{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T13:36:01Z","timestamp":1790516161539,"version":"4.1.0"},"reference-count":22,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["N000141410003"],"award-info":[{"award-number":["N000141410003"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/tcds.2016.2628365","type":"journal-article","created":{"date-parts":[[2016,11,14]],"date-time":"2016-11-14T14:12:04Z","timestamp":1479132724000},"page":"44-55","source":"Crossref","is-referenced-by-count":55,"title":["Learning From Explanations Using Sentiment and Advice in RL"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8654-6714","authenticated-orcid":false,"given":"Samantha","family":"Krening","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brent","family":"Harrison","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karen M.","family":"Feigh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charles Lee","family":"Isbell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Riedl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Thomaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer","author":"kuhlmann","year":"2004","journal-title":"Proceedings of the AAAI Workshop on Supervisory Control of Learning and Adaptive Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.018"},{"key":"ref12","first-page":"819","article-title":"Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression","volume":"20","author":"maclin","year":"2005","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref14","first-page":"1069","article-title":"An interactive approach for situated task specification through verbal instructions","author":"meri\u00e7li","year":"2014","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219855"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/1500000011"},{"key":"ref17","article-title":"Instructing a reinforcement learner","author":"sivamurugan","year":"2012","journal-title":"Proc FLAIRS Conf"},{"key":"ref18","author":"skinner","year":"1938","journal-title":"The Behavior of Organisms An Experimental Analysis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1126\/science.7244649"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2200\/S00568ED1V01Y201402AIM028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390187"},{"key":"ref5","first-page":"1061","article-title":"Object focused Q-learning for autonomous agents","author":"cobo","year":"2013","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2012.152"},{"key":"ref7","first-page":"2625","article-title":"Policy shaping: Integrating human feedback with reinforcement learning","author":"griffith","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651020"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref9","first-page":"1447","article-title":"Object-focused advice in reinforcement learning","author":"krening","year":"2016","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref20","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume":"1631","author":"socher","year":"2013","journal-title":"Proc Conf Empir Methods Nat Lang Process (EMNLP)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2010.5586133"},{"key":"ref21","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/7875186\/07742965.pdf?arnumber=7742965","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:08:20Z","timestamp":1641985700000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7742965\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":22,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2016.2628365","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3]]}}}