{"id":"https://openalex.org/W2909911836","doi":"https://doi.org/10.1109/iros.2018.8594312","title":"Policy Shaping with Supervisory Attention Driven Exploration","display_name":"Policy Shaping with Supervisory Attention Driven Exploration","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2909911836","doi":"https://doi.org/10.1109/iros.2018.8594312","mag":"2909911836"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8594312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052769867","display_name":"Taylor Kessler Faulkner","orcid":"https://orcid.org/0000-0002-5838-0021"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Kessler Faulkner","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077011363","display_name":"Elaine Schaertl Short","orcid":"https://orcid.org/0000-0002-4789-9979"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaine Schaertl Short","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066797327","display_name":"Andrea L. Thomaz","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrea Lockerd Thomaz","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"842","last_page":"847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8819773197174072},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7374405860900879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7334344983100891},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5652350187301636},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5082966685295105},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4760584533214569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4586714208126068},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.42957961559295654},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13260042667388916},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07929426431655884}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8819773197174072},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7374405860900879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7334344983100891},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5652350187301636},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5082966685295105},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4760584533214569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4586714208126068},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.42957961559295654},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13260042667388916},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07929426431655884},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8594312","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8594312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1740158594","https://openalex.org/W1969784320","https://openalex.org/W2034806191","https://openalex.org/W2084624217","https://openalex.org/W2091417852","https://openalex.org/W2096284813","https://openalex.org/W2098441518","https://openalex.org/W2099840956","https://openalex.org/W2105410877","https://openalex.org/W2105457610","https://openalex.org/W2110064869","https://openalex.org/W2121110499","https://openalex.org/W2139612737","https://openalex.org/W2159758967","https://openalex.org/W2160434794","https://openalex.org/W2290053245","https://openalex.org/W2540886653","https://openalex.org/W2593766708","https://openalex.org/W2739254393","https://openalex.org/W2758952034","https://openalex.org/W3143996792","https://openalex.org/W4297791094","https://openalex.org/W4299566536","https://openalex.org/W6637712497","https://openalex.org/W6674812091","https://openalex.org/W6676237905","https://openalex.org/W6696265566"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W2391666574","https://openalex.org/W2786230833","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1493952344","https://openalex.org/W4312372616","https://openalex.org/W8539471"],"abstract_inverted_index":{"Robots":[0],"deployed":[1],"for":[2],"long":[3],"periods":[4],"of":[5,87],"time":[6],"need":[7],"to":[8,11,20,39,75,84,154],"be":[9],"able":[10],"explore":[12],"and":[13,112,128,141],"learn":[14],"from":[15,33,56],"their":[16],"environment.":[17],"One":[18],"approach":[19,62,100,124],"this":[21,61],"problem":[22],"has":[23],"been":[24],"reinforcement":[25,52,89],"learning":[26,45,53,66],"(RL),":[27],"in":[28,77,125],"which":[29,72],"robots":[30],"receive":[31],"rewards":[32],"the":[34,155],"environment":[35],"that":[36,65,93,114,133],"allow":[37],"them":[38],"choose":[40],"optimal":[41],"actions.":[42],"To":[43],"speed":[44],"when":[46,110,119],"human":[47,58,97],"supervision":[48],"is":[49,73,151],"available,":[50],"interactive":[51,88],"solicits":[54],"feedback":[55,118],"a":[57,85,130],"teacher.":[59],"However,":[60],"typically":[63],"assumes":[64],"takes":[67,94],"place":[68],"under":[69],"continuous":[70],"supervision,":[71],"unlikely":[74],"hold":[76],"long-term":[78],"scenarios.":[79],"We":[80,121],"propose":[81],"an":[82],"extension":[83],"method":[86,135],"learning,":[90],"policy":[91,139,146],"shaping,":[92],"into":[95],"account":[96],"attention.":[98],"Our":[99],"enables":[101],"better":[102],"performance":[103],"while":[104,148],"unattended":[105],"by":[106],"favoring":[107],"information-gathering":[108],"actions":[109,113],"attended":[111],"have":[115],"received":[116],"positive":[117],"unattended.":[120],"test":[122],"our":[123,134],"both":[126],"simulation":[127],"on":[129],"robot,":[131],"finding":[132],"learns":[136],"faster":[137],"than":[138,145],"shaping":[140,147],"performs":[142],"more":[143],"safely":[144],"no":[149],"one":[150],"paying":[152],"attention":[153],"robot.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}