{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T15:25:04Z","timestamp":1774625104179,"version":"3.50.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2008,6,3]],"date-time":"2008-06-03T00:00:00Z","timestamp":1212451200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2008,12]]},"DOI":"10.1007\/s10994-008-5061-y","type":"journal-article","created":{"date-parts":[[2008,6,2]],"date-time":"2008-06-02T13:41:13Z","timestamp":1212414073000},"page":"289-312","source":"Crossref","is-referenced-by-count":39,"title":["Transfer in variable-reward hierarchical reinforcement learning"],"prefix":"10.1007","volume":"73","author":[{"given":"Neville","family":"Mehta","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sriraam","family":"Natarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prasad","family":"Tadepalli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan","family":"Fern","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2008,6,3]]},"reference":[{"key":"5061_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., & Ng, A. (2004). Apprenticeship learning via inverse reinforcement learning. In Proceedings of the ICML.","DOI":"10.1145\/1015330.1015430"},{"key":"5061_CR2","unstructured":"Andre, D., & Russell, S. (2002). State abstraction for programmable reinforcement learning agents. In Eighteenth national conference on artificial intelligence (pp. 119\u2013125)."},{"key":"5061_CR3","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"9","author":"T. Dietterich","year":"2000","unstructured":"Dietterich, T. (2000). Hierarchical reinforcement learning with the MAXQ value function decomposition. Journal of Artificial Intelligence Research, 9, 227\u2013303.","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"2","key":"5061_CR4","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1287\/moor.20.2.302","volume":"20","author":"E. Feinberg","year":"1995","unstructured":"Feinberg, E., & Schwartz, A. (1995). Constrained Markov decision models with weighted discounted rewards. Mathematics of Operations Research, 20(2), 302\u2013320.","journal-title":"Mathematics of Operations Research"},{"key":"5061_CR5","unstructured":"Gabor, Z., Kalmar, Z., & Szepesvari, C. (1998). Multi-criteria reinforcement learning. In Proceedings of the ICML."},{"key":"5061_CR6","unstructured":"Guestrin, C., Koller, D., & Parr, R. (2001). Multiagent planning with factored MDPs. In Proceedings NIPS-01."},{"key":"5061_CR7","unstructured":"Guestrin, C., Koller, D., Gearhart, C., & Kanodia, N. (2003). Generalizing plans to new environments in relational MDPs. In International joint conference on artificial intelligence."},{"key":"5061_CR8","doi-asserted-by":"crossref","unstructured":"Kaelbling, L., Littman, M., & Cassandra, A. (1998). Planning and acting in partially observable stochastic domains. AI Journal.","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"5061_CR9","unstructured":"Liu, Y., & Stone, P. (2006). Value-function-based transfer for reinforcement learning using structure mapping. In Proceedings of the twenty-first national conference on artificial intelligence."},{"key":"5061_CR10","unstructured":"Mausam, D. (2003). Solving relational MDPs with first-order machine learning. In Proceedings of the ICAPS workshop on planning under uncertainty and incomplete information."},{"key":"5061_CR11","unstructured":"Mehta, N., & Tadepalli, P. (2005). Multi-agent shared hierarchy reinforcement learning. In ICML workshop on rich representations in reinforcement learning."},{"key":"5061_CR12","doi-asserted-by":"crossref","unstructured":"Natarajan, S., & Tadepalli, P. (2005). Dynamic preferences in multi-criteria reinforcement learning. In Proceedings of the ICML.","DOI":"10.1145\/1102351.1102427"},{"key":"5061_CR13","unstructured":"Parr, R. (1998). Flexible decomposition algorithms for weakly coupled Markov decision problems. In UAI."},{"key":"5061_CR14","doi-asserted-by":"crossref","unstructured":"Price, B., & Boutilier, C. (2003). Accelerating reinforcement learning through implicit imitation. Journal of Artificial Intelligence Research, 569\u2013629.","DOI":"10.1613\/jair.898"},{"key":"5061_CR15","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes","author":"M. L. Puterman","year":"1994","unstructured":"Puterman, M. L. (1994). Markov decision processes. New York: Wiley."},{"key":"5061_CR16","unstructured":"Russell, S., & Zimdars, A. (2003). Q-decomposition for reinforcement learning agents. In Proceedings of ICML-03."},{"key":"5061_CR17","volume-title":"Proceedings of the 10th international conference on machine learning","author":"A. Schwartz","year":"1993","unstructured":"Schwartz, A. (1993). A reinforcement learning method for maximizing undiscounted rewards. In Proceedings of the 10th international conference on machine learning. San Mateo: Morgan Kaufmann."},{"key":"5061_CR18","unstructured":"Seri, S., & Tadepalli, P. (2002). Model-based hierarchical average reward reinforcement learning. In Proceedings of the ICML (pp. 562\u2013569)."},{"issue":"1\u20132","key":"5061_CR19","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. Sutton","year":"1999","unstructured":"Sutton, R., Precup, D., & Singh, S. (1999). Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112(1\u20132), 181\u2013211.","journal-title":"Artificial Intelligence"},{"key":"5061_CR20","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/S0004-3702(98)00002-2","volume":"100","author":"P. Tadepalli","year":"1998","unstructured":"Tadepalli, P., & Ok, D. (1998). Model-based average reward reinforcement learning. Artificial Intelligence, 100, 177\u2013224.","journal-title":"Artificial Intelligence"},{"key":"5061_CR21","unstructured":"Taylor, M., Stone, P., & Liu, Y. (2005). Value functions for RL-based behavior transfer: a comparative study. In Proceedings of the twentieth national conference on artificial intelligence."},{"key":"5061_CR22","unstructured":"Torrey, L., Shavlik, J., Walker, T., & Maclin, R. (2007). Relational macros for transfer in reinforcement learning. In Proceedings of the 17th conference on inductive logic programming."},{"key":"5061_CR23","unstructured":"Weeks, J. (1985). The shape of space: how to visualize surfaces and three-dimensional manifolds."},{"key":"5061_CR24","doi-asserted-by":"crossref","first-page":"639","DOI":"10.1016\/0022-247X(82)90122-6","volume":"89","author":"D. White","year":"1982","unstructured":"White, D. (1982). Multi-objective infinite-horizon discounted Markov decision processes. Journal of Mathematical Analysis and Applications, 89, 639\u2013647.","journal-title":"Journal of Mathematical Analysis and Applications"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-008-5061-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-008-5061-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-008-5061-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T21:40:25Z","timestamp":1559338825000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-008-5061-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,6,3]]},"references-count":24,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2008,12]]}},"alternative-id":["5061"],"URL":"https:\/\/doi.org\/10.1007\/s10994-008-5061-y","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,6,3]]}}}