{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:48:43Z","timestamp":1773247723722,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2013,9]]},"DOI":"10.1109\/tsmca.2012.2227719","type":"journal-article","created":{"date-parts":[[2013,8,1]],"date-time":"2013-08-01T18:02:23Z","timestamp":1375380143000},"page":"1141-1153","source":"Crossref","is-referenced-by-count":227,"title":["A Deterministic Improved Q-Learning for Path Planning of a Mobile Robot"],"prefix":"10.1109","volume":"43","author":[{"given":"Amit","family":"Konar","sequence":"first","affiliation":[]},{"given":"Indrani Goswami","family":"Chakraborty","sequence":"additional","affiliation":[]},{"given":"Sapam Jitu","family":"Singh","sequence":"additional","affiliation":[]},{"given":"Lakhmi C.","family":"Jain","sequence":"additional","affiliation":[]},{"given":"Atulya K.","family":"Nagar","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","author":"sutton","year":"1998","journal-title":"Reinforcement Learning"},{"key":"ref38","first-page":"935","volume":"17","author":"sakaguchi","year":"2004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SDR.2010.5507920"},{"key":"ref32","first-page":"1705","article-title":"Spectrum management of cognitive radio using multi-agent reinforcement learning","author":"wu","year":"2010","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1815396.1815448"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2043124"},{"key":"ref37","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114727"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISADS.2011.92"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICMTMA.2011.35"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307489"},{"key":"ref40","year":"0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282480"},{"key":"ref12","first-page":"2946","article-title":"A CMAC-Q-learning based Dyna agent","author":"hsu","year":"2008","journal-title":"Proc SICE Annu Conf"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2007.4389199"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IPC.2007.88"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2010.38"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIS.2009.17"},{"key":"ref17","first-page":"379","article-title":"Extended Q-learning algorithm for path-planning of a mobile robot","author":"goswami","year":"2010","journal-title":"Proc 8th Int Conf SEAL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INES.2007.4283689"},{"key":"ref19","first-page":"872","article-title":"Navigation of autonomous vehicles in unknown environments using reinforcement learning","author":"mart\ufffdnez-mar\ufffdn","year":"2007","journal-title":"Proc IEEE Intell Veh Symp"},{"key":"ref28","first-page":"369","article-title":"Dynamic analysis of multiagent Q-learning with E-greedy exploration","volume":"382","author":"gomes","year":"2009","journal-title":"Proc 26th Int Conf Mach Learn"},{"key":"ref4","author":"konar","year":"2005","journal-title":"Computational Intelligence Principles Techniques and Applications"},{"key":"ref27","first-page":"3943","article-title":"Hybrid Q-learning algorithm about cooperation in MAS","author":"chen","year":"2009","journal-title":"Proc CCDC"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"13","DOI":"10.3233\/IFS-2009-0412","article-title":"Cooperative multi-robot path planning using differential evolution","volume":"20","author":"chakraborty","year":"2009","journal-title":"J Intell Fuzzy Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SECON.2011.5752976"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/4235.585889"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.1997.620205"},{"key":"ref2","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/70.143360"},{"key":"ref1","author":"dean","year":"1993","journal-title":"Machine Learning Methods for Planning and Scheduling"},{"key":"ref20","first-page":"82","article-title":"Fast reinforcement learning using stochastic shortest paths for a mobile robot","author":"kwon","year":"2007","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HSI.2010.5514491"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HSI.2008.4581537"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368181"},{"key":"ref23","first-page":"871","article-title":"Extending Q-learning to general adaptive. Multi-agent systems","volume":"16","author":"tesauro","year":"2004","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"2854","article-title":"Incremental multistep Q-learning for adaptive traffic signal control based on delay minimization strategy","author":"lu","year":"2008","journal-title":"Proceedings of the 7th World Congress on Intelligent Control and Automation"},{"key":"ref25","first-page":"674","article-title":"Path planning for a robot manipulator based on probabilistic roadmap and reinforcement learning","volume":"5","author":"park","year":"2007","journal-title":"Int J Control Autom Syst"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/6579703\/06573377.pdf?arnumber=6573377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T08:40:30Z","timestamp":1596271230000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6573377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9]]},"references-count":40,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tsmca.2012.2227719","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9]]}}}