{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T20:45:10Z","timestamp":1764276310251,"version":"3.41.2"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1-3","license":[{"start":{"date-parts":[[1996,1,1]],"date-time":"1996-01-01T00:00:00Z","timestamp":820454400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1996,1,1]],"date-time":"1996-01-01T00:00:00Z","timestamp":820454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[1996,1]]},"DOI":"10.1023\/a:1018020625251","type":"journal-article","created":{"date-parts":[[2003,2,6]],"date-time":"2003-02-06T17:07:14Z","timestamp":1044551234000},"page":"251-281","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Creating Advice-Taking Reinforcement Learners"],"prefix":"10.1007","volume":"22","author":[{"given":"Richard","family":"Maclin","sequence":"first","affiliation":[]},{"given":"Jude W.","family":"Shavlik","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"107742_CR1","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1162\/neco.1995.7.4.639","volume":"7","author":"Y. Abu-Mostafa","year":"1995","unstructured":"Abu-Mostafa, Y. (1995). Hints. Neural Computation, 7, 639\u2013671","journal-title":"Neural Computation"},{"key":"107742_CR2","unstructured":"Agre, P, & Chapman, D. (1987). Pengi: An implementation of a theory of activity. In Proceedings of the Sixth National Corference on Artificial Intelligence, pp. 268\u2013272 Seattle, WA."},{"key":"107742_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, C. (1987) Strategy learning with multilayer connectionist representations. In Proceedings of the Fourth International Workshop on Machine Learning, pp. 103\u2013114 Irvine, CA.","DOI":"10.1016\/B978-0-934613-41-5.50014-3"},{"key":"107742_CR4","first-page":"834 846","volume":"13","author":"A. Barto","year":"1983","unstructured":"Barto, A., Suttoun R. & Anderson, C. (1983). Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man, and Cybernetics, 13, 834 846.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"107742_CR5","first-page":"539","volume-title":"Learning and Computational Neuroscience","author":"A.. Barto","year":"1990","unstructured":"Barto, A.. Sutton, R., & Watkins, C. (1990). Learning and sequential decision making. In Gabriel M., & Moore, J. (Eds.). Learning and Computational Neuroscience, pp. 539\u2013602. MIT Press. Cambridge, MA."},{"key":"107742_CR6","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1109\/72.159061","volume":"3","author":"H. Berenji","year":"1992","unstructured":"Berenji, H. & Khedkar P. (1992). Leaning and tuning fuzzy logic controllers through reinforcements. IEEE transactions on Neural Network, 3, 724\u2013740.","journal-title":"IEEE transactions on Neural Network"},{"key":"107742_CR7","volume-title":"vision, Instruction, and Action","author":"D. Chapman","year":"1991","unstructured":"Chapman, D. (1991). vision, Instruction, and Action. MIT Press, Cambridge, MA."},{"key":"107742_CR8","first-page":"92","volume-title":"Proceedings of the Ninth International Conference on Machine Learning","author":"J. Clouse","year":"1992","unstructured":"Clouse, J. & Utgoff, P. (1992). A teaching method for reinforcement learning. In Proceedings of the Ninth International Conference on Machine Learning. pp 92\u2013101 Aberdeen, Scotland."},{"key":"107742_CR9","volume-title":"Language and Learning for Robots","author":"C. Crangle","year":"1994","unstructured":"Crangle, C. & Suppes, P (1994) Language and Learning for Robots,. CSLI Publications Slunford, CA."},{"key":"107742_CR10","doi-asserted-by":"crossref","unstructured":"Craven, M., & Shavlik, J. (1994). Using sampling and queries to extract rules from trained neural networks. In Proceedings of the Eleventh International Conference on Machine Learning. pp 7\u201345 New Brunswick, NJ.","DOI":"10.1016\/B978-1-55860-335-6.50013-1"},{"key":"107742_CR11","doi-asserted-by":"crossref","unstructured":"Diederich, J. (1989) \"Learning, by instruction\" in connectionist systems. In Proceedings of the sixth International Workshop on Machine Learning, pp 66\u201368 Ithaca, NY.","DOI":"10.1016\/B978-1-55860-036-2.50024-2"},{"key":"107742_CR12","first-page":"80 82","volume":"6","author":"T. Dienerich","year":"1991","unstructured":"Dienerich, T. (1991). Knowledge compilation: Bridging the gap between specification and implementation IEEE Expert, 6. 