{"id":"https://openalex.org/W2549514639","doi":"https://doi.org/10.1109/tcds.2016.2628365","title":"Learning From Explanations Using Sentiment and Advice in RL","display_name":"Learning From Explanations Using Sentiment and Advice in RL","publication_year":2016,"publication_date":"2016-11-14","ids":{"openalex":"https://openalex.org/W2549514639","doi":"https://doi.org/10.1109/tcds.2016.2628365","mag":"2549514639"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2016.2628365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2016.2628365","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083083220","display_name":"Samantha Krening","orcid":"https://orcid.org/0000-0001-8654-6714"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samantha Krening","raw_affiliation_strings":["Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047163199","display_name":"Brent Harrison","orcid":"https://orcid.org/0000-0002-1301-5928"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brent Harrison","raw_affiliation_strings":["Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041686916","display_name":"Karen M. Feigh","orcid":"https://orcid.org/0000-0002-0281-7634"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen M. Feigh","raw_affiliation_strings":["Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091212723","display_name":"Charles L. Isbell","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Lee Isbell","raw_affiliation_strings":["Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061883150","display_name":"Mark Riedl","orcid":"https://orcid.org/0000-0001-5283-6588"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Riedl","raw_affiliation_strings":["Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066797327","display_name":"Andrea L. Thomaz","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Thomaz","raw_affiliation_strings":["Department of College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Department of College of Computing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5083083220"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":14.1352,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.98824044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"9","issue":"1","first_page":"44","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.9047592282295227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8364918231964111},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6292576789855957},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5951446890830994},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5925045013427734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.552161455154419},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.485110878944397},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4479154050350189},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4272170066833496},{"id":"https://openalex.org/keywords/software-agent","display_name":"Software agent","score":0.42654505372047424}],"concepts":[{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.9047592282295227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8364918231964111},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6292576789855957},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5951446890830994},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5925045013427734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.552161455154419},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.485110878944397},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4479154050350189},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4272170066833496},{"id":"https://openalex.org/C5894958","wikidata":"https://www.wikidata.org/wiki/Q2297769","display_name":"Software agent","level":2,"score":0.42654505372047424},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2016.2628365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2016.2628365","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8207089012","display_name":null,"funder_award_id":"N000141410003","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W186800770","https://openalex.org/W1970443370","https://openalex.org/W1986014385","https://openalex.org/W1996847178","https://openalex.org/W1999874108","https://openalex.org/W2031485535","https://openalex.org/W2086661052","https://openalex.org/W2098441518","https://openalex.org/W2101355568","https://openalex.org/W2122982548","https://openalex.org/W2123442489","https://openalex.org/W2140584963","https://openalex.org/W2150818585","https://openalex.org/W2163455955","https://openalex.org/W2251939518","https://openalex.org/W2257058996","https://openalex.org/W2277684984","https://openalex.org/W2402989524","https://openalex.org/W2530958810","https://openalex.org/W4205184193","https://openalex.org/W4211133235","https://openalex.org/W4214717370","https://openalex.org/W6607578298","https://openalex.org/W6674812091","https://openalex.org/W6678200026","https://openalex.org/W6691459498","https://openalex.org/W6728636380"],"related_works":["https://openalex.org/W4393601209","https://openalex.org/W4404663548","https://openalex.org/W3090906284","https://openalex.org/W253876680","https://openalex.org/W4393803066","https://openalex.org/W1987931999","https://openalex.org/W4293797372","https://openalex.org/W4238052600","https://openalex.org/W4254639292","https://openalex.org/W3005176110"],"abstract_inverted_index":{"In":[0],"order":[1],"for":[2],"robots":[3,13],"to":[4,29,52,62,70,79,91,98,104,110,129,163,185],"learn":[5,15,80,130],"from":[6,16,65,82,172],"people":[7,28],"with":[8,120],"no":[9,155],"machine":[10,21],"learning":[11,22,64,124],"expertise,":[12],"should":[14,116,182],"natural":[17],"human":[18,192],"instruction.":[19],"Most":[20],"techniques":[23],"that":[24,50,132],"incorporate":[25],"explanations":[26,66,72,93],"require":[27],"use":[30],"a":[31,47,143],"limited":[32],"vocabulary":[33],"and":[34,75,77,100,167],"provide":[35],"state":[36,85],"information,":[37],"even":[38],"if":[39],"it":[40],"is":[41],"not":[42],"intuitive.":[43],"This":[44],"paper":[45],"discusses":[46],"software":[48],"agent":[49,115,125,160,169],"learned":[51,161],"play":[53],"the":[54,114,159,165,168,178,187,191,195],"Mario":[55],"Bros.":[56],"game":[57],"using":[58,140],"explanations.":[59],"Our":[60],"goals":[61],"improve":[63],"were":[67],"twofold:":[68],"(1)":[69],"filter":[71,92,144],"into":[73,94],"advice":[74,95,109,128,150,156,196],"warnings":[76,101],"(2)":[78],"policies":[81,131],"sentences":[83],"without":[84],"information.":[86],"We":[87,106,175],"used":[88,126],"sentiment":[89,141],"analysis":[90],"of":[96,102,180,190,199],"what":[97,103,112],"do":[99],"avoid.":[105],"developed":[107],"object-focused":[108,127,149],"represent":[111],"actions":[113],"take":[117],"when":[118,154],"dealing":[119],"objects.":[121],"A":[122],"reinforcement":[123],"maximized":[133],"its":[134],"reward.":[135],"After":[136],"mitigating":[137],"false":[138],"negatives,":[139],"as":[142],"was":[145,157],"approximately":[146],"85%":[147],"accurate.":[148],"performed":[151],"better":[152],"than":[153],"given,":[158],"where":[162],"apply":[164],"advice,":[166],"could":[170],"recover":[171],"adversarial":[173],"advice.":[174],"also":[176],"found":[177],"method":[179],"interaction":[181],"be":[183,198],"designed":[184],"ease":[186],"cognitive":[188],"load":[189],"teacher":[193],"or":[194],"may":[197],"poor":[200],"quality.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":18},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}