{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T07:15:23Z","timestamp":1771658123379,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/icit.2017.7915468","type":"proceedings-article","created":{"date-parts":[[2017,5,12]],"date-time":"2017-05-12T22:23:01Z","timestamp":1494627781000},"page":"837-842","source":"Crossref","is-referenced-by-count":11,"title":["Model based path planning using Q-Learning"],"prefix":"10.1109","author":[{"given":"Avinash","family":"Sharma","sequence":"first","affiliation":[]},{"given":"Kanika","family":"Gupta","sequence":"additional","affiliation":[]},{"given":"Anirudha","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Aishwarya","family":"Sharma","sequence":"additional","affiliation":[]},{"given":"Rajesh","family":"Kumar","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"204","article-title":"The proposed Fuzzy Logic Navigation approach of Autonomous Mobile robots in unknown environments","volume":"3","author":"hachour","year":"2009","journal-title":"Mathematical Models and Methods in Applied Sciences"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2007.892728"},{"key":"ref12","volume":"25","author":"katic","year":"2003","journal-title":"Genetic Algorithms in Robotics International Series on Microprocessor-Based and Intelligent Systems Engineering"},{"key":"ref13","author":"jevti","year":"2007","journal-title":"Swarm intelligence and its applications in swarm robotics"},{"key":"ref14","first-page":"1","author":"beni","year":"2004","journal-title":"From swarm intelligence to swarm robotics In Swarm robotics"},{"key":"ref15","author":"wang","year":"2003","journal-title":"Car Simulation Using Reinforcement Learning"},{"key":"ref16","author":"levine","year":"2015","journal-title":"End-to-end training of deep visuomotor policies"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A Survey on Policy Search for Robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref18","first-page":"273","article-title":"Hierarchical relative entropy policy search","author":"daniel","year":"2012","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref4","first-page":"209","volume":"49","author":"kearns","year":"2002","journal-title":"Near-optimal reinforcement learning in polynomial time Machine Learning"},{"key":"ref27","article-title":"Overview of mini-batch gradient descent","author":"hinton","year":"2012","journal-title":"Neural Networks for Machine Learning"},{"key":"ref3","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","author":"brafman","year":"2003","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102459"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2010.5642471"},{"key":"ref7","first-page":"608","volume":"1","author":"kwakernaak","year":"1972","journal-title":"Linear Optimal Control Systems"},{"key":"ref2","first-page":"279","volume":"8","author":"watkins","year":"1992","journal-title":"Q-learning Machine Learning"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1109\/CIRA.2003.1222223","article-title":"GA-based learning in behaviour based robotics","volume":"3","author":"gu","year":"2003","journal-title":"Computational Intelligence in Robotics and Automation 2003 Proceedings 2003 IEEE International Symposium on"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90056-Q"},{"key":"ref22","first-page":"2650","article-title":"Reinforcement learning to adjust robot movements to new situations","volume":"22","author":"kober","year":"2011","journal-title":"IJCAI Proceedings-International Joint Conference on Artificial Intelligence"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509672"},{"key":"ref24","first-page":"679684","volume":"6","author":"bellman","year":"1957","journal-title":"A Markovian decision process Journal of Mathematics and Mechanics"},{"key":"ref23","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref26","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref25","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"}],"event":{"name":"2017 IEEE International Conference on Industrial Technology (ICIT)","location":"Toronto, ON","start":{"date-parts":[[2017,3,22]]},"end":{"date-parts":[[2017,3,25]]}},"container-title":["2017 IEEE International Conference on Industrial Technology (ICIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7907563\/7912587\/07915468.pdf?arnumber=7915468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,24]],"date-time":"2019-09-24T11:54:08Z","timestamp":1569326048000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7915468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icit.2017.7915468","relation":{},"subject":[],"published":{"date-parts":[[2017,3]]}}}