{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:42:38Z","timestamp":1784738558872,"version":"3.55.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,13]],"date-time":"2020-12-13T00:00:00Z","timestamp":1607817600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,13]],"date-time":"2020-12-13T00:00:00Z","timestamp":1607817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,13]],"date-time":"2020-12-13T00:00:00Z","timestamp":1607817600000},"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":[[2020,12,13]]},"DOI":"10.1109\/icarcv50220.2020.9305366","type":"proceedings-article","created":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T10:23:59Z","timestamp":1610274239000},"page":"387-392","source":"Crossref","is-referenced-by-count":1,"title":["HILPS: Human-in-Loop Policy Search for Mobile Robot Navigation"],"prefix":"10.1109","author":[{"given":"Mingxing","family":"Wen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ehsan","family":"Mihankhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3906\/elk-1311-129"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461203"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2018.8468643"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205564"},{"key":"ref15","author":"novati","year":"2018","journal-title":"Remember and forget for experience replay"},{"key":"ref16","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref17","author":"peshkin","year":"2003","journal-title":"Reinforcement Learning by Policy Search"},{"key":"ref18","first-page":"968","article-title":"Gradient descent for general reinforcement learning","author":"baird","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref4","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref3","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008987612352"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1996.571080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2867854"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/02783649922066484"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2869644"},{"key":"ref20","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"}],"event":{"name":"2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)","location":"Shenzhen, China","start":{"date-parts":[[2020,12,13]]},"end":{"date-parts":[[2020,12,15]]}},"container-title":["2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9305021\/9305302\/09305366.pdf?arnumber=9305366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:08:29Z","timestamp":1656374909000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9305366\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,13]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icarcv50220.2020.9305366","relation":{},"subject":[],"published":{"date-parts":[[2020,12,13]]}}}