{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T17:11:48Z","timestamp":1774717908816,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T00:00:00Z","timestamp":1668384000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T00:00:00Z","timestamp":1668384000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007053","name":"KETEP","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"MOTIE","doi-asserted-by":"publisher","award":["20222020800190"],"award-info":[{"award-number":["20222020800190"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11,14]]},"DOI":"10.1109\/rose56499.2022.9977430","type":"proceedings-article","created":{"date-parts":[[2022,12,23]],"date-time":"2022-12-23T18:42:12Z","timestamp":1671820932000},"page":"1-7","source":"Crossref","is-referenced-by-count":14,"title":["Path Planning of Cleaning Robot with Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Woohyeon","family":"Moon","sequence":"first","affiliation":[{"name":"Cho Chun Shik Graduate School of Mobility Korea Advanced Institute of Science and Technology (KAIST),Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bumgeun","family":"Park","sequence":"additional","affiliation":[{"name":"Cho Chun Shik Graduate School of Mobility Korea Advanced Institute of Science and Technology (KAIST),Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarvar Hussain","family":"Nengroo","sequence":"additional","affiliation":[{"name":"Cho Chun Shik Graduate School of Mobility Korea Advanced Institute of Science and Technology (KAIST),Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taeyoung","family":"Kim","sequence":"additional","affiliation":[{"name":"Cho Chun Shik Graduate School of Mobility Korea Advanced Institute of Science and Technology (KAIST),Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsoo","family":"Har","sequence":"additional","affiliation":[{"name":"Cho Chun Shik Graduate School of Mobility Korea Advanced Institute of Science and Technology (KAIST),Daejeon,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32723-0_5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC.2010.5498349"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISED.2016.7977097"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WCICA.2014.7053581"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2015.10.011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.01.054"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/RITAPP.2019.8932804"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICECA52323.2021.9675949"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936863"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3035846"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref13","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman","year":"2015"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2990722"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_5"},{"issue":"7","key":"ref20","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","article-title":"Shaping and policy search in reinforcement learning","volume-title":"University of California","author":"Ng","year":"2003"},{"key":"ref22","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv preprint"}],"event":{"name":"2022 IEEE International Symposium on Robotic and Sensors Environments (ROSE)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2022,11,14]]},"end":{"date-parts":[[2022,11,15]]}},"container-title":["2022 IEEE International Symposium on Robotic and Sensors Environments (ROSE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9977404\/9977408\/09977430.pdf?arnumber=9977430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T08:29:29Z","timestamp":1709368169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9977430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/rose56499.2022.9977430","relation":{},"subject":[],"published":{"date-parts":[[2022,11,14]]}}}