{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T21:06:43Z","timestamp":1750108003078},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540304623"},{"type":"electronic","value":"9783540316527"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11589990_19","type":"book-chapter","created":{"date-parts":[[2005,11,26]],"date-time":"2005-11-26T01:28:03Z","timestamp":1132968483000},"page":"164-175","source":"Crossref","is-referenced-by-count":13,"title":["Structural Abstraction Experiments in Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Robert","family":"Fitch","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernhard","family":"Hengst","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorian","family":"\u0160uc","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Greg","family":"Calbert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Scholz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"19_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"19_CR2","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1017\/S0140525X97000022","volume":"20","author":"A. Clark","year":"1997","unstructured":"Clark, A., Thornton, C.: Trading spaces: Computation, representation, and the limits of uninformed learning. Behavioral and Brain Sciences\u00a020, 57\u201366 (1997)","journal-title":"Behavioral and Brain Sciences"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Utgoff, P.E., Stracuzzi, D.J.: Many-layered learning. In: Neural Computation. MIT Press Journals, Cambridge (2002)","DOI":"10.1109\/DEVLRN.2002.1011824"},{"key":"19_CR4","volume-title":"Introduction to Cybernetics","author":"R. Ashby","year":"1956","unstructured":"Ashby, R.: Introduction to Cybernetics. Chapman & Hall, London (1956)"},{"key":"19_CR5","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"T.G. Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Hierarchical reinforcement learning with the MAXQ value function decomposition. Journal of Artificial Intelligence Research\u00a013, 227\u2013303 (2000)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"19_CR6","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, King\u2019s College (1989)"},{"key":"19_CR7","unstructured":"Ravindran, B., Barto, A.G.: SMDP homomorphisms: An algebraic approach to abstraction in semi markov decision processes. In: Proc. of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI 2003), pp. 1011\u20131018 (2003)"},{"key":"19_CR8","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/3-540-45622-8_15","volume-title":"Abstraction, Reformulation, and Approximation","author":"B. Ravindran","year":"2002","unstructured":"Ravindran, B., Barto, A.G.: Model minimization in hierarchical reinforcement learning. In: Koenig, S., Holte, R.C. (eds.) SARA 2002. LNCS (LNAI), vol.\u00a02371, pp. 196\u2013211. Springer, Heidelberg (2002)"},{"key":"19_CR9","unstructured":"Dean, T., Givan, R.: Model minimization in markov decision processes. In: AAAI\/IAAI, 106\u2013111 (1997)"},{"key":"19_CR10","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/S0004-3702(00)00047-3","volume":"122","author":"R. Givan","year":"2000","unstructured":"Givan, R., Leach, S.M., Dean, T.: Bounded-parameter markov decision processes. Artificial Intelligence\u00a0122, 71\u2013109 (2000)","journal-title":"Artificial Intelligence"},{"key":"19_CR11","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1007518724497","volume":"33","author":"R.H. Crites","year":"1998","unstructured":"Crites, R.H., Barto, A.G.: Elevator group control using multiple reinforcement learning agents. Machine Learning\u00a033, 235\u2013262 (1998)","journal-title":"Machine Learning"},{"key":"19_CR12","unstructured":"Wolpert, D., Tumer, K.: An introduction to collective intelligence. Technical Report NASA-ARC-IC-99-63, NASA Ames Research Center, CA (1999)"},{"key":"19_CR13","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/BF01918335","volume":"12","author":"D. Braess","year":"1968","unstructured":"Braess, D.: \u00dcber ein Paradoxon der Verkehrsplanung. Unternehmensforschung\u00a012, 258\u2013268 (1968)","journal-title":"Unternehmensforschung"},{"key":"19_CR14","unstructured":"Rohanimanesh, K., Mahadevan, S.: Learning to take concurrent actions. In: NIPS, pp. 1619\u20131626 (2002)"},{"key":"19_CR15","first-page":"243","volume-title":"Proceedings of the Nineteenth International Conference on Machine Learning","author":"B. Hengst","year":"2002","unstructured":"Hengst, B.: Discovering hierarchy in reinforcement learning with HEXQ. In: Sammut, C., Hoffmann, A. (eds.) Proceedings of the Nineteenth International Conference on Machine Learning, pp. 243\u2013250. Morgan Kaufmann, San Francisco (2002)"},{"key":"19_CR16","first-page":"167","volume-title":"Machine Learning Proceedings of the Tenth International Conference","author":"L.P. Kaelbling","year":"1993","unstructured":"Kaelbling, L.P.: Hierarchical learning in stochastic domains: Preliminary results. In: Machine Learning Proceedings of the Tenth International Conference, San Mateo, CA, pp. 167\u2013173. Morgan Kaufmann, San Francisco (1993)"}],"container-title":["Lecture Notes in Computer Science","AI 2005: Advances in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11589990_19.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T02:48:03Z","timestamp":1619491683000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11589990_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540304623","9783540316527"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/11589990_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}