{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:53:10Z","timestamp":1729637590539,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icra.2013.6630669","type":"proceedings-article","created":{"date-parts":[[2013,10,21]],"date-time":"2013-10-21T22:11:25Z","timestamp":1382393485000},"page":"828-835","source":"Crossref","is-referenced-by-count":11,"title":["Hierarchical sub-task decomposition for reinforcement learning of multi-robot delivery mission"],"prefix":"10.1109","author":[{"given":"Hiroshi","family":"Kawano","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"19","first-page":"361","article-title":"Automatic discovery of subgoals in reinforcement learning using diverse density","author":"mcgovern","year":"2001","journal-title":"Proceedings of the Eighteenth International Conference on Machine Learning"},{"key":"17","doi-asserted-by":"crossref","first-page":"1681","DOI":"10.1109\/ICSMC.2007.4414013","article-title":"Hierarchical reinforcement learning using a modular fuzzy model for multi-agent problem","author":"watanabe","year":"2007","journal-title":"Proceedings of the 2007 IEEE International Conference on Systems Man and Cybernetics Montreal"},{"key":"18","first-page":"243","article-title":"Discovering hierarchy in reinforcement learning with hexq","author":"hengst","year":"2002","journal-title":"Proceedings of the Nineteenth International Conference on Machine Learning"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376302"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5652923"},{"journal-title":"Hierarchical Control and Learning for Markov Decision Process","year":"1998","author":"parr","key":"13"},{"key":"14","first-page":"522","article-title":"Using abstract models of behaviours to automatically generate reinforcement learning hierarchies","author":"malcom","year":"2002","journal-title":"Proceedings of the Nineteenth International Conference on Machine Learning"},{"key":"11","first-page":"840","article-title":"Dynamic correlation matrix based multi-q learning for a multi-robot system","author":"guo","year":"2008","journal-title":"Proceedings of IEEE\/RSJ International Conference of Intelligent Robots and Systems Nice France"},{"key":"12","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1613\/jair.639","article-title":"Hierarchical reinforcement learning with the MAXQ value function decomposition","volume":"13","author":"dietterich","year":"2000","journal-title":"Artificial Intelligence Research"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-200-7.50075-1"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"1"},{"key":"10","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1023\/A:1008819414322","article-title":"Reinforcement learning in the multi-robot domain","volume":"1997","author":"mataric","year":"1997","journal-title":"Autonomous Robots"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/S1389-0417(01)00015-8"},{"key":"6","first-page":"242","article-title":"Correlated-q learning","author":"greenwald","year":"2003","journal-title":"Proceedings of the Twentieth International Conference on Machine Learning"},{"key":"5","first-page":"407","article-title":"Experimental results on Q-learning for general-sum stochastic games","author":"hu","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"key":"4","first-page":"242","article-title":"Multi agent reinforcement learning: Theoretical framework and an algorithm","author":"hu","year":"1998","journal-title":"Proc Machine Learning Fifteenth Int Conf"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1242005"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281729"}],"event":{"name":"2013 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2013,5,6]]},"location":"Karlsruhe, Germany","end":{"date-parts":[[2013,5,10]]}},"container-title":["2013 IEEE International Conference on Robotics and Automation"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6615630\/6630547\/06630669.pdf?arnumber=6630669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T02:11:18Z","timestamp":1564539078000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6630669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icra.2013.6630669","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}