{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:29:17Z","timestamp":1768422557350,"version":"3.49.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T00:00:00Z","timestamp":1685318400000},"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":[[2023,5,29]]},"DOI":"10.1109\/icra48891.2023.10161004","type":"proceedings-article","created":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T17:20:56Z","timestamp":1688491256000},"page":"5821-5828","source":"Crossref","is-referenced-by-count":4,"title":["Asking for Help: Failure Prediction in Behavioral Cloning through Value Approximation"],"prefix":"10.1109","author":[{"given":"Cem","family":"Gokmen","sequence":"first","affiliation":[{"name":"Stanford University,Stanford,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Ho","sequence":"additional","affiliation":[{"name":"Everyday Robots,Mountain View,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohi","family":"Khansari","sequence":"additional","affiliation":[{"name":"Everyday Robots,Mountain View,CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1","article-title":"Double reinforcement learning for efficient off-policy evaluation in markov decision processes","volume":"21","author":"kallus","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref12","article-title":"Data-efficient off-policy policy evaluation for reinforcement learning","author":"thomas","year":"2016","journal-title":"ArXiv vol abs\/1604 00923"},{"key":"ref15","article-title":"Empiri-cal study of off-policy policy evaluation for reinforce-ment learning","author":"voloshin","year":"2021","journal-title":"ArXiv vol abs\/1911 06854"},{"key":"ref14","article-title":"Benchmarks for deep off-policy evaluation","author":"fu","year":"2021","journal-title":"ArXiv vol abs\/2103 16596"},{"key":"ref11","article-title":"Off-policy temporal difference learning with function approximation","author":"precup","year":"2001","journal-title":"ICML"},{"key":"ref10","article-title":"Eligibility traces for off-policy policy evaluation","author":"precup","year":"2000","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2202.07600"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2202.01862"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594031"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.064"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968287"},{"key":"ref18","author":"wong","year":"2021","journal-title":"Error-aware imitation learning from teleoperation data for mobile manipulation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2202.02005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968091"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1612.00410"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/70.88151"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206152"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1996.506591"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1512.03385"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SAFEPROCESS45799.2019.9213393"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/906546"},{"key":"ref9","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref4","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"ahn","year":"2022","journal-title":"ar Xiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1011.0686"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.14445\/23488387\/IJCSE-V3I11P114"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0954406213507704"}],"event":{"name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","location":"London, United Kingdom","start":{"date-parts":[[2023,5,29]]},"end":{"date-parts":[[2023,6,2]]}},"container-title":["2023 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10160211\/10160212\/10161004.pdf?arnumber=10161004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:37:20Z","timestamp":1690220240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10161004\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,29]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icra48891.2023.10161004","relation":{},"subject":[],"published":{"date-parts":[[2023,5,29]]}}}