{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T04:15:09Z","timestamp":1772338509772,"version":"3.50.1"},"reference-count":5,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"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":[[2022,3,7]]},"DOI":"10.1109\/hri53351.2022.9889551","type":"proceedings-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T19:46:56Z","timestamp":1664480816000},"page":"1278-1280","source":"Crossref","is-referenced-by-count":5,"title":["Human-Interactive Robot Learning (HIRL)"],"prefix":"10.1109","author":[{"given":"Reuth","family":"Mirsky","sequence":"first","affiliation":[{"name":"The University of Texas at Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kim","family":"Baraka","sequence":"additional","affiliation":[{"name":"Vrije Universiteit Amsterdam,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taylor Kessler","family":"Faulkner","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Justin","family":"Hart","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harel","family":"Yedidsion","sequence":"additional","affiliation":[{"name":"Applied Materials,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuesu","family":"Xiao","sequence":"additional","affiliation":[{"name":"X The Moonshot Factory,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","article-title":"Explore, exploit or listen: Combining human feedback and policy model to speed up deep reinforcement learning in 3d worlds","author":"lin","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3006254"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09430-0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2513"}],"event":{"name":"2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)","location":"Sapporo, Japan","start":{"date-parts":[[2022,3,7]]},"end":{"date-parts":[[2022,3,10]]}},"container-title":["2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9889327\/9889305\/09889551.pdf?arnumber=9889551","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:05:17Z","timestamp":1667516717000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9889551\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,7]]},"references-count":5,"URL":"https:\/\/doi.org\/10.1109\/hri53351.2022.9889551","relation":{},"subject":[],"published":{"date-parts":[[2022,3,7]]}}}