80 82","journal-title":"IEEE Expert"},{"key":"107742_CR13","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","volume":"14","author":"J. Elman","year":"1990","unstructured":"Elman, J. (1990). Finding structure in time. Cognitive Science, 14, 179\u2013211","journal-title":"Cognitive Science"},{"key":"107742_CR14","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1109\/69.382304","volume":"7","author":"P. Frasconi","year":"1995","unstructured":"Frasconi, P., Gori, M., Maggini, M, & Soda, G. (1995). Unified integration of explicit knowledge and learning by example In recurrent networks. IEEE Transactions on Knowledge and Data Engineering, 7, 340\u2013346.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"107742_CR15","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1080\/09540098908915644","volume":"1","author":"L. M. Fu","year":"1989","unstructured":"Fu, L. M (1989). Integration of neural heuristics into knowledge-based inference. Connection Science. 1, 325\u2013340","journal-title":"Connection Science"},{"key":"107742_CR16","volume-title":"Autorntic Refinement of Expert System Knowledge Bases","author":"A Ginsberg","year":"1988","unstructured":"Ginsberg, A (1988). Autorntic Refinement of Expert System Knowledge Bases. Pitman, London."},{"key":"107742_CR17","first-page":"331","volume":"17","author":"D. Gordon","year":"1994","unstructured":"Gordon. D., & Subramanian, D. (1994). A multistrategy learning scheme for agent knowledge acquisition. Informatica, 17, 331\u2013346.","journal-title":"Informatica"},{"key":"107742_CR18","volume-title":"Neural Network Synthesis using Cellular Encoding and the Genetic Algorithm","author":"F Gruau","year":"1994","unstructured":"Gruau, F (1994). Neural Network Synthesis using Cellular Encoding and the Genetic Algorithm. Ph.D. thesis, Ecole Norniale Superieure de Lyon, France."},{"key":"107742_CR19","first-page":"231","volume-title":"Cognitive Skills and their Acquisition","author":"F. Hayes-Roth","year":"1981","unstructured":"Hayes-Roth. F. Klahr, P, & Mosrow, D.J. (1981). Advice-taking and knowledge refinement: An iterative view of skill acquisition. In Anderson, J (Ed.). Cognitive Skills and their Acquisition, pp. 231\u201325. Lawrence Erlbaum, Hillsdale, NJ"},{"key":"107742_CR20","doi-asserted-by":"crossref","unstructured":"Huffmnan, S & Laird, I. (1993). Learning procedures from interactive natural language instructions. In Machine learning: Proceedings on the Tenth International Conference, pp. 143\u2013150 Amherst, MA.","DOI":"10.1016\/B978-1-55860-307-3.50025-3"},{"key":"107742_CR21","doi-asserted-by":"crossref","unstructured":"Kaelbling, L.. (1987). REX: A symbolic language for the design and parallel implementation of embedded systems. In Proceedings of the AIAA Conferene on Computers in Aerospace Wakefield, MA","DOI":"10.2514\/6.1987-2822"},{"key":"107742_CR22","doi-asserted-by":"crossref","first-page":"s35","DOI":"10.1016\/S0921-8890(05)80027-2","volume":"6","author":"I. Kaelbling","year":"1990","unstructured":"Kaelbling, I. & Rosenschein, S. (1990). Action and planning in embedded agents. Robotics and Autonomous Systems 6, s35\u20138.","journal-title":"Robotics and Autonomous Systems"},{"key":"107742_CR23","doi-asserted-by":"crossref","unstructured":"Laird, J. Rucka, M. Yager, E., & Tuck, C. (1990). Correcting and extending domain knowledge using outside guidance. In Proceedings of the Seventh lnternational Conference on Machine Learning, pp. 235\u2013243 Austin, TX","DOI":"10.1016\/B978-1-55860-141-3.50032-8"},{"key":"107742_CR24","first-page":"598","volume-title":"Advances in Neural Information Processing Systems","author":"Y. Le Cun","year":"1990","unstructured":"Le Cun, Y. Denker, I. & Solla, S (1990) Optimal brain damage In Touretzky, D (Ed.) Advances in Neural Information Processing Systems Vol. 2, pp. 598\u2013605. Morgan Kaufmaun, Palo Alto, CA."},{"key":"107742_CR25","volume-title":"Lex & yacc","author":"J. Levine","year":"1992","unstructured":"Levine, J. Mason, T. & Brown, D. (1992). Lex & yacc. O'Reilly, Sebastopol, CA"},{"key":"107742_CR26","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1022628806385","volume":"8","author":"L. Lin","year":"1992","unstructured":"Lin, L. (1992). Self-improving reactive agents based on reinforcement learning, planning, and teaching.Machine Learning, 8, 293\u2013321","journal-title":"Machine Learning"},{"key":"107742_CR27","doi-asserted-by":"crossref","unstructured":"Lin, L. (1993). Scaling up reinforcement learning for robot control. In Proceedings of the Tenth International Conference on Machine Learning, pp. 182\u2013189 Amherst. MA.","DOI":"10.1016\/B978-1-55860-307-3.50030-7"},{"key":"107742_CR28","volume-title":"Learning from Insrtuction and Experience: Methods for Incorporating Procedural Domain Theories into knowledge-Based Neural Networks","author":"R. Maclin","year":"1995","unstructured":"Maclin, R. (1995). Learning from Insrtuction and Experience: Methods for Incorporating Procedural Domain Theories into knowledge-Based Neural Networks. Ph.D. thesis, Computer Sciences Department, University of Wisconsin, Madison, WI."