{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T15:00:43Z","timestamp":1729609243789,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1109\/robio.2010.5723536","type":"proceedings-article","created":{"date-parts":[[2011,3,5]],"date-time":"2011-03-05T07:53:28Z","timestamp":1299311608000},"page":"1411-1416","source":"Crossref","is-referenced-by-count":2,"title":["Human-like gradual learning of a Q-learning based Light exploring robot"],"prefix":"10.1109","author":[{"given":"Dip N","family":"Ray","sequence":"first","affiliation":[]},{"given":"Amit","family":"Mandal","sequence":"additional","affiliation":[]},{"given":"Somajyoti","family":"Majumder","sequence":"additional","affiliation":[]},{"given":"Sumit","family":"Mukhopadhyay","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Effect of learning rates on a Q-learning based light exploring robot","year":"0","author":"ray","key":"ref10"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: a survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"J of Artificial Intelligence Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3844\/jcssp.2005.28.30"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281729"},{"key":"ref15","first-page":"1018","article-title":"Obstacle avoidance of multi mobile robots based on behavior decomposition Reinforcement Learning","author":"zu","year":"2007","journal-title":"Proc IEEE International Conference on Robotics and Biomimetics"},{"journal-title":"The use of neural networks and reinforcement learning to train obstacle-avoidance behavior in a simulated robot","year":"0","author":"schuresko","key":"ref16"},{"key":"ref17","first-page":"694","article-title":"Reinforcement learning for a real robot in a real environment","author":"yamagnchi","year":"1996","journal-title":"Proc European Conference on Artificial Intelligence"},{"key":"ref18","first-page":"665","article-title":"A reinforcement learning approach to robot navigation","author":"su","year":"2004","journal-title":"Proc IEEE International Conference on Networking Sensing and Control"},{"key":"ref19","first-page":"119","article-title":"Trajectory generation for a mobile robot by reinforcement learning","author":"shimizu","year":"2005","journal-title":"Proceedings of the 3rd International Symposium on Autonomous Minirobots for Research and Edutainment (AMiRE 2005)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114731"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-1599-1_178"},{"article-title":"Learning from Delayed Rewards","year":"1989","author":"watkins","key":"ref3"},{"key":"ref6","first-page":"403","article-title":"Reinforcement learning for a vision based mobile robot","author":"gaskett","year":"2000","journal-title":"Proc IEEE International Conference on Intelligent Robots and Systems"},{"key":"ref5","first-page":"768","article-title":"Automatic programming of behavior-based robots using reinforcement learning","author":"mahadevan","year":"1991","journal-title":"Proc National Conference on Artificial Intelligence"},{"article-title":"Quicker Q-learning in Multi-Agent Systems","year":"0","author":"agogino","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-003-0369-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref9","first-page":"293","article-title":"Multi-agent reinforcement learning-an exploration using Q-learning","volume":"7","author":"graham","year":"2009","journal-title":"Research and Development in Intelligent Systems XXVI (Computer Science)"},{"key":"ref1","article-title":"How Children Learn","author":"vosniadou","year":"0","journal-title":"International Academy of Education"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/AMC.2002.1026964"},{"key":"ref22","article-title":"Robot behavioral selection using Q-learning","author":"martinson","year":"2001","journal-title":"CC Technical Report GIT-CC-0119"},{"key":"ref21","first-page":"450","article-title":"Simulation of intelligent robot behavior based on reinforcement learning and neural network approach","author":"jerbic","year":"1996","journal-title":"Applications of Artificial Intelligence in Engineering Series IX"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932603"},{"article-title":"Reinforcement learning of behaviors in mobile robots using noisy infrared sensing","year":"0","author":"willgoss","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932598"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281986"}],"event":{"name":"2010 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2010,12,14]]},"location":"Tianjin, China","end":{"date-parts":[[2010,12,18]]}},"container-title":["2010 IEEE International Conference on Robotics and Biomimetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5720496\/5723286\/05723536.pdf?arnumber=5723536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,8]],"date-time":"2019-06-08T21:14:25Z","timestamp":1560028465000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5723536\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/robio.2010.5723536","relation":{},"subject":[],"published":{"date-parts":[[2010,12]]}}}