{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T11:44:57Z","timestamp":1649072697112},"reference-count":11,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2008,12,1]],"date-time":"2008-12-01T00:00:00Z","timestamp":1228089600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artif Life Robotics"],"published-print":{"date-parts":[[2008,12]]},"DOI":"10.1007\/s10015-008-0565-x","type":"journal-article","created":{"date-parts":[[2008,12,13]],"date-time":"2008-12-13T10:27:57Z","timestamp":1229164077000},"page":"112-115","source":"Crossref","is-referenced-by-count":0,"title":["Networked reinforcement learning"],"prefix":"10.1007","volume":"13","author":[{"given":"Makito","family":"Oku","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuyuki","family":"Aihara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2008,12,14]]},"reference":[{"key":"565_CR1","doi-asserted-by":"crossref","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: An introduction. MIT Press","DOI":"10.1016\/S1474-6670(17)38315-5"},{"key":"565_CR2","unstructured":"Bakker B, Schmidhuber J (2004) Hierarchical reinforcement learning based on subgoal discovery and subpolicy specialization. In: Proceedings of the 8-th Conference on Intelligent Autonomous Systems, pp 438\u2013445"},{"key":"565_CR3","first-page":"271","volume":"5","author":"P. Dayan","year":"1993","unstructured":"Dayan P, Hinton GE (1993) Feudal reinforcement learning. Adv Neural Inf Process Syst 5:271\u2013278","journal-title":"Adv Neural Inf Process Syst"},{"key":"565_CR4","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"T.G. Dietterich","year":"2000","unstructured":"Dietterich TG (2000) Hierarchical reinforcement learning with the MAXQ value function decomposition. J Artif Intell Res 13:227\u2013303","journal-title":"J Artif Intell Res"},{"key":"565_CR5","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1162\/089976602753712972","volume":"14","author":"K. Doya","year":"2002","unstructured":"Doya K, Samejima K, Katagiri K, et al (2002) Multiple model-based reinforcement learning. Neural Comput 14:1347\u20131369","journal-title":"Neural Comput"},{"key":"565_CR6","first-page":"1043","volume":"10","author":"R. Parr","year":"1998","unstructured":"Parr R, Russell S (1998) Reinforcement learning with hierarchies of machines. Adv Neural Inf Process Syst 10:1043\u20131049","journal-title":"Adv Neural Inf Process Syst"},{"key":"565_CR7","first-page":"323","volume":"8","author":"S.P. Singh","year":"1992","unstructured":"Singh SP (1992) Transfer of learning by composing solutions of elemental sequential tasks. Mach Learn 8:323\u2013339","journal-title":"Mach Learn"},{"key":"565_CR8","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R.S. Sutton","year":"1999","unstructured":"Sutton RS, Precup D, Singh S (1999) Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artif Intell 112:181\u2013211","journal-title":"Artif Intell"},{"key":"565_CR9","unstructured":"Cassandra AR, Kaelbling LP, Littman ML (1994) Acting optimally in partially observable stochastic domains. In: Proceedings of the Twelfth National Conference on Artificial Intelligence, pp 1023\u20131028"},{"key":"565_CR10","unstructured":"Dolgov D, Durfee E (2004) Graphical models in local, asymmetric multi-agent Markov decision processes. In: Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, pp 956\u2013963"},{"key":"565_CR11","unstructured":"Nair R, Varakantham P, Tambe M, et al (2005) Networked distributed POMDPs: A synthesis of distributed constraint optimization and POMDPs. In: Proceedings of the Twentieth National Conference on Artificial Intelligence, pp 133\u2013139"}],"container-title":["Artificial Life and Robotics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-008-0565-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10015-008-0565-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-008-0565-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T12:36:01Z","timestamp":1559133361000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10015-008-0565-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,12]]},"references-count":11,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2008,12]]}},"alternative-id":["565"],"URL":"https:\/\/doi.org\/10.1007\/s10015-008-0565-x","relation":{},"ISSN":["1433-5298","1614-7456"],"issn-type":[{"value":"1433-5298","type":"print"},{"value":"1614-7456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,12]]}}}