{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T02:09:43Z","timestamp":1776218983542,"version":"3.50.1"},"reference-count":15,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,4]]},"DOI":"10.1109\/adprl.2013.6614989","type":"proceedings-article","created":{"date-parts":[[2014,9,10]],"date-time":"2014-09-10T19:29:28Z","timestamp":1410377368000},"page":"52-59","source":"Crossref","is-referenced-by-count":18,"title":["A combined hierarchical reinforcement learning based approach for multi-robot cooperative target searching in complex unknown environments"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Cai","sequence":"first","affiliation":[]},{"given":"Simon X.","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2009.5212216"},{"key":"13","article-title":"A hierarchical reinforcement learning based approach to multi-robot cooperation for target searching in unknown environments","author":"cai","year":"2012","journal-title":"Control and Intelligent Systems"},{"key":"14","first-page":"281","article-title":"Convergence analysis of discretization procedure in Q-learning","author":"jiang","year":"1999","journal-title":"World Congress Int Federation Automat Contr"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1997.633847"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4650734"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/ICINFA.2010.5512238"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2009.2017557"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2003.1244361"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/IMSCCS.2006.90"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"6","first-page":"1714","article-title":"Studies on hierarchical reinforcement learning in multi-agent environment","author":"yu","year":"2008","journal-title":"Proceedings of the 2008 IEEE International Conference on Networking Sensing and Control"},{"key":"5","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72588-6_12"},{"key":"9","article-title":"The MAXQ method for hierarchical reinforcement learning","author":"dietterich","year":"0","journal-title":"Proceedings of the 1998 International Conference on Machine Learning Madison USA"},{"key":"8","author":"parr","year":"1998","journal-title":"Hierarchical control and learning for Markov decision processes"}],"event":{"name":"2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","location":"Singapore, Singapore","start":{"date-parts":[[2013,4,16]]},"end":{"date-parts":[[2013,4,19]]}},"container-title":["2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6596003\/6614979\/06614989.pdf?arnumber=6614989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T17:44:11Z","timestamp":1490204651000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6614989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/adprl.2013.6614989","relation":{},"subject":[],"published":{"date-parts":[[2013,4]]}}}