},{"key":"107742_CR29","first-page":"195","volume":"11","author":"R. Maclin","year":"1993","unstructured":"Maclin, R., & Shavlik, J. (1993). Using knowledge-based neural networks to improve algorithms: Refining the Chou-Fasman algorithm for protein folding. Machine Learning, 11. 195\u2013215.","journal-title":"Machine Learning"},{"key":"107742_CR30","unstructured":"Maclin, KR. & Shavlik, (1994). Incorporating advice into agents that learn from reinforcements. In Proceedings of the Twelfth National Conference on Artificial Intelligence, pp. 694\u2013699 Seattle, WA."},{"key":"107742_CR31","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/0004-3702(92)90058-6","volume":"55","author":"S. Mahadevan","year":"1992","unstructured":"Mahadevan, S., & Connell, J. (1992). Automatic programming of behavior based robots using reinforcement learning.Artificial Intelligence 55. 311\u2013365.","journal-title":"Artificial Intelligence"},{"key":"107742_CR32","first-page":"77","volume":"I","author":"J. McCarthy","year":"1958","unstructured":"McCarthy, J. (1958). Programs with common sense. In Proceedings of the Symposium on the Mechanization of Thought Processes. Vol I. pp 77\u201384. (Reprinted in M. Minsky, editor, 96, Semantic Information Processing. Cambridge, MA. MIT Press, 403\u2013409,).","journal-title":"Proceedings of the Symposium on the Mechanization of Thought Processes"},{"key":"107742_CR33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1287\/mnsc.28.1.1","volume":"28","author":"C;. Monahan","year":"1982","unstructured":"Monahan, C;. (1982). A survey of partially observable Markov decision processes, Theory models, and algorithms. Management Science, 28, 1\u201316.","journal-title":"Management Science"},{"key":"107742_CR34","volume-title":"Machine Learning: An Artificial Intelligence Approach","author":"D.J. Mostow","year":"1982","unstructured":"Mostow, D.J. (1982). Transforming declarative advice into effective procedures: A heuristic search example.In Michalski, R., Carbonell, J., & Mitchell, T (Eds.), Machine Learning: An Artificial Intelligence Approach, Vol. 1. Tioga Press. Palo Alto."},{"key":"107742_CR35","first-page":"9","volume":"I","author":"N Nilsson","year":"1994","unstructured":"Nilsson, N (1994). Teleo reactive programs for agent control. Journal of Artificial Intelligence Research, I 9\u20138.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"107742_CR36","volume-title":"Conputational Architectures Integrating Neural and Symbolic Processes","author":"D. Noelle","year":"1994","unstructured":"Noelle, D. & Cottrell, G. (1994). Towards instructable connectionist systems. In Sun, R, & Bookman, L (Eds.) Conputational Architectures Integrating Neural and Symbolic Processes. Kluwer Academic, Boston."},{"key":"107742_CR37","first-page":"361","volume-title":"Proceedings of the Ninth International Conference on Machine Learning","author":"C. Omlin","year":"1992","unstructured":"Omlin, C. & Giles, C. (1992). Training second-order recurrent neural networks using hints. In Proceedings of the Ninth International Conference on Machine Learning, pp. 361\u2013366 Aberdeen, Scotland."},{"key":"107742_CR38","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/0004-3702(94)90028-0","volume":"66","author":"D. Ourston","year":"1994","unstructured":"Ourston. D., & Mooney, R (1994). Theory refinemcnt combining analytical and empirical methods. Artificial Intelligence, 66, 273\u2013309","journal-title":"Artificial Intelligence"},{"key":"107742_CR39","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1023\/A:1022601518391","volume":"9","author":"M. Pazzani","year":"1992","unstructured":"Pazzani. M. & Kibler, D. (1992). The utility of knowledge in inductive learning Machine Learning, 9, 57\u201394.","journal-title":"Machine Learning"},{"key":"107742_CR40","doi-asserted-by":"crossref","unstructured":"Riecken, D (1994). Special issue on intelligent agents. Communications of the ACM. 37(7)","DOI":"10.1145\/176789.176801"},{"key":"107742_CR41","doi-asserted-by":"crossref","unstructured":"Shavlik, J., & Towell, G. (1989) An approach to combining explanation-based and neural learning algorithms. Connection Science, 233\u2013255.","DOI":"10.1080\/09540098908915640"},{"key":"107742_CR42","unstructured":"Siegelmann, H. (1994). Neural programming language In Proceedings of the Twelfth National Conference on Arificial Intelligence., pp. 877\u2013882 Seattle WA."