{"id":"https://openalex.org/W2793753262","doi":"https://doi.org/10.1145/3173386.3177074","title":"Using Human Reinforcement Learning Models to Improve Robots as Teachers","display_name":"Using Human Reinforcement Learning Models to Improve Robots as Teachers","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2793753262","doi":"https://doi.org/10.1145/3173386.3177074","mag":"2793753262"},"language":"en","primary_location":{"id":"doi:10.1145/3173386.3177074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3173386.3177074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-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/A5054362444","display_name":"Sayanti Roy","orcid":"https://orcid.org/0000-0002-5963-0918"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sayanti Roy","raw_affiliation_strings":["Oklahoma State University, Stillwater, OK, USA"],"affiliations":[{"raw_affiliation_string":"Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084822677","display_name":"Emily Kieson","orcid":"https://orcid.org/0000-0002-0858-1343"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emily Kieson","raw_affiliation_strings":["Oklahoma State University, Stillwater, OK, USA"],"affiliations":[{"raw_affiliation_string":"Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063948391","display_name":"Charles I. Abramson","orcid":"https://orcid.org/0000-0001-8961-3089"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Abramson","raw_affiliation_strings":["Oklahoma State University, Stillwater, OK, USA"],"affiliations":[{"raw_affiliation_string":"Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014357711","display_name":"Christopher Crick","orcid":"https://orcid.org/0000-0002-1635-823X"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Crick","raw_affiliation_strings":["Oklahoma State University, Stillwater, OK, USA"],"affiliations":[{"raw_affiliation_string":"Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054362444"],"corresponding_institution_ids":["https://openalex.org/I115475287"],"apc_list":null,"apc_paid":null,"fwci":1.1402,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8322306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.995199978351593,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8756130933761597},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.7927054166793823},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7052857279777527},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6950369477272034},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6566049456596375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6386363506317139},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5160155296325684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5029014945030212},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4958549439907074},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44776707887649536},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.446260929107666},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4206130802631378},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16476121544837952},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15387362241744995},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07709929347038269}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8756130933761597},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.7927054166793823},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7052857279777527},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6950369477272034},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6566049456596375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6386363506317139},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5160155296325684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029014945030212},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4958549439907074},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44776707887649536},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.446260929107666},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4206130802631378},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16476121544837952},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15387362241744995},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07709929347038269},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3173386.3177074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3173386.3177074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5441948728","display_name":null,"funder_award_id":"1527828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1900701192","https://openalex.org/W2061181234","https://openalex.org/W2121110499","https://openalex.org/W2593471787","https://openalex.org/W2772033479"],"related_works":["https://openalex.org/W4293926484","https://openalex.org/W2559881192","https://openalex.org/W4388624165","https://openalex.org/W2586362452","https://openalex.org/W2621386530","https://openalex.org/W2148892780","https://openalex.org/W2099069812","https://openalex.org/W3097029141","https://openalex.org/W2159606325","https://openalex.org/W2157119315"],"abstract_inverted_index":{"Robotic":[0],"teaching":[1,42],"has":[2],"not":[3],"received":[4],"nearly":[5],"as":[6,10,44],"much":[7],"research":[8],"attention":[9],"robotic":[11],"learning.":[12],"In":[13],"this":[14],"research,":[15],"we":[16],"used":[17],"the":[18,41,48,53],"humanoid":[19],"robot":[20,38],"Baxter":[21],"to":[22,28,32,51],"provide":[23],"feedback":[24],"and":[25,60,77],"positive":[26],"reinforcement":[27,70],"human":[29,58],"participants":[30],"attempting":[31],"achieve":[33],"a":[34,73,79],"complex":[35],"task.":[36],"Our":[37],"autonomously":[39],"casts":[40],"problem":[43],"one":[45],"that":[46],"invokes":[47],"exploration/exploitation":[49],"tradeoff":[50],"understand":[52],"cognitive":[54],"strategy":[55],"of":[56],"its":[57],"partner":[59],"develop":[61],"an":[62],"effective":[63],"motivational":[64],"approach.":[65],"We":[66],"compare":[67],"our":[68],"learned":[69],"model":[71],"with":[72,78],"baseline":[74],"non-reinforcement":[75],"approach":[76],"random":[80],"reinforcer.":[81]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}