{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:27:37Z","timestamp":1756996057182},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540779476"},{"type":"electronic","value":"9783540779490"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-77949-0_6","type":"book-chapter","created":{"date-parts":[[2008,2,8]],"date-time":"2008-02-08T04:01:52Z","timestamp":1202443312000},"page":"75-86","source":"Crossref","is-referenced-by-count":14,"title":["Combining Reinforcement Learning with Symbolic Planning"],"prefix":"10.1007","author":[{"given":"Matthew","family":"Grounds","sequence":"first","affiliation":[]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"6_CR1","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1022140919877","volume":"13","author":"A. Barto","year":"2003","unstructured":"Barto, A., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems\u00a013(4), 341\u2013379 (2003)","journal-title":"Discrete Event Systems"},{"key":"6_CR2","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":"6_CR3","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, Cambridge University, U.K. (1989)"},{"key":"6_CR4","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/0004-3702(71)90010-5","volume":"2","author":"R. Fikes","year":"1971","unstructured":"Fikes, R., Nilsson, N.: STRIPS: A new approach to the application of theorem proving to problem solving. Artificial Intelligence\u00a02, 189\u2013208 (1971)","journal-title":"Artificial Intelligence"},{"key":"6_CR5","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1016\/S0004-3702(96)00047-1","volume":"90","author":"A.L. Blum","year":"1997","unstructured":"Blum, A.L., Furst, M.L.: Fast planning through planning graph analysis. Artificial Intelligence\u00a090, 281\u2013300 (1997)","journal-title":"Artificial Intelligence"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Hoffmann, J.: A heuristic for domain independent planning and its use in an enforced hill-climbing algorithm. In: Proceedings of the 12th International Symposium on Methodologies for Intelligent Systems, pp. 216\u2013227 (2000)","DOI":"10.1007\/3-540-39963-1_23"},{"key":"6_CR7","unstructured":"Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic Programming. Athena Scientific (1996)"},{"key":"6_CR8","unstructured":"Ghallab, M., Howe, A., Knoblock, C., McDermott, D., Ram, A., Veloso, M., Weld, D., Wilkins, D.: PDDL\u2014the planning domain definition language. Technical Report CVC TR-98-003\/DCS TR-1165, Yale Center for Computational Vision and Control (1998)"},{"key":"6_CR9","unstructured":"Ryan, M.: Using abstract models of behaviours to automatically generate reinforcement learning hierarchies. In: Proceedings of the 19th International Conference on Machine Learning (2002)"},{"key":"6_CR10","unstructured":"Boutilier, C., Brafman, R.I., Geib, C.: Prioritized goal decomposition of Markov decision processes: Towards a synthesis of classical and decision theoretic planning. In: International Joint Conference on Artificial Intelligence (1997)"}],"container-title":["Lecture Notes in Computer Science","Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-77949-0_6.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T10:56:50Z","timestamp":1619521010000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-77949-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540779476","9783540779490"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-77949-0_6","relation":{},"subject":[]}}