{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T03:19:33Z","timestamp":1761621573909,"version":"3.28.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T00:00:00Z","timestamp":1612396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,2,4]]},"DOI":"10.1109\/icara51699.2021.9376477","type":"proceedings-article","created":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T20:24:06Z","timestamp":1616012646000},"page":"21-25","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning Based Online Area Covering Autonomous Robot"],"prefix":"10.1109","author":[{"given":"Olimpiya","family":"Saha","sequence":"first","affiliation":[]},{"given":"Guohua","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Javad","family":"Heydari","sequence":"additional","affiliation":[]},{"given":"Viswanath","family":"Ganapathy","sequence":"additional","affiliation":[]},{"given":"Mohak","family":"Shah","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570413"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932890"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/AIM.2007.4412480"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989583"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354499"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-012-0406-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2005.861455"},{"key":"ref17","article-title":"A terrain-covering algorithm for an AUV","volume":"3","author":"hert","year":"1999","journal-title":"Autonomous Robots"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0571-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/robotics8020044"},{"key":"ref28","article-title":"A new convergent variant of q-learning with linear function approximation","volume":"33","author":"carvalho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2013.09.004"},{"journal-title":"Towards characterizing divergence in deep q-learning","year":"2019","author":"achiam","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2018.03.015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-7721(00)00015-8"},{"key":"ref29","first-page":"486","article-title":"A theoretical analysis of deep q-learning","author":"fan","year":"2020","journal-title":"Learning for Dynamics and Control"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/drones3010004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509860"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-1273-0_32"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_23"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/027836402320556359"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/659457"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref21"},{"key":"ref24","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Proceedings of the 1993 Connectionist Models Summer School Hillsdale"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"0","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"journal-title":"Prioritized experience replay","year":"2015","author":"schaul","key":"ref25"}],"event":{"name":"2021 7th International Conference on Automation, Robotics and Applications (ICARA)","start":{"date-parts":[[2021,2,4]]},"location":"Prague, Czech Republic","end":{"date-parts":[[2021,2,6]]}},"container-title":["2021 7th International Conference on Automation, Robotics and Applications (ICARA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9376360\/9376362\/09376477.pdf?arnumber=9376477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:43:52Z","timestamp":1652197432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9376477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icara51699.2021.9376477","relation":{},"subject":[],"published":{"date-parts":[[2021,2,4]]}}}