},{"key":"107742_CR43","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/S0020-7373(05)80130-0","volume":"35","author":"S. Suddarth","year":"1991","unstructured":"Suddarth, S., & Holden,. A. (1991). Symtbolic neural systems and the use of hints for developing complex systems. International Journal of Man-Machine Studies, 35, 291\u2013311.","journal-title":"International Journal of Man-Machine Studies"},{"key":"107742_CR44","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1022633531479","volume":"5","author":"R. Sutton","year":"1988","unstructured":"Sutton, R. (1988). Learning to predict by the methods of temporal differences. Machine Learning,5 9\u201344.","journal-title":"Machine Learning"},{"key":"107742_CR45","doi-asserted-by":"crossref","first-page":"288","DOI":"10.7551\/mitpress\/3115.003.0040","volume-title":"From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior","author":"R. Sutton","year":"1991","unstructured":"Sutton, R. (1991). Reinforceent learning architectures for animats In Meyer, J., & Wilson, S. (Eds.), From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior, pp. 288\u2013296. MIT Press, Cambndge, MA."},{"key":"107742_CR46","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1023\/A:1022624705476","volume":"8","author":"G. Tesauro","year":"1992","unstructured":"Tesauro, G.(1992). Practial issues in temporal difference learning, Machine Learning. 8. 257\u2013277","journal-title":"Machine Learning"},{"key":"107742_CR47","unstructured":"Thrun, S. & Mitchell, T. (1993). Integrating inductive neural network learning and explanalion-based learning. In Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence pp. 930\u2013936 Chamber, France."},{"key":"107742_CR48","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1023\/A:1022683529158","volume":"13","author":"G. Towell","year":"1993","unstructured":"Towell, G. & Shavlk, J. (1993) Extracting refined rules from knowledge based neural networks. Machine Learning, 13, 71\u2013101","journal-title":"Machine Learning"},{"key":"107742_CR49","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/0004-3702(94)90105-8","volume":"70","author":"G. Towell","year":"1994","unstructured":"Towell, G. & Shavlik, J (1994). Knowledge-based artificial neural networks. Artificial Intelligence, 70 119\u2013165.","journal-title":"Artificial Intelligence"},{"key":"107742_CR50","unstructured":"Towell, G. Shavik, J, & Noordewier M. (1990) Refinement of approximate domain theories by knowledge-based neural networks. In Proceedings of the Eighth National Conference on Artificial Intelligence, pp.861\u2013866 Boston, MA."},{"key":"107742_CR51","unstructured":"Utgoff. P. & Clouse, I. (1991) Two kinds of training information for evaluation function learning. In Proceedings of the Ninth International Conference on Artificial Intelligence. pp. 596\u2013600 Anaheim, CA."},{"key":"107742_CR52","volume-title":"Learning from Delayed Rewards","author":"C Watkins","year":"1989","unstructured":"Watkins, C (1989). Learning from Delayed Rewards Ph.D. thesis, King's College, Cambridge"},{"key":"107742_CR53","first-page":"279","volume":"8","author":"C. Watkins","year":"1992","unstructured":"Watkins, C., & Dayan. P (1992) Q-leanirng. Machine Learning. 8, 279\u2013292.","journal-title":"Machine Learning"},{"key":"107742_CR54","unstructured":"Weigend, A. (1993). On overfitting and the effective number of hidden units. In Proceedings. of the 1993 Connectionist Models, Summer School, pp. 335\u2013342 San Mateo, CA. Morgan Kaufinann"},{"key":"107742_CR55","unstructured":"Whitehead, S. (1991). A complexity analysis of cooperative mechanisms in reinforcement learning. In Proceedings of the Ninth National Conference on Artificial Intelligence, pp. 607\u2013613 Anaheim CA"},{"key":"107742_CR56","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1016\/S0019-9958(65)90241-X","volume":"8","author":"L. Zadeh","year":"1965","unstructured":"Zadeh, L. (1965). Fuzzy sets. Information and Control,8, 338\u2013353.","journal-title":"Information and Control"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1018020625251.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1018020625251\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1018020625251.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:45:07Z","timestamp":1752147907000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1018020625251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1996,1]]},"references-count":56,"journal-issue":{"issue":"1-3","published-print":{"date-parts":[[1996,1]]}},"alternative-id":["107742"],"URL":"https:\/\/doi.org\/10.1023\/a:1018020625251","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[1996,1]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}