{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:28:11Z","timestamp":1774024091148,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9341669","type":"proceedings-article","created":{"date-parts":[[2021,2,13]],"date-time":"2021-02-13T02:26:48Z","timestamp":1613183208000},"page":"10945-10951","source":"Crossref","is-referenced-by-count":6,"title":["Maximizing BCI Human Feedback using Active Learning"],"prefix":"10.1109","author":[{"given":"Zizhao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyao","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iretiayo","family":"Akinola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Allen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"475","article-title":"Reinforcement learning from simultaneous human and mdp reward","volume":"1","author":"knox","year":"2012","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref11","first-page":"5","article-title":"Combining manual feedback with subsequent mdp reward signals for reinforcement learning","volume":"1","author":"knox","year":"2010","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref12","article-title":"Active learning literature survey","author":"settles","year":"2009","journal-title":"Tech Rep"},{"key":"ref13","first-page":"1220","article-title":"Selective sampling algorithms for cost-sensitive multi-class prediction","author":"agarwal","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref14","first-page":"433","article-title":"Better algorithms for selective sampling","author":"orabona","year":"2011","journal-title":"International Conference on Machine Learning"},{"key":"ref15","first-page":"453","article-title":"Online multitask learning","author":"dekel","year":"2006","journal-title":"Computation Theory"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157693"},{"key":"ref17","article-title":"Skill learning by autonomous robotic playing using active learning and creativity","author":"hangl","year":"2017"},{"key":"ref18","article-title":"Active learning for teaching a robot grounded relational symbols","author":"kulick","year":"2013","journal-title":"Twenty-Third International Joint Conference on Artificial Intelligence"},{"key":"ref19","first-page":"155","article-title":"Error-related potentials during continuous feedback: using eeg to detect errors of different type and severity","volume":"9","author":"sp\u00fcler","year":"2015","journal-title":"Frontiers in Human Neuroscience"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11485","article-title":"Deep tamer: Interactive agent shaping in high-dimensional state spaces","author":"warnell","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref3","first-page":"4299","article-title":"Deep reinforcement learning from human preferences","author":"christiano","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Face valuing: Training user interfaces with facial expressions and reinforcement learning","author":"veeriah","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2017.2700395"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"13893","DOI":"10.1038\/srep13893","article-title":"Teaching brain-machine interfaces as an alternative paradigm to neuroprosthetics control","volume":"5","author":"iturrate","year":"2015","journal-title":"Scientific Reports"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759137"},{"key":"ref2","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"griffith","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Accelerated robot learning via human brain signals","author":"akinola","year":"2019"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1597735.1597738"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460551"},{"key":"ref22","first-page":"3179","article-title":"Evidential deep learning to quantify classification uncertainty","author":"sensoy","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref23","article-title":"Self-imitation learning","author":"oh","year":"2018"},{"key":"ref26","article-title":"On evaluation of embodied navigation agents","author":"anderson","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09341669.pdf?arnumber=9341669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T04:15:53Z","timestamp":1671250553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9341669\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9341669","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}