{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:14:54Z","timestamp":1771514094296,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T00:00:00Z","timestamp":1658016000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T00:00:00Z","timestamp":1658016000000},"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":[[2022,7,17]]},"DOI":"10.1109\/rcar54675.2022.9872253","type":"proceedings-article","created":{"date-parts":[[2022,9,5]],"date-time":"2022-09-05T20:31:54Z","timestamp":1662409914000},"page":"475-480","source":"Crossref","is-referenced-by-count":4,"title":["End-to-End Autonomous Exploration for Mobile Robots in Unknown Environments through Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zhi","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghao","family":"Xin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Department of Automation,Shanghai,P.R. China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref11","article-title":"Curiosity-driven exploration for mapless navigation with deep reinforcement learning","author":"zhelo","year":"2018","journal-title":"arXiv preprint arXiv 1804 00209"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR.2016.7784001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759428"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463213"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2891991"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2514\/6.2019-0396"},{"key":"ref18","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref4","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041446"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7068349"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2936167"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202319"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.1997.613851"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2018.8468643"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR52367.2021.9517416"},{"key":"ref21","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv preprint arXiv 1506 02349"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"}],"event":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","location":"Guiyang, China","start":{"date-parts":[[2022,7,17]]},"end":{"date-parts":[[2022,7,22]]}},"container-title":["2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9872150\/9872152\/09872253.pdf?arnumber=9872253","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T21:11:41Z","timestamp":1664226701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9872253\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,17]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/rcar54675.2022.9872253","relation":{},"subject":[],"published":{"date-parts":[[2022,7,17]]}}}