summer School, Hillsdale, NJ (December 1993)"},{"key":"11_CR32","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/11589990_14","volume-title":"AI 2005: Advances in Artificial Intelligence","author":"P. Vamplew","year":"2005","unstructured":"Vamplew, P., Ollington, R.: Global Versus Local Constructive Function Approximation for On-Line Reinforcement Learning. In: Zhang, S., Jarvis, R.A. (eds.) AI 2005. LNCS (LNAI), vol.\u00a03809, pp. 113\u2013122. Springer, Heidelberg (2005)"},{"key":"11_CR33","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1007\/978-3-540-89378-3_37","volume-title":"AI 2008: Advances in Artificial Intelligence","author":"P. Vamplew","year":"2008","unstructured":"Vamplew, P., Yearwood, J., Dazeley, R., Berry, A.: On the Limitations of Scalarisation for Multi-objective Reinforcement Learning of Pareto Fronts. In: Wobcke, W., Zhang, M. (eds.) AI 2008. LNCS (LNAI), vol.\u00a05360, pp. 372\u2013378. Springer, Heidelberg (2008)"},{"issue":"3","key":"11_CR34","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., Dayan, P.: Q-learning. Machine Learning\u00a08(3), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"11_CR35","unstructured":"Waugh, S.G.: Extending and benchmarking Cascade-Correlation, PhD thesis, Department of Computer Science, University of Tasmania, Australia (1995)"},{"issue":"2","key":"11_CR36","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/72.661125","volume":"9","author":"L. Yingwei","year":"1998","unstructured":"Yingwei, L., Sundararajan, N., Saratchandran, P.: Performance evaluation of a sequential minimal radial basis function (rbf) neural network learning algorithm. IEEE Transactions on Neural Networks\u00a09(2), 308\u2013318 (1998)","journal-title":"IEEE Transactions on Neural Networks"}],"container-title":["Studies in Computational Intelligence","Constructive Neural Networks"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-04512-7_11.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T11:22:27Z","timestamp":1739445747000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-04512-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642045110","9783642045127"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-04512-7_11","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2009]]}}}