{"id":"https://openalex.org/W4313005643","doi":"https://doi.org/10.1109/hri53351.2022.9889498","title":"Learning Reward Functions from a Combination of Demonstration and Evaluative Feedback","display_name":"Learning Reward Functions from a Combination of Demonstration and Evaluative Feedback","publication_year":2022,"publication_date":"2022-03-07","ids":{"openalex":"https://openalex.org/W4313005643","doi":"https://doi.org/10.1109/hri53351.2022.9889498"},"language":"en","primary_location":{"id":"doi:10.1109/hri53351.2022.9889498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri53351.2022.9889498","pdf_url":null,"source":{"id":"https://openalex.org/S4363607950","display_name":"2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","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/A5028560428","display_name":"Eric Hsiung","orcid":null},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Hsiung","raw_affiliation_strings":["Brown University,Providence,RI","Brown University, Providence, RI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University,Providence,RI","institution_ids":["https://openalex.org/I27804330"]},{"raw_affiliation_string":"Brown University, Providence, RI","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046853629","display_name":"Eric Rosen","orcid":"https://orcid.org/0000-0002-0223-4324"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Rosen","raw_affiliation_strings":["Brown University,Providence,RI","Brown University, Providence, RI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University,Providence,RI","institution_ids":["https://openalex.org/I27804330"]},{"raw_affiliation_string":"Brown University, Providence, RI","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064997007","display_name":"Vivienne Bihe","orcid":"https://orcid.org/0000-0002-2425-0317"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivienne Bihe Chi","raw_affiliation_strings":["Brown University,Providence,RI","Brown University, Providence, RI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University,Providence,RI","institution_ids":["https://openalex.org/I27804330"]},{"raw_affiliation_string":"Brown University, Providence, RI","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090962780","display_name":"Bertram F. Malle","orcid":"https://orcid.org/0000-0003-0845-9601"},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bertram F. Malle","raw_affiliation_strings":["Brown University,Providence,RI","Brown University, Providence, RI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University,Providence,RI","institution_ids":["https://openalex.org/I27804330"]},{"raw_affiliation_string":"Brown University, Providence, RI","institution_ids":["https://openalex.org/I27804330"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":0.6228,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.68592632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"807","last_page":"811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9848999977111816,"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/computer-science","display_name":"Computer science","score":0.6815891265869141},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6637378931045532},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6552579998970032},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6376944780349731},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5765778422355652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5137661695480347},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.5098954439163208},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12429684400558472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6815891265869141},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6637378931045532},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6552579998970032},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6376944780349731},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5765778422355652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5137661695480347},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.5098954439163208},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12429684400558472},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hri53351.2022.9889498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri53351.2022.9889498","pdf_url":null,"source":{"id":"https://openalex.org/S4363607950","display_name":"2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1591675293","https://openalex.org/W1999874108","https://openalex.org/W2037552959","https://openalex.org/W2062531735","https://openalex.org/W2064673991","https://openalex.org/W2114864106","https://openalex.org/W2155872498","https://openalex.org/W2735318784","https://openalex.org/W2900406861","https://openalex.org/W2945159000","https://openalex.org/W2945642643","https://openalex.org/W2963308241","https://openalex.org/W2964177756","https://openalex.org/W2966120739","https://openalex.org/W3000002597","https://openalex.org/W3006303816","https://openalex.org/W3038092671","https://openalex.org/W3041202696","https://openalex.org/W3048196125","https://openalex.org/W3173852058","https://openalex.org/W4300110528","https://openalex.org/W4312740067","https://openalex.org/W6635261211","https://openalex.org/W6732417791","https://openalex.org/W6762358693","https://openalex.org/W6774122581","https://openalex.org/W6780298458"],"related_works":["https://openalex.org/W8302103","https://openalex.org/W3171631314","https://openalex.org/W2674584172","https://openalex.org/W2967743314","https://openalex.org/W2606825221","https://openalex.org/W2184085865","https://openalex.org/W3213722473","https://openalex.org/W2110944602","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"As":[0],"robots":[1,27],"become":[2],"more":[3],"prevalent":[4],"in":[5,81],"society,":[6],"they":[7],"will":[8],"need":[9],"to":[10,12,77],"learn":[11,68],"act":[13],"appropriately":[14],"under":[15],"diverse":[16],"human":[17],"teaching":[18,26,35,48],"styles.":[19],"We":[20,59],"present":[21],"a":[22,32,62,82],"human-centered":[23],"approach":[24],"for":[25,50],"reward":[28],"functions":[29],"by":[30],"using":[31],"mixture":[33],"of":[34,75],"strategies":[36,49,76],"when":[37],"communicating":[38],"action":[39,53],"appropriateness":[40],"and":[41,55],"goal":[42],"success.":[43],"Our":[44],"method":[45,66],"incorporates":[46],"two":[47],"learning:":[51],"explicit":[52],"instruction":[54],"evaluative,":[56],"scalar-based":[57],"feedback.":[58],"demonstrate":[60],"that":[61,86],"robot":[63,80],"instantiating":[64],"our":[65],"can":[67],"from":[69],"humans":[70],"who":[71],"use":[72],"both":[73],"kinds":[74],"train":[78],"the":[79],"complex":[83],"navigation":[84],"task":[85],"includes":[87],"norm-like":[88],"constraints.":[89]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}