{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:09:26Z","timestamp":1732032566158},"publisher-location":"Berlin, Heidelberg","reference-count":6,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540440741"},{"type":"electronic","value":"9783540460848"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2002]]},"DOI":"10.1007\/3-540-46084-5_132","type":"book-chapter","created":{"date-parts":[[2007,10,19]],"date-time":"2007-10-19T08:20:51Z","timestamp":1192782051000},"page":"813-818","source":"Crossref","is-referenced-by-count":7,"title":["Speeding-up Reinforcement Learning with Multi-step Actions"],"prefix":"10.1007","author":[{"given":"Ralf","family":"Schoknecht","sequence":"first","affiliation":[]},{"given":"Martin","family":"Riedmiller","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2002,8,21]]},"reference":[{"key":"132_CR1","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"T. G. Dietterich","year":"2000","unstructured":"T. G. Dietterich. Hierarchical reinforcement learning with the MAXQ value function decomposition. Journal of Artificial Intelligence Research, 13:227\u2013303, 2000.","journal-title":"Journal of Artificial Intelligence Research"},{"unstructured":"A. McGovern, R.S. Sutton, and A.H. Fagg. Roles of macro-actions in accelerating reinforcement learning. In Grace Hopper Celebration of Women in Computing, 1997.","key":"132_CR2"},{"unstructured":"S. Pareigis. Adaptive choice of grid and time in reinforcement learning. In Advances in Neural Information Processing Systems, volume 10. MIT Press, 1998.","key":"132_CR3"},{"key":"132_CR4","series-title":"PhD thesis","volume-title":"Hierarchical Control and Learning for Markov Decision Processes","author":"R. E. Parr","year":"1998","unstructured":"R. E. Parr. Hierarchical Control and Learning for Markov Decision Processes. PhD thesis, University of California, Berkeley, CA, 1998."},{"key":"132_CR5","volume-title":"Technical report","author":"T. J. Perkins","year":"1999","unstructured":"T. J. Perkins and D. Precup. Using options for knowledge transfer in reinforcement learning. Technical report, University of Massachusetts, Amherst, 1999."},{"key":"132_CR6","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"R. S. Sutton","year":"1999","unstructured":"R. S. Sutton, D. Precup, and S. Singh. Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112:181\u2013211, 1999.","journal-title":"Artificial Intelligence"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks \u2014 ICANN 2002"],"original-title":[],"link":[{"URL":"https:\/\/linproxy.fan.workers.dev:443\/http\/link.springer.com\/content\/pdf\/10.1007\/3-540-46084-5_132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T20:06:48Z","timestamp":1548360408000},"score":1,"resource":{"primary":{"URL":"https:\/\/linproxy.fan.workers.dev:443\/http\/link.springer.com\/10.1007\/3-540-46084-5_132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002]]},"ISBN":["9783540440741","9783540460848"],"references-count":6,"URL":"https:\/\/linproxy.fan.workers.dev:443\/https\/doi.org\/10.1007\/3-540-46084-5_132","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2002]]}}}